Workflow YAML reference
Define when Shipfox runs and what each workflow does.
Each section lists the fields for one part of a workflow YAML file and highlights that part in an example.
Enable editor autocomplete
Add # yaml-language-server: $schema=https://www.shipfox.io/docs/workflow.schema.json
as the first line of a workflow file.
Workflow
namestringRequiredNames the workflow.
Use a literal value. Workflow expressions are not allowed.
run_namestringNames each workflow run. Supports workflow expressions.
triggersRecord<string, Trigger>Defines the events that start the workflow. Add no more than one
manualtrigger.concurrencyConcurrencyLimits each group to one active run and the newest waiting run. See Workflow concurrency groups.
runnerstring | string[]Selects the default runner for jobs in this workflow. List labels in fallback order. See Runners and execution environments.
envEnvironmentSets environment variables for run steps in every job.
jobsRecord<string, Job>RequiredDefines the jobs that the workflow runs. Add at least one job.
outputsRecord<string, string>Creates named outputs from job outputs when a run succeeds. An output that cannot be evaluated fails the run.
name: Deploy
run_name: Deploy ${{ event.ref }}
triggers:
push:
source: github_acme
event: push
concurrency:
group: deploy-${{ event.ref }}
runner: shipfox
env:
NODE_ENV: production
jobs:
deploy:
steps:
- key: deploy
run: echo "url=https://example.com" >> "$SHIPFOX_OUTPUT"
outputs:
url: string
outputs:
url: ${{ steps.deploy.outputs.url }}
outputs:
url: ${{ jobs.deploy.outputs.url }}
triggers.<trigger_id>
sourcestringRequiredSelects the slug of an integration connection or a built-in source that starts the workflow. See Integrations for provider sources.
eventstringSelects the event that starts the workflow. Omit it to accept every event from the source.
filterstringStarts the workflow only when an event matches this condition. The condition can use
eventandtrigger.manualandcrontriggers do not use this field. See Expressions and Contexts.withRecord<string, value>Provides values that match or configure the trigger. See each provider's event catalog in Integrations.
secretsRecord<string, value>Maps trigger input names to secret names in the Shipfox project.
configRecord<string, value>Configures a built-in trigger source, such as
cron. See Schedule workflows.
name: Review pull requests
triggers:
ready:
source: github_acme
event: pull_request.ready_for_review
filter: event.pull_request.base.ref == "main"
secrets:
REVIEW_TOKEN: REVIEW_TOKEN
nightly:
source: cron
with:
suite: full
config:
schedule: "0 2 * * *"
jobs:
review:
steps:
- prompt: Review the change and report the main risks.
concurrency
groupstringRequiredNames the group. Runs with the same group name wait for each other. Supports workflow expressions. See Contexts.
scopeenumDefaultworkflowChooses whether the group applies to this workflow or every workflow in the project.
workflowproject
cancel_in_progressbooleanDefaultfalseSet to
trueto stop the active run when a newer run joins the group.
name: Deploy
concurrency:
group: deploy-${{ event.ref }}
scope: project
cancel_in_progress: true
triggers:
push:
source: github_acme
event: push
jobs:
deploy:
steps:
- run: ./deploy.sh
env
<NAME>string | number | booleanDefines one environment variable. Values support workflow expressions.
Use letters, numbers, and underscores. Start with a letter or underscore.
name: Build
env:
NODE_ENV: production
CI: true
jobs:
build:
env:
PORT: 3000
steps:
- run: pnpm build
env:
LOG_LEVEL: debug
jobs.<job_id>
namestringNames the job.
