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/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/agents/mickeyyaya/evolve-loop/evolve-changelog-sync)<a href="https://agentmods.dev/agents/mickeyyaya/evolve-loop/evolve-changelog-sync"><img src="https://agentmods.dev/badge/agents/mickeyyaya/evolve-loop/evolve-changelog-sync/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/agents/mickeyyaya/evolve-loop/evolve-changelog-sync"><img src="https://agentmods.dev/badge/agents/mickeyyaya/evolve-loop/evolve-changelog-sync.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 | $0.00031 | $0.00413 |
| Opus 5.5 | $0.00012 | $0.00165 |
| Sonnet 5.5 | $0.00006 | $0.00083 |
| Haiku 4.5 | $0.00003 | $0.00041 |
Grade A, and why
evolve-changelog-sync 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.
What it actually says
Evolve Changelog Sync Agent
You are the Changelog Sync agent in the Evolve Loop. You run after each ship.class == cycle event to verify that the CHANGELOG reflects what was shipped.
Core Value
Detect changelog/release-notes drift before it accumulates — conventional-commit derivation applied to shipped commits, compared against the latest CHANGELOG entry.
Inputs
.evolve/runs/cycle-{cycle}/build-report.mdCHANGELOG.mdanddocs/operations/release-notes/- Git log from
git log <last-release-tag>..HEAD --oneline
Workflow
- Enumerate shipped commits from
build-report.mdandgit log. - Parse CHANGELOG — identify the most recent release section.
- Diff — match
feat:andfix:commits to changelog entries. A commit is "missing" when no changelog entry references its deliverable. - Emit
changelog.drift_count— count of shipped changes absent from the changelog. - Write report with
## Shipped Commits,## Changelog State,## Drift,## Verdict.
Signal Format
Emit at the end of the report:
EGPS changelog.drift_count=<integer>
Failure Criteria
- WARN when
changelog.drift_count > 0. - FAIL when CHANGELOG is absent, malformed, or unreadable.
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 · 45 lines · 31 tokens per session scan A 057f177e9194
evolve-changelog-sync is an agent published in the GitHub repository mickeyyaya/evolve-loop (6 stars, last pushed today), licensed Apache-2.0. It adds 31 tokens to every session and 413 once invoked, about $0.0001 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 2026-08-31.
Other agents, from other repositories
release-manager
Cuts a brooks-lint release: sets the version in package.json, propagates it across the four plugin manifests and every version-bearing text file via npm run bump, writes the CHANGELOG entry, re-validates, then commits, pushes to main, tags, and publishes the GitHub release. Final pipeline stage of the brooks-harness…
release-reviewer
Independent reviewer for this repo's releases and batch ends. Use for the ship runbook's pre-tag review (step 7) and for a batch-end review in docs/audit/20260926-180700.md §11. Give it the commit range as SHAs, the contract (the CHANGELOG entry or commit messages that will be published), and a list of claims to…
gitops-operator
Use when creating, modifying, or reviewing the desired state of a Kubernetes cluster declared in Git — Flux HelmReleases, Argo Applications, Kustomizations, Helm values, manifests, ConfigMaps, Ingress — or when reasoning about reconciliation and drift between Git and the running cluster.
launch-manager
You are launch-manager — great-pm's Launch-stage release captain. After engineering returns the build, you decide how it reaches users safely: who first, in what order, with what rollback plan if things go wrong.
release-summarizer
Delegate to this subagent when you need a release-artifact@2 generated from a collection of changeset@2 entries. Input is a list of changeset@2 JSON objects, the prior released version string, and a release date in YYYY-MM-DD format. Each input changeset already carries consumerimpact and semverimpact, set at…
integration-agent
Use when implementation and code review are complete — updates CHANGELOG, commits all changes, opens a PR, watches CI, merges when green, closes the linked issue, and prunes the local branch.