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/release-summarizer)<a href="https://agentmods.dev/agents/orin-dx/agent-plugins/release-summarizer"><img src="https://agentmods.dev/badge/agents/orin-dx/agent-plugins/release-summarizer/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/release-summarizer"><img src="https://agentmods.dev/badge/agents/orin-dx/agent-plugins/release-summarizer.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 | $0.00191 | $0.01103 |
| Opus 5.5 | $0.00076 | $0.00441 |
| Sonnet 5.5 | $0.00038 | $0.00221 |
| Haiku 4.5 | $0.00019 | $0.00110 |
Grade A, and why
release-summarizer 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 — 67 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>
Key failure modes:
- A changeset appears in the output despite consumer_impact: internal-only.
- The computed version bump is lower than what the highest semver_impact entry requires.
- A summary is rewritten and drifts from what changeset-analyzer actually verified.
{
"version": "1.2.0",
"date": "2026-08-04",
"changesets": [
{
"summary": "string (user-facing, carried through from changeset@2 unedited)",
"consumer_impact": "behavior-change|new-capability|internal-only",
"semver_impact": "major|minor|patch|none",
"linked_requirement": "REQ-001",
"commits": ["string"]
}
],
"breaking_changes": ["string"],
"reasoning": "string"
}
reasoning is a scratchpad — include the prior version, which changeset's semver_impact determined the bump, and formatted markdown release notes here. It is not forwarded downstream.
WHEN breaking_changes are present in any input changeset, aggregate all of them into the top-level breaking_changes array.
IF a changeset entry has consumer_impact: internal-only, NEVER include it in the output changesets array.
THE SYSTEM SHALL set version to the prior version bumped by max(semver_impact) across the included changesets — major > minor > patch > none — never by asking which version "sounds right."
NEVER rewrite a carried-through summary — changeset-analyzer already wrote it in consumer-facing language at the detail its semver_impact earns.
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 d4d5bd9d2f6e
- 1mo ago Changed · +5 lines 5a6dbbc58f3b
- 1mo ago First seen · 61 lines · 191 tokens per session scan A 969f334443e3
release-summarizer is an agent published in the GitHub repository orin-dx/agent-plugins (1 stars, last pushed 19d ago), licensed MIT. It adds 191 tokens to every session and 1,103 once invoked, about $0.0008 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.