Use a literal value. Workflow expressions are not allowed.
execution_namestringSets the name of each job execution. Supports workflow expressions.
needsstring | string[]Lists the jobs that must finish before this job starts.
ifstringRuns this job only when the condition is true. See Conditionals.
run_afterenumPicks when this job runs relative to the jobs in
needs:success(default) needs every job to succeed,failureneeds at least one job to fail,alwaysruns whatever their status. Theifis checked afterrun_afterpasses.successfailurealways
runnerstring | string[]Selects the runner for this job. List labels in fallback order. See Runners and execution environments.
containerstring | JobContainerRuns this job in a Docker container. Set a string for the image, or an object for the image and its settings.
execution_timeoutstringStops one job execution after this duration.
envEnvironmentSets environment variables for every run step in this job.
checkoutJobCheckoutConfigures repository permissions and saved credentials for the project checkout at the job root. Set to
falseto skip that checkout.listeningListeningKeeps the job open for matching events. Set
until,timeout, ormax_executionsto end it. See Listening jobs.stepsStep[]RequiredLists the steps of this job. Each step starts after the step before it ends, unless that step runs in the background or in a
parallelblock.Add at least one item.
successstringMarks the job as successful when the condition returns
true. See Expressions and Contexts.outputsRecord<string, string>Creates named outputs from values produced by this job's steps. A later job must list this job in
needsbefore it can use them.
name: Build and release
jobs:
build:
name: Build
runner: shipfox
execution_timeout: 30m
env:
NODE_ENV: production
steps:
- key: pkg
run: printf 'version=%s\n' "$(cat VERSION)" >> "$SHIPFOX_OUTPUT"
outputs:
version: string
outputs:
version: ${{ steps.pkg.outputs.version }}
release:
execution_name: Release ${{ jobs.build.outputs.version }}
needs: build
if: ${{ event.ref == "refs/heads/main" }}
steps:
- key: publish
run: ./publish.sh "${{ jobs.build.outputs.version }}"
success: ${{ steps.publish.status == "succeeded" }}
jobs.<job_id>.container
imagestringRequiredNames the Docker image the job runs in. The
ENTRYPOINTandCMDof the image do not run. Supports workflow expressions, but cannot read secrets.credentials{username: string; password: string}Signs in to a private registry before the runner pulls the image.
envEnvironmentSets environment variables for every process in the container.
optionsstringPasses extra flags to
docker create, as written. Do not set--networkor--entrypoint: the runner sets them. Supports workflow expressions, but cannot read secrets.docker_socketbooleanDefaulttrueMounts the Docker socket of the runner into the container. Defaults to
true.
name: Lint with the toolbox image
jobs:
lint:
runner: shipfox
container:
image: ghcr.io/acme/toolbox:2026.10
credentials:
username: acme-bot
password: ${{ secrets.GHCR_TOKEN }}
env:
LICENSE_KEY: ${{ secrets.TOOLBOX_LICENSE }}
options: --cpus 4 --memory 12g
docker_socket: false
steps:
- run: acme-lint --strict
jobs.<job_id>.checkout
permissionsCheckoutPermissionsSets the repository permissions for this checkout.
persist-credentialsbooleanKeeps checkout credentials available to later run steps.
name: Push a fix
jobs:
fix:
checkout:
permissions:
contents: write
persist-credentials: true
steps:
- prompt: Fix the failing test and commit the change.
- run: git push origin HEAD
jobs.<job_id>.listening
onTrigger[]RequiredSelects the events to listen for.
Add at least one item.
untilTrigger[]Stops listening when one of these events arrives.
Add at least one item.
timeoutstringStops listening after this duration.
max_executionsintegerStops listening after this many job executions.
Use a number greater than 0.
batchListeningBatchGroups matching events before the job processes them. Set
debounce,max_size, ormax_wait.on_resolveenumChooses what Shipfox does when listening ends.
finishlets the current execution finish.cancelstops it.finishcancel
name: Answer review comments
jobs:
answer:
listening:
on:
- source: github_acme
event: pull_request_review_comment.created
until:
- source: github_acme
event: pull_request.closed
timeout: 8h
max_executions: 10
on_resolve: finish
steps:
- prompt: Answer the review comment in the step log.
jobs.<job_id>.listening.batch
debouncestringWaits for this quiet period before processing a batch.
max_sizeintegerLimits each batch to this number of events.
