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 skills/mickeyyaya/evolve-loop/releasenpx skills add mickeyyaya/evolve-loop --skill releasegit clone --depth 1 https://github.com/mickeyyaya/evolve-loopWrote 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/skills/mickeyyaya/evolve-loop/release)<a href="https://agentmods.dev/skills/mickeyyaya/evolve-loop/release"><img src="https://agentmods.dev/badge/skills/mickeyyaya/evolve-loop/release.svg" alt="Measured on agentmods" 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 | $0.00083 | $0.00894 |
| Opus 5 | $0.00042 | $0.00447 |
| Sonnet 5 | $0.00017 | $0.00179 |
| Haiku 4.5 | $0.00008 | $0.00089 |
Grade A, and why
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 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/evo:release
Release readiness-gate, not a release executor. It composes the checks that already exist (
evolve release-preflight,evolve release-consistency) and adds the two gaps they miss — CI green onmainHEAD and no WIP/fixup commits — then hands a green report to/evo:publish, which owns the actual bump → changelog → ship → propagate lifecycle.
Why this exists
evolve release-preflight already gates: clean tree, attached branch, semver bump, recent audit PASS, gate-test suites. evolve release-consistency already verifies the 6 version markers (plugin.json, marketplace.json, README, CHANGELOG, SKILL headings). Neither checks whether GitHub CI is actually green on the commit you're about to release from, nor screens for accidental WIP commits. This skill closes exactly those gaps — nothing more.
Defense-in-depth:
/evo:publishnow performs the same pre-release CI-green check itself (so a direct/evo:publishcall is still gated) and adds a post-release watch of the released commit'sgo/CIworkflows. Running/evo:releasefirst stays the recommended path;evolve release(the raw binary) isgh-free and only prints a "CI not verified" advisory.
Procedure
Run in order. Any FAIL → print the reason and stop (do not delegate to /evo:publish).
- Preflight (5 gates) — read-only:
Non-zero exit → stop.$CLAUDE_PROJECT_DIR/go/bin/evolve release-preflight <target> --dry-run - Consistency (version markers):
Non-zero exit → stop.$CLAUDE_PROJECT_DIR/go/bin/evolve release-consistency <target> - Gap 1 — CI green on
mainHEAD (requiresgh; if absent, report "cannot verify CI" and stop):
Confirmgh run list --branch main --limit 1 --json headSha,status,conclusion,urlheadShamatchesgit rev-parse origin/main,status == "completed",conclusion == "success". Anything else (in-progress, failure, stale SHA) → stop with the run URL. - Gap 2 — no WIP/fixup commits since the last tag:
If any subject matchesgit log "$(git describe --tags --abbrev=0)..HEAD" --format=%s^(WIP|fixup!|squash!|amend!)→ stop and list them. - All green → delegate: invoke
/evo:publish <target>(pass--dry-runthrough if the user gave it). Report the readiness summary first so the user sees what passed.
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 · 60 lines · 83 tokens per session scan A 8d97904d305e
release is a skill published in the GitHub repository mickeyyaya/evolve-loop (5 stars, last pushed 2d ago), licensed Apache-2.0. It adds 83 tokens to every session and 894 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
release
Cut a brooks-lint release: set the version in package.json, propagate it across all four plugin manifests and every version-bearing text file (README badges, docs site metadata), write the CHANGELOG entry, validate, then commit, push, tag, and publish the GitHub release. Triggers when the maintainer asks to "release"…
bump-version
Bump the Logic-Lens version across all six metadata locations at once (package.json, the four plugin manifests, and the README badge), then validate. Use when cutting a release or when npm run validate reports a version mismatch.
release-docs
Diff-driven documentation sync after a release. Determines what source files changed, delegates changelog to zuvo:docs, updates only docs whose source changed. Flags: --dry-run, explicit range argument.
changelog
Add CHANGELOG.md entries, derive them from commits, or cut a Keep a Changelog and SemVer release.
ship
Pre-merge release pipeline: run tests, auto-scaled code review, version bump, changelog generation, git tag, push or PR. Auto-detects branch context (direct push on main, PR on feature branch). Scales review depth by diff size. Flags: --full, --no-bump, --no-tag, --dry-run, patch/minor/major.
sw-ship
Ships the current work unit. Verifies all gates passed, creates a PR with evidence-mapped body, updates workflow state to shipped.