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/mertjane/awesome-claude-commandsWrote 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/mertjane/awesome-claude-commands/changelog)<a href="https://agentmods.dev/commands/mertjane/awesome-claude-commands/changelog"><img src="https://agentmods.dev/badge/commands/mertjane/awesome-claude-commands/changelog/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/commands/mertjane/awesome-claude-commands/changelog"><img src="https://agentmods.dev/badge/commands/mertjane/awesome-claude-commands/changelog.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 | $0.00032 | $0.01120 |
| Opus 5.5 | $0.00013 | $0.00448 |
| Sonnet 5.5 | $0.00006 | $0.00224 |
| Haiku 4.5 | $0.00003 | $0.00112 |
Grade A, and why
changelog 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 2mo 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 — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generate CHANGELOG.md
Analyze git history and produce a CHANGELOG.md following the Keep a Changelog format.
If $ARGUMENTS is provided, use it as the new version number (e.g. 1.2.0). Otherwise auto-detect from package.json or use Unreleased.
Step 1 — Detect Version
From $ARGUMENTS: Use as-is. Strip leading v if present for the version number, keep v for git tags.
Auto-detect: Read package.json → version field. If not found, use Unreleased.
Step 2 — Get Git Log
Run:
git tag --sort=-version:refname | head -1
to find the latest existing tag.
If a tag exists, run:
git log {latest-tag}..HEAD --pretty=format:"%H|%s|%an|%ad" --date=short
If no tags exist, run:
git log --pretty=format:"%H|%s|%an|%ad" --date=short
If git is not available or no commits exist, report and stop.
Step 3 — Parse and Classify Commits
For each commit line (hash|subject|author|date):
Parse Conventional Commits format (type(scope): subject):
| Commit type | Changelog section |
|---|---|
feat |
Added |
fix |
Fixed |
refactor, perf |
Changed |
style |
Changed |
docs |
Changed |
chore, test, ci |
— (omit from changelog unless meaningful) |
revert |
Fixed |
Breaking change (! or BREAKING CHANGE:) |
⚠ Breaking |
For non-conventional commits, classify by keywords in the subject:
add,create,implement,new→ Addedfix,bug,patch,resolve,correct→ Fixedupdate,change,improve,refactor,optimize→ Changedremove,delete,drop,deprecate→ Removedsecurity,cve,vulnerability,auth→ Security
Skip these commits:
- Merge commits (
Merge branch,Merge pull request) - WIP commits (
wip,work in progress) - Release commits that only bump version
Step 4 — Read Existing CHANGELOG.md
If CHANGELOG.md exists, read it.
The new version entry will be prepended before the existing entries, preserving all previous history.
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.
- 2mo ago First seen · 157 lines · 32 tokens per session scan A c3c5832a437a
changelog is a command published in the GitHub repository mertjane/awesome-claude-commands (2 stars, last pushed 8mo ago), licensed MIT. It adds 32 tokens to every session and 1,120 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.
changelog compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| changelogmertjane/awesome-claude-commands | Command | 2 | 8mo ago | MIT | A | 32 | Claude Code |
| add-changelogdavepoon/buildwithclaude | Command | 3.7k | yesterday | MIT | A | 6 | Claude Code |
| publishcode-yeongyu/oh-my-openagent | Command | 71k | yesterday | none | A | 12 | Claude Code, OpenCode |
| get-unpublished-changescode-yeongyu/oh-my-openagent | Command | 71k | yesterday | none | A | 16 | OpenCode |
| releasejezweb/claude-skills | Command | 1.1k | 28d ago | MIT | B | 7 | Claude Code |
| commitfusengine/agents | Command | 34 | 25d ago | MIT | A | 31 | Claude Code |
| shipCavalry-Collective/visual-stack | Command | 11 | yesterday | MIT | A | 16 | Claude Code |