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/christopherlouet/claude-baseWrote 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/commands/christopherlouet/claude-base/work-flow-release)<a href="https://agentmods.dev/commands/christopherlouet/claude-base/work-flow-release"><img src="https://agentmods.dev/badge/commands/christopherlouet/claude-base/work-flow-release/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/commands/christopherlouet/claude-base/work-flow-release"><img src="https://agentmods.dev/badge/commands/christopherlouet/claude-base/work-flow-release.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 | $0.00000 | $0.00550 |
| Opus 5.5 | $0.00000 | $0.00220 |
| Sonnet 5.5 | $0.00000 | $0.00110 |
| Haiku 4.5 | $0.00000 | $0.00055 |
Grade A, and why
work-flow-release 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WORK-FLOW-RELEASE Agent
Complete workflow to prepare and publish a release.
Context
$ARGUMENTS
Objective
Execute the complete release cycle: branch, quality audit, changelog, semantic versioning, complete tests, production build, tag, deployment.
Workflow
- BRANCH: Create
release/vX.Y.Zbranch from up-to-date main - AUDIT: Tests, lint, typecheck,
npm audit, build (all must pass) - CHANGELOG: List changes since the last tag (Added, Changed, Fixed, Deprecated, Removed, Security)
- VERSION: Semantic Versioning (breaking = MAJOR, features = MINOR, fixes = PATCH)
- TESTS: Complete validation (unit, integration, E2E, manual)
- BUILD: Production build, verify bundle size and assets
- TAG: Annotated tag
git tag -a vX.Y.Z, push, GitHub release with notes - DEPLOY: Production deployment with rollback plan ready
Performance notes
- Use the project's parallel test runner when one exists. On claude-base specifically,
bash scripts/test.shruns ~4.5x faster thanbats tests/*.batsdirectly (uses GNU parallel + 8 jobs; ~1 min for 455 tests vs ~4-5 min sequential). For other projects, prefernpm test/pytest -n auto/cargo test --jobsover single-threaded invocations. - Run the test suite ONCE per release, after all version bumps + CHANGELOG + generators are done. Doc-only changes (CHANGELOG, version banners, generated files) cannot break the test suite by construction; re-running tests after these changes wastes time.
Expected output
- Audit: Quality go/no-go report
- Changelog: CHANGELOG.md updated
- Release: Tag + release notes on GitHub
- Deploy: Application deployed, monitoring OK
Related agents
| Agent | Usage |
|---|---|
/qa:qa-audit |
Quality audit |
/doc:doc-changelog |
Changelog |
/dev:dev-tdd |
Complete tests |
/ops:ops-release |
Simplified alternative |
/ops:ops-monitoring |
Post-deployment |
IMPORTANT: Never skip tests before a release.
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 · 55 lines · 0 tokens per session scan A b2ffe75d4e7e
work-flow-release is a command published in the GitHub repository christopherlouet/claude-base (5 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 550 tokens. 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 commands, from other repositories
changelog
Generate a changelog entry from git commits since the last tag using conventional commit format.
deploy
Deploy application with pre/post-deploy checks.
sync-ecosystem
Detect API changes, sync satellite repos, and publish releases.
changelog
Auto-generate release notes from merged PRs and FORGE:TRAJECTORY annotations — grouped by conventional commit type.
rollback
Create a revert PR to roll back a shipped feature or fix that caused a production incident.
ship
Complete PR workflow from commit to production with validation.