Menu
Hybrid DAG execution primitive combining deterministic and agentic nodes with hard iteration caps
The review-first prompt is selected by default. You can switch to a direct command or download a local copy.
Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
A direct command skips the review prompt. Inspect the source before running it.
npx skills add https://github.com/CleanExpo/DR-NRPG --skill blueprint-engineThe command stays on one line. Scroll horizontally to inspect it before copying.
Prefer a local copy? Download the files currently available to SkillsMP.
Showing SKILL.md
| name | blueprint-engine |
| version | 1.0.0 |
| description | Hybrid DAG execution primitive combining deterministic and agentic nodes with hard iteration caps |
Inspired by Stripe Minions: deterministic scaffolding + bounded agentic intelligence. Hard caps are non-advisory โ they are enforced by iteration-counter.py.
Commands executed directly with no iteration cost:
git-branch โ git checkout -b minion/{task-id}git-commit โ git add -A && git commit -m "minion: {message}"git-push โ git push -u origin HEADcreate-pr โ gh pr create --title "minion: {task}" --body "{template}" --label "minion-generated"lint โ pnpm turbo run linttype-check โ pnpm turbo run type-checktest โ pnpm turbo run testcircular-deps-check โ pnpm turbo run lint (includes circular dep detection)system-supervisor-quick-audit โ read .claude/memory/current-state.md + grep for violations (deterministic)execution-guardian-check โ evaluate risk level from task keywords (deterministic mapping)implement โ Implement the requested feature. Cap: 1 pass onlyreproduce-bug โ Write a failing test that reproduces the bug. Cap: 1 pass onlyimplement-fix โ Fix the reproduced bug. Cap: 1 pass onlyimplement-migration โ Execute a database or code migration. Cap: 1 pass onlyimplement-refactor โ Refactor per system supervisor audit findings. Cap: 1 pass onlyfix-ci โ Fix CI/test failures. Cap: 2 rounds maximumfix-lint โ Fix non-auto-fixable lint errors. Cap: 1 round maximum| Node | Cap |
|---|---|
implement | 1 pass |
reproduce-bug | 1 pass |
implement-fix | 1 pass |
implement-migration | 1 pass |
implement-refactor | 1 pass |
fix-ci | 2 rounds |
fix-lint | 1 round |
| Total agentic per blueprint | 3 max |
When any cap is reached โ output BLUEPRINT_ESCALATION block, halt, write to .claude/memory/current-state.md, stop.
These are applied automatically before any agentic node. They do NOT count against caps:
| Error Pattern | Auto-Fix Command |
|---|---|
Cannot find module | pnpm install |
ModuleNotFoundError | uv sync |
| Auto-fixable ESLint errors | pnpm turbo run lint -- --fix |
| Auto-fixable Python lint | uv run ruff check src/ --fix |
| Missing type stubs | pnpm add -D @types/{package} |
When a cap is reached or a blocking error occurs, output this exact block and halt:
BLUEPRINT_ESCALATION
task_id: {id}
node: {failing-node}
iteration: {n}/{max}
reason: {what failed in one line}
evidence: {last 5 lines of error output}
next_action: Human review required โ do not retry automatically
Then write to .claude/memory/current-state.md:
## Minion Escalation โ {DD/MM/YYYY HH:MM AEST}
task_id: {id}
status: ESCALATED
node: {failing-node}
reason: {reason}
.claude/data/minion-state.json.create-pr.node-type โ node-type โ [optional-node] โ node-type
Brackets [...] indicate conditional nodes (only executed if the preceding deterministic check fails).
Based on SOC occupation classification