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 vidhunnan/agentic-skills --skill changelog-trackergit clone --depth 1 https://github.com/vidhunnan/agentic-skillsWrote 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/vidhunnan/agentic-skills/changelog-tracker)<a href="https://agentmods.dev/skills/vidhunnan/agentic-skills/changelog-tracker"><img src="https://agentmods.dev/badge/skills/vidhunnan/agentic-skills/changelog-tracker/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/vidhunnan/agentic-skills/changelog-tracker"><img src="https://agentmods.dev/badge/skills/vidhunnan/agentic-skills/changelog-tracker.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 | $0.00084 | $0.02020 |
| Opus 5 | $0.00042 | $0.01010 |
| Sonnet 5 | $0.00017 | $0.00404 |
| Haiku 4.5 | $0.00008 | $0.00202 |
Grade A, and why
changelog-tracker 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 11d 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
changelog-tracker
Turns commits into a durable, human-readable record. For each substantive commit it writes a per-commit file at changelog/commits/NNN-slug.md (the full "what changed and why") and adds an entry to a rolling changelog/CHANGELOG.md index. This is what keeps a project's history legible long after the diffs scroll out of view.
The guiding rule is faithful, not generative: every fact comes from git. Never invent a rationale, a file, or a hash.
Instructions
Step 0 — Detect your surface
Decide where you're running before doing anything, using Bash availability:
- Claude Code — Bash works and there's a real filesystem + git repo. Proceed with the full flow.
- Claude.ai — no Bash, no git. You can't read commits here. Offer instead to format a per-commit entry from
git show/git logoutput the user pastes in, and skip all file writes and CLAUDE.md registration. Don't error — degrade gracefully.
Confirm you're in a git repo: git rev-parse --show-toplevel. If it fails, tell the user this isn't a git repository and stop.
Step 1 — Resolve which commit(s) to document
- Default target is
HEAD(the just-made commit) when invoked after a commit or via/changelog-trackerwith no argument. - If a
[commit-ref]or range is given, use it. - Detect what's already documented: scan
changelog/commits/*.mdfor recorded hashes. If several undocumented commits exist, list them and confirm which to document (AskUserQuestion) rather than guessing.
Step 2 — Filter (keep the log clean)
Skip commits that shouldn't be documented, and say why when you skip:
- Merge commits —
git log -1 --format=%P <ref>returns 2+ parents. - Changelog-only commits —
git show --stat --format='' <ref>touches only paths underchangelog/. This is how the log avoids chasing its own tail (the commit that adds a changelog entry never gets its own entry).
Step 3 — Gather data from git (never invent)
Per commit, pull everything from git:
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 138 lines · 84 tokens per session scan A 565838219db9
changelog-tracker is a skill published in the GitHub repository vidhunnan/agentic-skills (2 stars, last pushed 5d ago), licensed MIT. It adds 84 tokens to every session and 2,020 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
agent-release-swarm
Agent skill for release-swarm - invoke with $agent-release-swarm.
release-announcement
Write a release announcement — changelog, blog post, in-app note, or social post — that leads with user impact, names the audience, and includes upgrade/migration steps without filler.
multi-agent-release-manager
Cleans up the workspace, formats code, runs presubmit checks, and uploads CLs to Gerrit.
release-notes
Generate user-facing release notes from tickets, PRDs, or changelogs. Creates clear, engaging summaries organized by category (new features, improvements, fixes). Use when writing release notes, creating changelogs, announcing product updates, or summarizing what shipped.
pack-submit
Package one of this agent's own skills as a standalone community pack and submit it to the aeon registry as a PR.
updater_guide
Guidance for checking for and installing Row-Bot updates.