Orchestrator Pipeline (shared engine)
SkillAI & modelsorch-pipeline is a skill that acts as the shared orchestration engine behind the orch-* skill family. It runs coding tasks through a gated pipeline of research, planning, TDD implementation, code review, and commit, classifying each request by size and delegating phases to existing agents and commands. It pauses at two human gates: plan approval before coding starts and commit confirmation before changes are committed. Operation skills such as orch-add-feature and orch-fix-delegate to it, so it is normally used indirectly.
Use Orchestrator Pipeline (shared engine) in Claude, ChatGPT or Ahel Desktop
Free. Sign in, add Orchestrator Pipeline (shared engine) and connect your AI. About a minute.
Also: Claude Code · Cursor · Codex
Then ask your AI: use the Orchestrator Pipeline (shared engine) skill
Details
Instructions available. Your AI can read the instructions. Execution depends on the setup they require.
Account requirements not reviewed. Check the skill instructions before use; ahel provides instructions and does not run this skill.
No other account needed.
Have the orch-* operation skills available, since orch-pipeline is used through them rather than called directly.
What your AI can do with it
- Classifies a coding request by size before choosing how to run it
- Runs a research phase and a planning phase for the task
- Delegates TDD implementation to existing agents and commands
- Runs a code review phase before any commit
- Pauses for plan approval before coding starts
- Pauses for commit confirmation before changes are committed
Getting started
- Have the orch-* operation skills available, since orch-pipeline is used through them rather than called directly.
- Make sure the agents and commands that the pipeline delegates to are configured in your setup.
- Start a coding task with an operation skill such as orch-add-feature or orch-fix-delegate.
- Approve the plan when the pipeline pauses at the first human gate.
- Confirm the commit when the pipeline pauses at the second human gate.
What this skill tells your AI
The instructions your AI receives, as published by affaan-m/ecc in skills/orch-pipeline/SKILL.md and read by ahel’s review.
The orch-* skills are thin wrappers. They do not re-implement any work — they
classify the request, choose which phases of this pipeline run, and delegate
each phase to an existing ECC agent or command. This file is that pipeline.
Invoke an operation skill (
orch-add-feature,orch-fix-defect, …) rather than this engine directly. This file is the reference they point at.
When to Use
- Loaded indirectly whenever an
orch-*operation skill runs. - Read directly only when adding a new operation to the family or tuning the shared phases, gates, or agent map.
The operation family
| Skill | Operation | Trigger | First move |
|---|---|---|---|
orch-add-feature | feature | capability does not exist yet | research + plan a new slice |
orch-change-feature | tweak | works, but desired behavior differs | amend existing behavior and its tests |
orch-fix-defect | fix | broken; behavior is wrong | reproduce as a failing test, then fix |
orch-refine-code | refactor | behavior stays, structure improves | restructure while keeping tests green |
orch-build-mvp | mvp | bootstrap from a design/spec doc | ingest doc → vertical slices |
These wrappers compose existing ECC commands rather than replace them:
/feature-dev,/plan,/code-review,/build-fix,/refactor-clean, and/gan-build, plus thetdd-workflowskill. The orch-* family adds the shared size classifier and the two gates on top of them, so one umbrella covers all five operations consistently.
Step 0 — Classify size (right-sizing)
Ceremony scales to blast radius. Score the request on three signals, take the highest tier any signal reaches, and state the result in one line so the user can override:
| Tier | Files touched | New dependency / contract | Design ambiguity | Phases that run |
|---|---|---|---|---|
| trivial | 1, a few lines | none | none — the change is obvious | 4 → 5 → 6 |
| small | 1 file / 1 function | none | clear once you read the code | (1 light) → 4 → 5 → 6 |
| standard | 2–5 files | maybe a new internal module | one real choice to make | 1 → 2 → 4 → 5 → 6 |
| large | many / cross-cutting | new external dep, public API, or a spec doc | multiple open questions | 1 → 2 → (3) → 4 → 5 → 6 |
Phase 0 (Intake) always runs and is omitted from the mask column above. The tie-breaker: anything touching a security trigger (below) or a public API / contract is at least standard, regardless of file count.