Use a number greater than 0.
max_waitstringProcesses a partial batch after this duration.
name: Summarize review comments
jobs:
summarize:
listening:
on:
- source: github_acme
event: pull_request_review_comment.created
timeout: 8h
batch:
debounce: 30s
max_size: 5
max_wait: 2m
steps:
- prompt: Summarize the comments in this batch.
jobs.<job_id>.steps[*]
keystringGives the step an identifier that other fields can use.
namestringSets the name shown for the step.
ifstringRuns this step only when the condition is true. See Conditionals.
run_afterenumPicks when this step runs relative to earlier steps in the job:
success(default) skips it after a failed step,failureruns it only after a failed step,alwaysruns it either way. Theifis checked afterrun_afterpasses.successfailurealways
continue_on_errorbooleanLets the job go on as if this step succeeded when it fails. The step still ends
failed, but its failure does not count forrun_afteror for the job result. Gate restarts run first. It does not cover a step that cannot start or a job that times out.backgroundbooleanStarts the step and moves on to the next step without waiting. The step needs a
key. Later steps read its results after awaitthat joins it.waitstring | string[]Blocks until the listed background steps finish. Give one step
keyor a list. A wait step accepts onlyname.wait_allnull | booleanBlocks until every background step that is still running finishes. Write
wait_all:orwait_all: true. A wait step accepts onlyname.cancelstring | string[]Stops the listed background steps without waiting for them to finish. Give one step
keyor a list. A cancel step accepts onlyname.gateGateChecks the step result and can restart earlier steps. Set
success,on_failure, or both. See Feedback loops.outputsRecord<string, Output>Defines values that later steps can use.
exporttrue | string[]Promotes outputs of this step to job outputs of the same name. Use
truefor every declared output, or list the output names. The step needs akey. Checkout steps do not support it.
name: Test
jobs:
test:
steps:
- key: db
background: true
run: docker run --rm --name pg -p 5432:5432 -e POSTGRES_PASSWORD=pg postgres:17
- key: unit
name: Unit tests
if: ${{ event.pull_request.draft == false }}
run: pnpm test
gate:
success: step.exit_code == 0
outputs:
coverage: number
export: true
- cancel: db
steps[*].gate
successstringMarks the step as successful when the condition returns
true. See Check and restart are separate.on_failureGateFailure | GateFailure[]Restarts the job from an earlier step when the gate fails. Give one rule, or a list of rules where the first rule that applies restarts the job. See Feedback loops.
name: Fix until tests pass
jobs:
fix:
steps:
- key: fix
prompt: Fix the failing test.
- key: test
run: pnpm test
gate:
success: step.exit_code == 0
on_failure:
restart_from: fix
steps[*].gate.on_failure
ifstringSelects this rule when the condition returns
true. A rule with noifalways applies, so only the last rule can omit it. The condition reads the same context assuccess, includingstep.outputs. Usehas()before you read an output the step may not set. When no rule applies, the job fails with the error of the step.restart_fromstringRequiredSelects the earlier step where the job restarts after the gate fails.
feedbackstringProvides text that the repeated step can read after the gate fails. Supports workflow expressions.
max_attemptsintegerDefault5Maximum number of executions of the gating step, including the first execution. Accepts integers from 1 through 1,000. Omit to use five attempts. There is no
unlimitedvalue.Use 1 or a larger number. Use 1000 or a smaller number.
name: Fix until tests pass
jobs:
fix:
steps:
- key: install
run: pnpm install
- key: fix
prompt: Fix the failing test.
- key: test
run: ./scripts/test.sh # writes failure-kind.txt when the tests fail
outputs:
failure_kind:
type: string
from_file: failure-kind.txt
gate:
on_failure:
- if: has(step.outputs.failure_kind) && step.outputs.failure_kind == "assertion"
restart_from: fix
feedback: The tests still fail. Reproduce the failure first.
