pipeline-orchestrate
Skill8 starsChanged 5 months agoMITView on GitHub
Merge scorer and PE signals to route PRs. Applies routing matrix (auto-fix / auto-fix-verify / hitl-light / hitl-full) based on score thresholds and risk levels.
In this repository31 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- accelerateSkill
- implement-issueSkill
- pipeline-engSkill
- pipeline-peSkill
- pipeline-scorerSkill
- qa-acceleratedSkill
- qa-prSkill
- qa-webSkill
- releaseSkill
- review-feedbackSkill
- roadmap-prioritizationSkill
- roadmap-refinementSkill
- security-auditSkill
- accelerateSkill
- implement-issueSkill
- pipeline-engSkill
- pipeline-orchestrateSkill
- pipeline-peSkill
- pipeline-scorerSkill
- qa-acceleratedSkill
- qa-hitlSkill
- qa-prSkill
- qa-webSkill
- releaseSkill
- review-feedbackSkill
- roadmap-prioritizationSkill
- roadmap-refinementSkill
- screenshotsSkill
- security-auditSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
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
- Distinctive: line 50
Read scorer and PE comments from the PR
- Very specific: line 55
If verdict is auto-fix or auto-fix-verify, dispatch pipeline-fix.yml
- Very specific: line 66
If the same PR also touched src/main/ipc.ts:
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Pipeline Orchestrator
Merges scorer and PE analysis signals to determine the final routing verdict for a PR.
Usage
/pipeline-orchestrate <pr-number>Routing Matrix
Source of truth: run-orchestrator.mjs route() function.
| Score (1-10) | PE Risk | Route | Action |
| 1-3 | LOW | auto-fix | Codex pushes fix commit |
| 1-3 | MEDIUM+ | hitl-light | Post analyses, label needs-review |
| 4-6 | LOW | auto-fix-verify | Fix + request human verification |
| 4-6 | MEDIUM+ | hitl-full | Full analyses, assign human |
| 7+ | Any | hitl-full | Label complex, full human review |
| Any | CRITICAL | hitl-full | Always escalate |
| Any | privileged | hitl-full | Security hard gate — always escalate |
Label Mapping
| Verdict | Labels Applied |
auto-fix | auto-fix-queued |
auto-fix-verify | auto-fix-queued, needs-review |
hitl-light | needs-review |
hitl-full | complex, needs-review |
Security Hard Gate
PRs touching privilege-boundary paths auto-route to hitl-full regardless of score:
src/main/**— full system accesssrc/preload/**— context bridge / attack surfaceelectron-builder.*,electron.vite.config.*— build/packaging config
With the security-gate short-circuit (383-2), these PRs skip scorer+PE entirely — the pipeline-triage.yml security-gate-check job detects the <!-- security-gate: true --> sentinel in the review and posts hitl-full directly.
Workflow
- Read scorer and PE comments from the PR
- Parse sentinel JSON from both (
<!-- scorer-output: {...} -->and<!-- pe-output: {...} -->) - Apply routing matrix
- Post verdict comment with
<!-- orchestrator-verdict: auto-fix|auto-fix-verify|hitl-light|hitl-full --> - Apply GitHub labels per the label mapping table
- If verdict is
auto-fixorauto-fix-verify, dispatchpipeline-fix.yml
Decision Trace Example
Given a PR that touches src/renderer/components/editor/Editor.tsx only:
- Scorer returns:
{"score": 4, "threshold": "review"} - PE returns:
{"risk": "LOW", "privileged": false, "concerns": 1} - Path: score 4 >= 4, risk LOW →
auto-fix-verify - Labels:
auto-fix-queued,needs-review - Pipeline dispatches
pipeline-fix.yml, then requests human verification
If the same PR also touched src/main/ipc.ts:
- PE returns:
{"risk": "MEDIUM", "privileged": true, "concerns": 2} - Path: privileged = true → immediate
hitl-full(score doesn't matter) - Labels:
complex,needs-review - No auto-fix dispatched
Output Format
Machine-readable sentinel:
<!-- orchestrator-verdict: auto-fix|auto-fix-verify|hitl-light|hitl-full -->
Human-readable summary with routing rationale referencing scorer dimensions and PE risk assessment.
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.