The phases
Each phase delegates — it does not do the work inline.
- 0. Intake — restate the request. For
orch-build-mvp, read the spec/design doc and extract scope, locked decisions, and a feature list. - 1. Research & Reuse — per
rules/common/development-workflow.md:gh search repos/gh search code, then Context7 / vendor docs, then package registries, then Exa. Prefer adopting a proven implementation over net-new code. - 2. Plan — delegate to the
planneragent (orarchitect/code-architectfor structural decisions). Output atask_listordered as thin vertical slices. → GATE 1. - 3. Scaffold —
orch-build-mvponly: stand up the first end-to-end slice. - 4. Implement (TDD) — drive each task through the
tdd-guideagent (or thetdd-workflowskill): red → green → refactor. Honor the operation's first-move rule. - 5. Review —
code-revieweragent //code-review. Addsecurity-reviewerwhenever the diff touches a security trigger (below). - 6. Commit — conventional commits (
feat:/fix:/refactor:/ …), one per logical chunk. → GATE 2.
The two gates
This family is gated, not autonomous:
- GATE 1 — after Plan. Present the
task_list; do not write implementation code until the user approves. - GATE 2 — before Commit. Present the diff summary and proposed messages; do not commit until the user confirms.
Everything between the gates flows without stopping.
Agent / command map
| Phase | Primary | Fallback / escalation |
|---|---|---|
| Intake / understand | code-explorer | trace existing paths before a tweak, fix, or refactor |
| Plan | planner | architect, code-architect for structural calls |
| Implement | tdd-guide (or tdd-workflow skill) | build-error-resolver / /build-fix on build breaks |
| Review | code-reviewer / /code-review | language reviewer (python-reviewer, typescript-reviewer, …) |
| Security | security-reviewer | — |
| MVP inner loop | /gan-build "<brief>" --skip-planner | drives gan-generator → gan-evaluator; tune --max-iterations / --pass-threshold |
Match the language reviewer to the repo (see the repo's own CLAUDE.md).
Security-review trigger
Pull in security-reviewer when the diff touches any of: authentication or
authorization, user-input handling, database queries, file-system paths,
external API calls, cryptography, or secrets / credentials. (Per rules/common/security.md.)
Handoff artifacts
The pipeline carries no hidden state — the planning docs are the handoff:
task_list(from Plan) drives the Implement loop.- Larger work may also emit PRD / architecture / system_design under the repo's
docs/perrules/common/development-workflow.md. - Review findings (CRITICAL / HIGH) must be resolved before Gate 2.
Verification
- size tier was stated and matched the work
- Gate 1 (plan) and Gate 2 (commit) were both honored
security-reviewerran iff a security trigger was touched- commits are conventional and scoped to one logical change
- new / changed behavior has tests; coverage ≥ 80% per
rules/common/testing.md
Signals
- GitHub stars
- 270k
- Forks
- 40k
- Last commit
- Sep 2026
Questions
- Can I use orch-pipeline directly?
- It is meant to be used indirectly through the orch-* operation skills, which delegate to it. Those skills are the normal entry point for a coding task.
- What are the two human gates?
- Plan approval, which happens before coding starts, and commit confirmation, which happens before changes are committed. The pipeline pauses at both.
Advanced
- Item type
- skill
- Key
orch-pipeline- Source
- github.com/affaan-m/ecc
Related picks
Skill · affaan-m
Does the same job in other wordsskill-creator
Skill · anthropics
More in AI & modelswayfinder
Skill · mattpocock
More in AI & modelswizard
Skill · mattpocock
More in AI & modelsalgorithmic-art
Skill · anthropics
More in AI & modelscode-review-and-quality
Skill · addyosmani
More in AI & models