- if: has(step.outputs.failure_kind) && step.outputs.failure_kind == "flaky"
restart_from: install
max_attempts: 2
steps[*].outputs
<output_name>string | number | boolean | json | {type: string | number | boolean; default?: value; from_file?: string; from_stdout?: true} | {type: json; schema?: value; default?: value; from_file?: string; from_stdout?: true}Defines an output from the step. Set its type directly, for example
sha: string, or use an object withtype. Onlyjsonoutputs can includeschema. Withoutschema, ajsonoutput can contain any JSON value. Run and agent steps can adddefault, which later steps read when the step has no value for the output, for example when it is skipped. The default must match the type andschema. Only run steps supportfrom_fileandfrom_stdout; agent and checkout steps reject them.from_filereads the output from a file after the command exits, andfrom_stdoutreads it from standard output. A file path is relative to the step working directory and must stay inside the job workspace. A missing file leaves the output unset. Standard output and each file are limited to 64 KiB, and one trailing newline is removed. An output usesfrom_fileorfrom_stdout, not both, and a step has at most onefrom_stdoutoutput.
name: Publish outputs
jobs:
build:
steps:
- key: revision
run: git rev-parse HEAD
outputs:
commit:
type: string
from_stdout: true
- key: version
run: printf 'sha=%s\ncount=3\n' "$(git rev-parse HEAD)" >> "$SHIPFOX_OUTPUT"
outputs:
sha: string
count: number
report:
type: json
schema:
type: object
outcome:
type: string
default: none
- key: package
run: git diff --cached --binary > .git/shipfox-repair.patch
outputs:
patch:
type: string
from_file: .git/shipfox-repair.patch
steps[*] run step
Accepts the shared step fields plus:
runstringRequiredRuns a shell command. Pass workflow values as command arguments, such as
deploy "$TARGET". Do not send them to commands such asevalorsh -c.working_directorystringSets the folder where the command runs. The path is relative to the job workspace.
envEnvironmentSets environment variables for this run step.
name: Build
jobs:
build:
steps:
- key: compile
run: |
pnpm install --frozen-lockfile
pnpm build
working_directory: apps/api
env:
NODE_ENV: production
steps[*] agent step
Accepts the shared step fields plus:
promptstring | PromptPart[]RequiredGives the agent its instructions. Use a string, or a list of parts that Shipfox joins with a blank line. A part is a string or a
filereference.harnessenumSelects the agent runtime. Shipfox uses the workspace default harness, or
piif no default exists. See Agent harness.piclaude
providerstringSelects the model provider for this step. See Model providers.
modelstringSelects the model that the agent uses.
thinkingenum | expressionSets agent reasoning.
defaultrequests the provider default without workspace or deployment overrides. Omitting this field uses configured defaults orxhigh. Available values depend on the harness. Supports workflow expressions. See Model providers.offminimallowmediumhighxhighmaxdefault
toolsstring[]Gives the agent the listed built-in tools.
Add at least one item.
integrationsIntegration[]Adds tools from integration connections to this agent step. See integrations and tools.
Add at least one item.
mcp_serversRecord<string, McpServer>Gives the agent the tools of these MCP servers as
<name>__<tool>. The runner starts eachcommandserver for the step and connects to eachurlserver. Each key is a server name: a lowercase letter, then lowercase letters, numbers, and single underscores, with at most 20 characters. See Use your own MCP server.tool_surfaceenumIntegration tool surface for an agent step. Strict direct tools are the default; discovery retains the generic mcp proxy.
strict-directdiscovery
sessionstring | SessionContinues an agent conversation across steps in one workflow run. See Agent sessions.
Use letters, numbers, dots, underscores, or hyphens. Start with a letter or number. Use at most 128 characters.
repository_contextboolean | string | RepositoryContextDefaulttrueControls the repository instructions and skills that the agent reads. Set to
falseto turn both off, or setinstructionsandskillsseparately. See Coding agents.
name: Review
jobs:
review:
steps:
- key: review
prompt: Review the change and report the main risks.
harness: claude
provider: anthropic
model: claude-sonnet-5
thinking: high
tools: [read_file]
integrations:
- include: [pull_request_read]
session: review
steps[*].integrations[*]
connectionstringSelects an integration connection by its slug.
includestring[]RequiredSelects tools for the agent. See Integrations for each provider's selectors.
