pipeline
Skill1 starsChanged 42 days agoMITView on GitHub
Use when starting any development task (feature, bugfix, refactor, hotfix) in a project that has a pipeline profile (.claude/pipeline/profile.json), before writing or editing any production code.
29 other projects use a version of this.
Adopted by
Most recently taken up by
- Jlosev/agent-skillstheir own version, first seen Nov 15, 2026
- baekenough/oh-my-customcodetheir own version, first seen Nov 14, 2026
- elfrost/ai-patchlabtheir own version, first seen Nov 9, 2026
- PeterPartridge/CooperativeAICodingtheir own version, first seen Nov 8, 2026
- Jakeschincariol/closer-skilltheir own version, first seen Nov 8, 2026
- Nucleify/Nucleifytheir own version, first seen Nov 2, 2026
Used with
Projects with it also use follow-up, status and 7 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
n24q02mSkillfollow-up
Find emails needing follow-up -- unanswered sent emails, flagged unreplied, draft contextual responses
Also in 3 projects that use this
AnthropicSkillstatus
Case status summary by audience — client-facing (plain language), internal (for the professor), or court-ready (formal caption format per local rules). Same facts, different framing and depth. Use when a student needs to update the client, brief the professor, or prepare a court status report.
Also in 5 projects that use this
genomewalkerSkillexplore
RLM-style recursive memory exploration - dynamically navigate the memory graph
Also in 3 projects that use this
genomewalkerSkillresume
Resume a thread by loading its ~800-token context capsule
Also in 3 projects that use this
AnthropicSkillanalyze
Answer data questions -- from quick lookups to full analyses. Use when looking up a single metric, investigating what's driving a trend or drop, comparing segments over time, or preparing a formal data report for stakeholders.
Also in 3 projects that use this
dubwoahSkillask
Answer questions about the codebase without generating or modifying any code. Use when the user wants to understand how something works, find where something is defined, or explore the project structure. Invoked with /ask.
Also in 3 projects that use this
Other versions29 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 29
- Yeachan-Heo/oh-my-codex★ 34ksame name
- H-mmer/pentest-agents★ 815same name
- spytensor/openmozi★ 215same name
- Nucleify/Nucleify★ 171same name
- akashgit/remote-factory★ 74same name
- boston-harness-group/remote-factory★ 74same name
- baekenough/oh-my-customcode★ 42same name
- Jakeschincariol/closer-skill★ 33same name
- Magerko/claude-code-skills★ 22same name
- alejopijuan/Claude-Code-Agency-Co-Founder★ 19same name
19 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository2 other files it gives its agents.
- init-profileSkill
- tasksSkill
The file
We split this skill into the rules it gives an agent
5 rules. 0 are common, 3 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 22 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 10
If .claude/pipeline/profile.json does not exist, stop and run the init-profile skill first.
- Distinctive: line 12
Read the profile now — it is the project's contract and several of its fields drive this skill directly:
- Distinctive: line 34
Create one todo per step when the task begins.
- Very specific: line 54
Never prefix a commit with PIPELINE_SKIP_GATE=1 on your own initiative — the bypass exists for the user to authorize explicitly, and every …
- Distinctive: line 63
Verify deliverables directly (read the files, run the tests) — an agent reporting "done" is a claim, not evidence.
“Common” is measured: kept by at least 6 in 10 of the 22 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Development Pipeline
You are the Orchestrator of one task, from request to committed code. You coordinate agents, decide architecture with the user, and on level 3+ tasks you never write production code yourself.
If .claude/pipeline/profile.json does not exist, stop and run the init-profile skill first. If the project has no CLAUDE.md, stop as well and run init-profile's CLAUDE.md step — planning without project context (domain glossary, permanent decisions, "never" rules) produces generic plans that fail review.
