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 skills add mickeyyaya/evolve-loop --skill verify-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/verify-release)<a href="https://agentmods.dev/skills/mickeyyaya/evolve-loop/verify-release"><img src="https://agentmods.dev/badge/skills/mickeyyaya/evolve-loop/verify-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/skills/mickeyyaya/evolve-loop/verify-release"><img src="https://agentmods.dev/badge/skills/mickeyyaya/evolve-loop/verify-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 | $0.00049 | $0.00836 |
| Opus 5.5 | $0.00020 | $0.00334 |
| Sonnet 5.5 | $0.00010 | $0.00167 |
| Haiku 4.5 | $0.00005 | $0.00084 |
Grade A, and why
verify-release scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 14d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/evo:verify-release
Standalone post-publish propagation check. It polls the local marketplace checkout until the checkout shows the target version. Use it after a manual
git pushto confirm that the new version landed. Use it also when a user asks "is my installed plugin out of date?"
What this skill does
The skill runs evolve marketplace-poll (go/internal/marketplacepoll). On each poll, the command does these steps:
- If the marketplace directory is a git checkout, run
git fetch origin mainandgit reset --hard origin/mainin it. - Read the
versionfield of~/.claude/plugins/marketplaces/evo/.claude-plugin/plugin.json. - Compare that version with the target version. When they match, exit 0.
The command does not refresh installed_plugins.json. That refresh called release.sh, and the Go migration removed the script. The step is now a no-op (DefaultReleaseSh returns nil), but the command still prints a running release.sh log line.
The slash command translates to:
"$CLAUDE_PROJECT_DIR/go/evolve" marketplace-poll <args>
Invocation
/evo:verify-release 8.13.4 # default: poll up to 5 min, 15s interval
/evo:verify-release 8.13.4 --max-wait-s 60 # shorter deadline (faster diagnostic)
/evo:verify-release 8.13.4 --poll-interval-s 5 # tighter loop, faster convergence detection
/evo:verify-release 8.13.4 --dry-run # print the poll parameters; do not pull
When to use this skill
- After a manual ship that did not use
/evo:publish(for example, a hot fix throughevolve ship --class manual). The marketplace does not pull by itself. This skill makes sure that it caught up. - Stale-plugin reports. If a user says "I'm running v8.13.2 but the marketplace shows v8.13.1," run
/evo:verify-release 8.13.2to force a marketplace pull. - After a
git push origin mainthat used the explicitevolve guard ship --bypassemergency path.
When NOT to use this skill
- During an in-flight
/evo:publishrun. The pipeline already polls internally. Running this concurrently could race against the pipeline's poll loop. - For non-evo marketplaces. This skill targets the evo marketplace specifically. Override the default path with
--marketplace-dir <path>if you need to point elsewhere.
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.
- 14d ago Changed · +6 lines · -11 tokens per session b5dd8753109f
- 1mo ago First seen · 58 lines · 60 tokens per session scan A 27cfcdd1c98f
verify-release is a skill published in the GitHub repository mickeyyaya/evolve-loop (6 stars, last pushed 2d ago), licensed Apache-2.0. It adds 49 tokens to every session and 836 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 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.
sw-ship
Ships the current work unit. Verifies all gates passed, creates a PR with evidence-mapped body, updates workflow state to shipped.
push-ci
Push to remote and monitor CI. Validates branch safety, executes git push WITH explicit user approval, then monitors CI run status via gh CLI. Use when: user says 'push', 'push and watch CI', 'ship it', 'push-ci'. Not for: committing (use /smart-commit), creating PRs (use /create-pr), merging (use /merge-prep).