Add at least one item.
excludestring[]Removes tools from the
includeselection.Add at least one item.
name: Triage issues
jobs:
triage:
steps:
- prompt: Label the issue and post a short triage comment.
integrations:
- connection: github_acme
include: [issue_read, issue_write]
exclude: [issue_write.update]
steps[*].mcp_servers.<name>
commandstringNames the program that starts the server. It runs without a shell. Set
commandorurl, not both.Use a literal value. Workflow expressions are not allowed.
argsstring[]Passes these arguments to
command. Workflow expressions are not allowed; useenvfor values.envEnvironmentSets environment variables for the
commandserver. Values support workflow expressions, includingsecrets.urlstringConnects to a server that you run, over Streamable HTTP. An
httporhttpsURL that the runner can reach. Setcommandorurl, not both.Use a literal value. Workflow expressions are not allowed.
headersRecord<string, string>Sends these HTTP headers to the
urlserver with every request. Values support workflow expressions, includingsecrets.includestring[]Lists the tools to give the agent, named as the server lists them. Defaults to every tool.
Add at least one item.
name: Investigate slow queries
jobs:
investigate:
steps:
- prompt: Find the slowest queries on the orders collection.
mcp_servers:
mongodb:
command: npx
args: [-y, mongodb-mcp-server@1.2.0]
env:
MDB_MCP_CONNECTION_STRING: ${{ secrets.MONGO_URI }}
MDB_MCP_READ_ONLY: "true"
include: [find, aggregate, list-collections, explain]
internal_docs:
url: http://127.0.0.1:3000/mcp
headers:
Authorization: Bearer ${{ secrets.DOCS_MCP_TOKEN }}
steps[*].session
keystringRequiredNames the session. Supports a ${{ }} expression.
Use letters, numbers, dots, underscores, or hyphens. Start with a letter or number. Use at most 128 characters.
modeenumDefaultresumeChooses how to continue the session.
resumecontinues and updates it.forkreads a snapshot without updating it.resumefork
name: Review
jobs:
review:
steps:
- key: draft
prompt: Review the diff and note the main risks.
session: review
- key: summary
prompt: Summarize your findings for the author.
session:
key: review
mode: fork
steps[*].repository_context
instructionsboolean | stringDefaulttrueReads
AGENTS.mdorCLAUDE.mdfrom the runner home directory and from the repository root down to the working directory. Supports a ${{ }} expression.skillsboolean | string | string[]DefaulttrueLoads skills from the skill directories of mainstream coding agents, such as
.agents/skillsand.claude/skills, in the repository and in the runner home directory. Usetrue,false, a ${{ }} expression, or a list of skill names.
name: Review
jobs:
review:
steps:
- prompt: Review the pull request and list the main risks.
repository_context:
instructions: true
skills: [code-review]
steps[*] tool step
toolstringRequiredCalls an integration tool by its id. Use a standalone tool or a family method such as
family.method. See Call an integration tool for an example.Use a literal value. Workflow expressions are not allowed.
connectionstringSelects an integration connection by its slug. If omitted, Shipfox uses the source integration connection of the project.
Use a literal value. Workflow expressions are not allowed.
withRecord<string, value>Provides input values to the tool. The tool defines the accepted fields. String values support workflow expressions. See Context availability.
name: Notify
jobs:
notify:
steps:
- key: message
tool: send_message
connection: slack_acme
with:
channel_id: C0ABC12345
message: Run ${{ run.number }} started.
outputs:
ts: ${{ result.ts }}
steps[*].outputs tool step
<output_name>stringCreates an output from the tool response or a workflow variable. Use one workflow expression. Later steps can read the full response from
steps.<key>.outputs.result.
name: Notify
jobs:
notify:
steps:
- key: message
tool: send_message
connection: slack_acme
with:
channel_id: C0ABC12345
message: Run ${{ run.number }} started.
