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 commands/sigistry/marketplace/release-notesgit clone --depth 1 https://github.com/sigistry/marketplaceWrote 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/commands/sigistry/marketplace/release-notes)<a href="https://agentmods.dev/commands/sigistry/marketplace/release-notes"><img src="https://agentmods.dev/badge/commands/sigistry/marketplace/release-notes.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 | $0.00020 | $0.00868 |
| Opus 5 | $0.00010 | $0.00434 |
| Sonnet 5 | $0.00004 | $0.00174 |
| Haiku 4.5 | $0.00002 | $0.00087 |
Grade A, and why
release-notes 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 yesterday.
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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Turn a range of git history into human-readable release notes grouped by Keep a Changelog categories, with breaking changes called out at the top and a suggested next version. Works even when the history does NOT use Conventional Commits, it infers change types from diffs and messages. $ARGUMENTS is an optional from-ref..to-ref range.
Process
Step 1: Resolve the range
- If
$ARGUMENTScontains a..range, use it verbatim. - Otherwise find the last release tag:
git describe --tags --abbrev=0and use<last-tag>..HEAD. - If there are no tags at all, use the full history
--root..HEAD(the first release) and say so.
Print the resolved range and the tag it starts from.
Step 2: Gather the history
git log --no-merges --pretty=format:'%H%x09%s%x09%an%x09%ad' --date=short <range>: the commit list.git log --no-merges --pretty=format:'%H%n%B%n==END==' <range>: full bodies, to mine footers and rationale.- For commits whose message is uninformative ("wip", "fix", "update"), read
git show --stat <sha>and, if needed,git show <sha>to infer the real change type from the diff.
Step 3: Classify each commit
Map every commit to a Keep a Changelog category AND note its conventional type where inferable, per the changelog-assembly skill:
| Category | Signals |
|---|---|
| Added | new files/exports/endpoints/flags; feat |
| Changed | modified behavior/defaults/signatures; refactor, perf that alters behavior |
| Deprecated | @deprecated, deprecation notices |
| Removed | deleted exports/endpoints/flags/files |
| Fixed | bug fixes; fix |
| Security | vuln fixes, dependency CVE bumps, auth hardening |
De-duplicate: collapse "fix typo in fix" churn, fold follow-up commits into the feature they complete. Reword terse messages into user-facing language (describe the effect, not the code).
Step 4: Detect breaking changes
Flag any BREAKING CHANGE: footer, any ! marker, and any behavioral break inferable from the diff (removed/renamed public export, changed signature/default, removed flag/env var). Consult the breaking-change-detection skill. Collect these into a prominent top section.
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.
- yesterday First seen · 68 lines · 20 tokens per session scan A 523b0fb48469
release-notes is a command published in the GitHub repository sigistry/marketplace (3 stars, last pushed yesterday), licensed MIT. It adds 20 tokens to every session and 868 once invoked, about $0.0001 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 commands, from other repositories
version-bump
Bump versions across the monorepo during release process.
release
Generate changelog, bump version, and create git tag.
ship
Branch, commit, open PR, gather Claude + every enabled AI reviewer (Copilot, CodeRabbit, etc.), fix/justify/resolve every finding, loop until clean, then merge. Run only when implementation is finished AND the owner has said to ship (e.g. "ship it") — never self-invoke just because the work looks done. To design and…
release
Prepare a release of the sonu plugin — decide the semver bump, sync the version and plugin description across all five homes, run /validate, then hand to /sonu:ship. Only meaningful inside the claude-plugins repo; in any other repo, say so and stop.
cancel-ship
Cancel active ship pipeline.
copush
Pull, version-bump, commit all changes, and push to origin.