Read the profile now — it is the project's contract and several of its fields drive this skill directly:
areas— everytask-clicall below meansnode <plugin-root>/scripts/task-cli.js <command>. The plugin root is announced at session start by the plugin's SessionStart hook (and is two directories above this skill's base directory). Never store it in the project — the install path is versioned and changes on every plugin update; an old profile'scliPathfield is obsolete and ignored.areas.<area>.skills— project/user skills the area's agents must follow. In every tester/dev/reviewer prompt, name the area's skills and state they are binding; agents load them via the Skill tool. If a listed skill fails to resolve at spawn time, read itsSKILL.mdyourself and inline the content in the agent's prompt instead — never silently drop a declared skill.models— when spawning an agent, apply the matrix cell for that role and the task's level band. A cell is either a model name ("sonnet") or{"model": "sonnet", "effort": "low"}— passmodelat spawn, andefforttoo where the spawn surface supports it (e.g. Workflow agents).inherit/absent = session model.task-cli startsnapshots the applied cells into the registry for cost reporting.branch— whenperTaskis true and the task level ≥minLevel, create the branch frompattern(e.g.feat/task-{id}) right aftertask-cli start, before any test or code is written.rework.maxAttempts— replaces the "3 attempts" default in step 5;rework.incrementalReviewtoggles per-phase review on level 5.language— talk to the user inlanguage.user; code identifiers/comments followlanguage.code; strings shown by the product followlanguage.productStrings.lean—off|lite|full|ultra(absent =off): the lean mode adapted from Ponytail. The Lean notes in the steps below apply when it isn'toff; the agents' part reaches them through the spawn brief.
Agent prompts stay short. The plugin's SubagentStart hook hands every tester, dev and reviewer a brief at spawn — plugin root, active task, plan path, TDD state, all areas (globs, test command, notes, skills), languages, CLAUDE.md and the lean rules for its role. A prompt needs only what the brief can't know: the area, the plan path, the tests to pass and adjust (dev), the changed files (reviewer). Don't paste profile data, CLAUDE.md or lean rules into prompts.
Complexity level (decide first, with the user)
| Level | Meaning | Mechanics |
| 1-2 | Small fix, localized change | Plain subagents (tester → dev), fire-and-collect |
| 3-4 | Medium feature, refactor with impact | Named agents per area + SendMessage coordination |
| 5 | Large feature, architectural change | Named agents + phased execution + incremental review per phase |
Steps
Create one todo per step when the task begins.
Register + discovery —
task-cli new "<title>" --type=<improvement|bugfix> --level=NcreatesTASK-<id>and its plan file. Ask the open questions with AskUserQuestion (batch up to 4 per call, never one-by-one). Write the answers into the plan file's Discovery section immediately after receiving them — before planning, not later.Lean: before asking, climb rungs 2–5 yourself — grep the repo for an existing helper, check the standard library, a native platform feature, an already-installed dependency — and turn what you find into options. Rung 1 ("does this need to exist?") and adding a new dependency are always the user's call: they go in the same AskUserQuestion batch, never decided by you or an agent.
