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.
npx agentmods add commands/commerce-atoms/agents/deploy-checkgit clone --depth 1 https://github.com/commerce-atoms/agentsWhat 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 | $0.00026 | $0.00666 |
| Opus 5 | $0.00013 | $0.00333 |
| Sonnet 5 | $0.00005 | $0.00133 |
| Haiku 4.5 | $0.00003 | $0.00067 |
Grade A, and why
deploy-check 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 2d 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/deploy-check
Doctrine reminder (
AGENTS.md §0sub-doctrine): the agent prepares and validates. CI deploys. This command validates locally; CI runs the same gates again on push.
Reproduce the CI gates locally before git push origin main. If anything fails, fix it and re-run — do not push a broken change and rely on CI to catch it.
Prerequisites
- Working tree should ideally be clean. Uncommitted changes are validated but flagged.
- Dependencies installed (
npm installornpm ci).
Workflow
Run each step in order. Stop on the first failure and surface the output to the operator.
1. Working tree status
git status --porcelain
If output is non-empty, surface a warning: "Uncommitted changes detected — they will be excluded from the push but included in the local pre-flight."
2. Codegen
npm run codegen
Must succeed. If GraphQL fragments / types drift, codegen reports it; commit any regenerated files before proceeding.
3. TypeScript
npm run typecheck
Zero errors required.
4. Lint
npm run lint
Zero errors required. Warnings are surfaced but do not block.
5. Tests
npm test
Full unit + integration suite. All green.
6. Build
npm run build
Production build must succeed. Bundle-size regressions are not blocking but are surfaced.
7. Architecture validation
npx @commerce-atoms/agents validate-architecture
Zero errors required (the validate-architecture skill).
8. Summary
If all eight steps pass, print:
PRE-FLIGHT PASSED — safe to push.
Push when ready:
git push origin main
Or, if the change warrants a release: /release
Done when
- All eight steps exit 0 (with warnings allowed only at step 1, codegen-clean, and lint).
- Operator has been told whether to push directly or to
/release.
Failure modes
| Failure | Remedy |
|---|---|
| codegen drift | Commit regenerated GraphQL types. |
| typecheck fails | Fix the TS errors; do not loosen tsconfig to silence them. |
| lint fails | Fix the rule violations; do not suppress globally. |
| validate-architecture fails | Resolve the violations per the cross-module reuse ladder. |
| Build fails | Inspect Vite / Oxygen-specific errors; do not work around them. |
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.
- 2d ago First seen · 111 lines · 26 tokens per session scan A f4c97c2bb120
deploy-check is a command published in the GitHub repository commerce-atoms/agents (1 stars, last pushed 4mo ago), licensed MIT. It adds 26 tokens to every session and 666 once invoked, about $0.0001 per session on Opus 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 2026-08-31.
Other commands, from other repositories
monitor
Monitor GitHub Actions CI status for the current branch. If any workflow fails, diagnose the failure, fix it, commit, push, and re-monitor — up to 3 cycles.
core-review
Review code changes against SpecOps project-specific patterns. Catches recurring failure modes from real PRs — tool abstraction violations, generated file drift, cross-platform gaps, variable inconsistencies, and more. Complements full-review-gate (generic quality) and pr-fix (applying bot comments).
full-review-gate
Perform a comprehensive repository code review in an isolated worktree. Fix P0/P1 findings and ship them as a PR targeting the current branch.
ship-pr
Commit all changes to a new branch, push, and open a PR for review. The original branch stays clean.
brownfield-map
Run a complete brownfield analysis on the codebase and generate MASTER.md, summaries, risk scores, and all derived analytics.
implement-fastapi-routes
The file docstring contains a description of the FastAPI routes we need to implement. Implement these routes.