pipeline-pe
Skill8 starsChanged 5 months agoMITView on GitHub
Principal Engineer architectural risk analysis for PRs. Assesses blast radius, hidden coupling, and privilege boundary concerns. Outputs LOW-CRITICAL risk rating.
In this repository31 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- accelerateSkill
- implement-issueSkill
- pipeline-engSkill
- pipeline-orchestrateSkill
- 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, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 59
Ask yourself: "If this change has a subtle bug, what's the worst that happens?"
- Distinctive: line 64
When in doubt, lean MEDIUM — the cost of over-escalating is a human glance.
- Distinctive: line 70
Check changed file paths against privilege boundary list
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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 PE (Principal Engineer) Analysis
Architectural risk assessment from a senior engineering perspective.
Usage
/pipeline-pe <pr-number>Analysis Framework
The PE agent evaluates changes across five dimensions:
| Dimension | What It Catches |
| Architectural coherence | Duct tape vs proper integration |
| Blast radius | Failure propagation paths |
| Root cause vs symptom | Band-aids vs real fixes |
| Tech debt trajectory | Is the codebase getting better or worse? |
| Hidden coupling | Implicit contracts created or broken |
Electron-Specific Checks
| Check | Why It Matters | Example |
| Process boundary respect | Renderer <-> main must go through IPC | Importing fs in renderer bypasses sandbox |
| Context bridge exposure | New preload APIs need input validation | Adding window.api.exec() without sanitization |
getApi() abstraction | Direct window.api bypasses the browser fallback | Should always use getApi() from browserApi.ts |
| IPC validation | Handlers must validate renderer input | validatePath() on all filesystem operations |
| Store interactions | Cross-store deps create hidden coupling | chatStore reading from editorStore directly |
Risk Levels
| Level | Meaning | Routing Impact | Example |
| LOW | Standard changes, well-contained | auto-fix eligible (if score ≤ 3) | Fixing a typo in a UI string |
| MEDIUM | Some architectural concern | hitl-full (if score ≥ 4) or hitl-light (if score ≤ 3) | Adding a new Zustand store with cross-store subscription |
| HIGH | Significant risk, multiple concerns | hitl-full | Changing the IPC channel protocol |
| CRITICAL | Security, data loss, or systemic risk | hitl-full (always) | Weakening CSP, disabling contextIsolation |
Privilege Boundary
PRs touching these paths are auto-flagged as privileged: true:
src/main/**— full system access (Node.js, filesystem, network)src/preload/**— context bridge / attack surfaceelectron-builder.*— build/packaging config (signing, fuses, entitlements)electron.vite.config.*— build config (define blocks, entry points)
privileged: true is a routing directive, not a bug. It forces hitl-full regardless of score. This is correct — changes to the trust boundary between renderer and main process should always have human review. Don't lower this flag to get auto-fix routing.
LOW vs MEDIUM Decision Guide
Ask yourself: "If this change has a subtle bug, what's the worst that happens?"
- LOW: User sees a visual glitch, a tooltip is wrong, a log message is malformed. The app still works. Fix is straightforward and contained.
- MEDIUM: User data could be stale, a sync could skip items, a store subscription fires out of order. The app works but produces wrong results in some cases. Fix requires understanding interaction between components.
When in doubt, lean MEDIUM — the cost of over-escalating is a human glance; the cost of under-escalating is a shipped bug.
Workflow
- Fetch the review comment and changed files from the PR
- Send to Codex Opus with the PE analysis prompt
- Check changed file paths against privilege boundary list
- Produce risk assessment, concern list, and verdict
- Output structured analysis with sentinel for downstream pipeline
Output Format
Machine-readable sentinel:
<!-- pe-output: {"risk":"LOW|MEDIUM|HIGH|CRITICAL", "privileged": true|false, "concerns": N} -->
Human-readable analysis with architecture review, specific concerns, and verdict.
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.

