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/orin-dx/agent-pluginsWrote 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/orin-dx/agent-plugins/changeset-analyzer)<a href="https://agentmods.dev/agents/orin-dx/agent-plugins/changeset-analyzer"><img src="https://agentmods.dev/badge/agents/orin-dx/agent-plugins/changeset-analyzer/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/orin-dx/agent-plugins/changeset-analyzer"><img src="https://agentmods.dev/badge/agents/orin-dx/agent-plugins/changeset-analyzer.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 | $0.00233 | $0.01970 |
| Opus 5.5 | $0.00093 | $0.00788 |
| Sonnet 5.5 | $0.00047 | $0.00394 |
| Haiku 4.5 | $0.00023 | $0.00197 |
Grade A, and why
changeset-analyzer 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<load_first> shared/references/delivery/changesets.md </load_first>
Decide what belongs together by checking, in order:
- Shared artifact. The same
linked_spec,linked_plan, orlinked_requirementdefines one scope across packages. Different links define separate scopes. - Explicit shared scope. Honor a stated cross-package purpose such as a testing push or coordinated release.
- Shared cause. When neither signal exists, ask whether one change exists because of another. Independent causes need separate changesets.
None of this proxies file, package, or commit count. Check 1 and 2 first — most cases resolve there. When step 3 still leaves genuine ambiguity, splitting is the fallback, not the default; reaching for it without checking 1 and 2 first produces changeset sprawl. Verify a topic's file/package attribution against its own diff slice, not a summary of the whole batch.
Beyond that: the changeset succeeds when each summary is written for a consumer assessing whether that specific change affects them, at the level of detail its semver_impact earns. Classify consumer_impact and semver_impact from shared/references/delivery/changesets.md; if no row fits cleanly, choose the more conservative bump and explain why in reasoning.
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 Changed · +1 lines · +2 tokens per session 3cee14803076
- 1mo ago Changed · +3 lines f8a288d8e939
- 1mo ago Changed · +6 lines 7f19c210a0e4
- 1mo ago First seen · 86 lines · 231 tokens per session scan A 925a6eae0582
changeset-analyzer is an agent published in the GitHub repository orin-dx/agent-plugins (1 stars, last pushed 19d ago), licensed MIT. It adds 233 tokens to every session and 1,970 once invoked, about $0.0009 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-captain
Owns the release ritual end-to-end — semver decisions, changelog generation, version bumping, tagging, release notes, deploy gates, rollback rehearsal, and post-release verification. Catches the silly mistakes that turn a routine release into a Sunday outage. Use before cutting any new version, or when a release went…
evolve-merge-to-main-gate
Merge-to-main promotion-readiness gate for the Evolve Loop (Evaluate archetype). The campaign executor invokes this at milestone/wave boundaries to verify a completed milestone's already-integrated work is ready to be promoted to main, emitting a PASS/WARN/FAIL verdict plus mergegate. signals. READ-ONLY — it never…
evolve-changelog-sync
Changelog drift controller (Control archetype) — verifies CHANGELOG/release-notes match shipped commits after every cycle ship.
evolve-rollback-plan
Revert readiness controller (Control archetype).
release-auditor
Internal dynos-work agent. Audits rollout, rollback, migrations, feature flags, versioning, and release hygiene. Spawned only by the dynos-work pipeline during an explicitly invoked /dynos-work:audit; never spawn this agent directly, from conversation, or outside a dynos-work task.