outputs:
ts: ${{ result.ts }}
channel: ${{ result.channel }}
- env:
MESSAGE_TS: ${{ steps.message.outputs.ts }}
run: printf 'Posted %s\n' "$MESSAGE_TS"
steps[*] checkout step
Accepts the shared step fields plus:
checkoutCheckoutRequiredChecks out a repository for this step. Set a non-root
pathto keep the project checkout at the job root.
name: Compare branches
jobs:
compare:
steps:
- key: base
checkout:
ref: main
path: base
- run: |
diff -rq --exclude=.git base . | grep -vxF 'Only in .: base' || true
steps[*].checkout
projectstringChecks out the repository from this Shipfox project. Do not use it with
connectionorrepository.connectionstringSelects the integration connection that can access the repository. Use it with
repository.repositorystringNames the repository to check out. Use
owner/nameor a bare repository name.refstringSelects the branch, tag, or commit to check out.
pathstringSets the destination folder under the job root. Required unless this checkout owns the job root.
fetch-depthintegerSets how many commits to fetch. Use
0for the full history.Use 0 or a larger number.
forcebooleanAllows checkout to replace existing content at the destination.
permissionsCheckoutPermissionsSets the repository permissions for this checkout.
persist-credentialsbooleanKeeps checkout credentials available to later run steps.
name: Check out a second repository
jobs:
docs:
steps:
- checkout:
connection: github_acme
repository: acme/docs
ref: main
path: docs
fetch-depth: 1
force: true
permissions:
contents: read
persist-credentials: false
- run: ls docs
steps[*].checkout.permissions
contentsenumSets read or write access to the repository contents.
readwrite
name: Push docs changes
jobs:
docs:
steps:
- checkout:
connection: github_acme
repository: acme/docs
path: docs
permissions:
contents: write
persist-credentials: true
- run: git -C docs push origin HEAD
steps[*] parallel block
A parallel block is an item of steps that holds only the parallel field.
Each item of its list is a step with the shared step fields.
parallelStep[]RequiredRuns the listed steps at the same time, then waits for all of them. It is shorthand for marking each step
background: trueand adding awaitthat names exactly those steps. A step needs nokey, but without one its outputs are not readable.Add at least 2 items.
name: Test
jobs:
test:
steps:
- run: npm ci
- parallel:
- key: lint
run: npm run lint
- key: unit
continue_on_error: true
run: npm test
- run: npm run build
Concurrent step rules
These rules cover background, wait, wait_all, cancel, and parallel.
Sync rejects a workflow that breaks one of them.
| Rule | Applies to |
|---|---|
Needs a key. | A step with background: true. |
| Is a run, action, agent, or tool step. A checkout step cannot run in the background. | A step with background: true. |
Cannot have a gate. | A background step and a step of a parallel block. |
Accepts only name. It cannot set if, run_after, or continue_on_error. | A wait, wait_all, or cancel step. |
| Names a background step that exists and is still running at that point. | A wait or cancel step. |
Cannot run while a background step may still run. Add wait_all before it. | A checkout step. |
| Lists at least two steps and takes no other field. Blocks do not nest. | A parallel block. |
Is not a checkout, wait, wait_all, cancel, or parallel step, and does not set background or gate. | A step of a parallel block. |
Cannot go back past a background step that may still be running. Cannot name a step in the middle of a parallel block. | gate.on_failure.restart_from. |
Cannot read steps.<key> of a background step before a wait joins it. | An expression. |
Cannot use the same key as another step that can run at the same time, unless both steps use mode: fork. | An agent session. |
A wait or wait_all step always runs. It fails when a step it waits for
failed without continue_on_error. wait_all waits for every background step
started earlier that no wait joined and no cancel stopped.
Without name, the run page labels these steps by their keys:
| Step | Label |
|---|---|
wait: [security, perf] | Wait for security, perf |
wait_all: | Wait for background steps |
cancel: db | Cancel db |
The wait at the end of a parallel block | Wait for parallel steps |
Jobs and steps explains how these steps run.