lite: offer the lazier option, but recommend what was asked.full: recommend the laziest option that works (listed first, "(Recommended)").ultra: also ask rung 1 for every requirement beyond the core.Plan — fill the plan file: mini-tasks with checkboxes, architecture options (present to the user, they decide), impact analysis (which existing tests cover the code being touched — list them, or state
none: <reason>), and, when the task spans areas, the cross-area contract in its own section: exact field names, value formats, endpoints, shared params. The contract lives in the file, not in prompts — it must survive context compression. Runtask-cli start <id>. Tell the user the plan file path so they can review it before execution.Lean (
full,ultra): every mini-task names its rung (— rung 2: reuse src/lib/slug.ts,— rung 4: native <input type="date">,— rung 7: minimal, with validation); a bugfix's impact analysis lists every caller of the function touched; whatever the ladder or the user deferred goes under "Out of scope" as plain bullets with the trigger to revisit — testers don't test it and devs don't build it.- Tests first (red) — spawn one
testeragent per affected area, all in parallel. Each writes failing tests for the new behavior, runs them, and reports: which tests failed (expected) and which passed (suspicious — a test that passes before implementation proves nothing). Review the tests against the plan, then runtask-cli tdd-red <id> --area=<area>for each area: it runs the area'stestCommand(or--cmd="..."narrowed to the new tests) and records red only if the run fails — a green run is refused. Read the output: the failures must be assertions on the new behavior, not syntax/import errors. The TDD hook tracks red per area and blocks production edits in an area — through Write/Edit and through Bash (>,sed -i,cp,mv,rm, ...) — until that area is red. An area with genuinely no testable code path (docs, config):task-cli tdd-skip <id> --area=<area> --reason="..."(without--areait applies to every area) — the reason is recorded and visible in the registry. - Implement — spawn
devagents per area; parallel when they touch different files (the default), sequenced when one depends on the other's output. Each dev prompt states: the plan file path, which tests must pass, and which existing tests to adjust (from the impact analysis). Devs report back via message; they never tick checkboxes or edit the registry. A dev reporting a higher rung than the plan's (a helper nobody listed, a part a native feature covers): inside the plan's scope → let it proceed; a scope change → AskUserQuestion first, and record the decision. - Review — spawn the
revieweragent with the task id and the changed-file list. It runs the affected areas' test commands, the complexity ratchet (scripts/complexity-check.js— it compares against the commit recorded bytask-cli start, so untouched legacy code is never blamed) on changed files, and checks the plan was fully delivered. Verdict: approve, or return to the dev with a precise defect description — and on every rejection runtask-cli rework <id> --area=<area> --reason="<short>"so the attempt is recorded (this feeds the cost/rework report and is how the attempt limit is counted). Maxrework.maxAttemptsper dev per mini-task (default 3); one attempt before the last, check whether the test is wrong before blaming the implementation; at the limit, stop and ask the user. Level 5 withincrementalReview: review after each phase, not only at the end. Lean findings (gate 6) are handled asreferences/reviewer-protocol.mdsays: advisory infull,reuse:/delete:reject inultra. Conclude — tick every checkbox in the plan file, present the changed-file summary to the user, and wait for commit approval. One commit per task, never grouped; the message follows
commitin the profile (format: "conventional"→type(scope): subject,requireTaskRef→ includeTASK-<id>, written incommit.language).task-cli ready <id>before committing — it refuses while the plan has unticked checkboxes, and the commit gate blocksgit commituntil it passes and validates the message convention (heredoc messages included). A deliberately partial delivery (rollback option a, decided by the user) usesready <id> --partial --reason="...". The post-commit hook records the hash, closes the task and attaches its token usage from the session transcripts automatically.Lean: if the reviewer reported lean findings, ask before the commit, in one AskUserQuestion: apply now (one rework cycle), defer (a bullet under "Out of scope"), or ignore — and record the choice in Decisions.
task-cli debtlists every deferral andlean:marker with the task it came from.Never prefix a commit with
PIPELINE_SKIP_GATE=1on your own initiative — the bypass exists for the user to authorize explicitly, and every bypassed commit is registered as abypasstask that shows up inlistandreport.
Tests are the spec
If a change makes an existing test fail, never silently edit the test to make it pass. Stop and ask the user: is this an intentional behavior change (update test and code together) or a regression (fix the code)? There is no third option, and "the test was probably outdated" is not a decision you get to make alone.
Agent hygiene
- Release each named agent as soon as its deliverable is validated — never leave agents idle after their work is accepted.
- Verify deliverables directly (read the files, run the tests) — an agent reporting "done" is a claim, not evidence.
References
references/orchestration.md— read only for level 3+: agent naming, SendMessage, parallelism rules, when a Workflow script beats a teamreferences/reviewer-protocol.md— what to do with a verdict: rework loop, lean findings, rollback options on partial failurereferences/lean.md— the agents' lean rules (injected by the SubagentStart hook); read it only to change them
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

