Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/danielvm-git/bigpowersWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/rules/danielvm-git/bigpowers/compose-workflow)<a href="https://agentmods.dev/rules/danielvm-git/bigpowers/compose-workflow"><img src="https://agentmods.dev/badge/rules/danielvm-git/bigpowers/compose-workflow/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/danielvm-git/bigpowers/compose-workflow"><img src="https://agentmods.dev/badge/rules/danielvm-git/bigpowers/compose-workflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00038 | $0.00797 |
| Opus 5.5 | $0.00015 | $0.00319 |
| Sonnet 5.5 | $0.00008 | $0.00159 |
| Haiku 4.5 | $0.00004 | $0.00080 |
Grade A, and why
compose-workflow scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
story: e09s01
story: e45s27
story: e21s04
Compose Workflow
HARD GATE — HARD GATE — Workflows are orchestration, not automation. Do NOT create workflows for tasks that should be single skills. Workflow complexity must be justified.
Process
- Interview: goal, phases, which skills, gates between steps.
- Write
specs/workflows/<name>.yaml:name,command,description,skills[],verify- Optional:
argsfor skill-specific arguments
- Register in state.yaml Active Decisions.
- Optional: reference from
orchestrate-projectAd-Hoc mode.
Prefer the YAML recipe format over the legacy
specs/WORKFLOW-<name>.mdmarkdown format. YAML recipes are command-mappable, machine-readable, and listed in the Standard Recipe Library.
Terminal-state taxonomy (e45s27)
Every workflow step and /loop tick MUST exit with exactly one terminal state:
| State | Meaning | Next action |
|---|---|---|
success |
Step verify passed; artifacts written | Advance to next skill in recipe |
no-op |
Nothing to do (already green / already applied) | Skip step; advance |
blocked |
External gate (approval, red CI, missing dep) | diagnose-stall or escalate to user |
exhausted |
Max iterations/cycles reached (review cap, dispatch cycles) | Stop; human decision required |
Record terminal state in specs/state.yaml handoff.last_terminal_state when a recipe step completes. /loop ticks that produce no progress for two consecutive wakes → invoke diagnose-stall.
Standard Recipe Library
Pre-built recipes in specs/workflows/ map agentic stack commands to skill chains.
Reference them in AGENTS.md so /command directly invokes the matching recipe.
| Command | Workflow | Skill chain |
|---|---|---|
/check-stack |
check-stack | survey-context → assess-impact → setup-environment |
/ship |
ship | audit-code → commit-message → release-branch |
/tdd |
tdd | develop-tdd → enforce-first |
/code-review |
code-review | audit-code → request-review → respond-review |
/security |
security | audit-code → request-review |
/plan |
plan | survey-context → research-first → plan-work |
/build-fix |
build-fix | investigate-bug → diagnose-root → develop-tdd → validate-fix |
/e2e |
e2e | smoke-test → verify-work |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 82 lines · 38 tokens per session scan A 7d26f50d1a8d
compose-workflow is a cursor rule published in the GitHub repository danielvm-git/bigpowers (267 stars, last pushed 27d ago), licensed MIT. It adds 38 tokens to every session and 797 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other cursor rules, from other repositories
payload-cms
Payload CMS: collections, fields, hooks, access control, admin UI.
monorepo
Monorepo: workspace references, shared packages, boundaries.
pnpm
PNPM: workspace monorepos, efficient package management.
ai-dev-os-ticket
Generates a ticket (local file or GitHub Issue) with implementation summary and checklist candidates derived from AI Dev OS guidelines. Used to create structured implementation tasks.
agent-workflow-orchestration
Mandatory PM-orchestrated subagent workflow — main agent is manager, no separate PM subagent.
12-new-project
Workflow for starting a new app from this template - rebranding, identity, cleanup and first feature.