Agent file
A file in .shipfox/agents/ configures one project agent. The file name
without its extension is the agent key, so a file declares no key, and a
nested file is an error. shippy.yaml adds to the built-in agent, and every
field in it is optional. Any other file is a custom agent, which needs
description and instructions. Sync checks each agent file on its own. An
invalid file keeps the agent's last valid version, reports the error, and
never blocks the workflows.
integrations uses the selectors of an agent step. Sync rejects a file that
selects an unknown tool. Shipfox records a write call before it runs. If the
call stops after it starts and before its result is stored, a retry does not
run it again. The agent gets the result unknown and reads the current state
before it tries again.
namestringSets the display name of the agent. Without it, the agent shows its key, the file name without the extension. The name never identifies the agent.
Use a literal value. Workflow expressions are not allowed.
descriptionstringDescribes what the agent is for. Users read it when they pick an agent. Required for a custom agent.
instructionsstring | PromptPart[]Gives the agent its instructions. Use a string, or a list of parts that Shipfox joins with a blank line. A part is a string or a
filereference. Inshippy.yamlthe instructions add to the built-in prompt. Required for a custom agent, where they are the whole prompt.modelstringSelects the model that the agent uses. Without it, the workspace default applies.
providerstringSelects the model provider for the agent. See Model providers.
thinkingenumSets agent reasoning.
defaultrequests the provider default without workspace or deployment overrides. Omitting this field uses configured defaults orxhigh.offminimallowmediumhighxhighmaxdefault
integrationsIntegration[]Adds tools from integration connections to the agent. See integrations and tools.
Add at least one item.
onRule[]Declares the requests from Slack or Linear that the agent claims. When several rules match, a custom agent wins over a Shippy, and the rule added first wins within each.
name: Code reviewer
description: Reviews pull requests in this project and reports the main risks.
instructions:
- Review the change like a senior engineer on this team.
- file: ./.shipfox/prompts/review-rules.md
model: claude-sonnet-5
provider: anthropic
thinking: high
integrations:
- include: [pull_request_read]
on:
- source: slack_acme
filter: request.channel_id == "C04PAYMENTS" || request.viewing_channel_id == "C04PAYMENTS"
- source: linear_acme
filter: "'payments' in request.labels"
Agent rules
An on rule declares which requests the agent claims. A request is a
message that starts a conversation, such as a mention in a Slack channel or
a Linear agent session. One agent answers each conversation. When several
rules match a new request, a custom agent wins over a Shippy, and within each
group the rule that was added first wins. A request that no rule matches goes
to the Shippy of the workspace's default project. Replies in a thread stay with
the agent that answered first, even after a rule changes.
source is the slug of an integration connection that lets people talk to
agents, such as slack_acme or linear_acme. Use the slug of your own
connection. A rule has no event, with,
secrets, or config, because only requests can match. filter is a
condition like a workflow trigger filter. It reads request, where the
request was made, and event, the raw payload. Sync rejects a filter on a
field that the provider does not set for request, and a filter longer than
2,000 bytes. See Limits. A rule that
sync rejects leaves the agent on its last valid version.
sourcestringRequiredSelects the slug of the integration connection whose requests this rule covers, such as
slack_acmeorlinear_acme. Use the slug of your own connection. The integration must let people talk to agents.filterstringNarrows the rule to requests that match this condition. The condition can use
request, where the request was made, andevent, the raw payload. Without it, the rule covers every request from the source. See Expressions.
name: Code reviewer
description: Reviews pull requests in this project and reports the main risks.
instructions:
- Review the change like a senior engineer on this team.
- file: ./.shipfox/prompts/review-rules.md
model: claude-sonnet-5
provider: anthropic
thinking: high
integrations:
- include: [pull_request_read]
on:
- source: slack_acme
filter: request.channel_id == "C04PAYMENTS" || request.viewing_channel_id == "C04PAYMENTS"
- source: linear_acme
filter: "'payments' in request.labels"
Related pages
Contexts
Every context, its properties, and the fields that can read it.
Expressions
The syntax, operators, and functions available inside an expression.
Model Providers
Every provider ID, default model, and how agent config resolves.
Limits
Every default and cap: attempts, timeouts, log budgets, env sizes.