Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/starcat-app/Starcatnpx agentmods add skills/starcat-app/starcat/starcat-update-changelogWrote 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/starcat-app/starcat/starcat-update-changelog)<a href="https://agentmods.dev/skills/starcat-app/starcat/starcat-update-changelog"><img src="https://agentmods.dev/badge/skills/starcat-app/starcat/starcat-update-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/skills/starcat-app/starcat/starcat-update-changelog"><img src="https://agentmods.dev/badge/skills/starcat-app/starcat/starcat-update-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 | $0.00098 | $0.03356 |
| Opus 5.5 | $0.00039 | $0.01342 |
| Sonnet 5.5 | $0.00020 | $0.00671 |
| Haiku 4.5 | $0.00010 | $0.00336 |
Grade A, and why
starcat-update-changelog scanned grade A with 1 finding 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 23d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Requires: `git`, `python3`, `rsync`, `ssh`, `curl` How it starts
The opening of the file, as written. The whole thing — 345 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Update Starcat Changelog
Read ALL git commits from the main Starcat project since the last version tag, then update
CHANGELOG.md (English) and CHANGELOG-ZH.md (Chinese) in supports/starcat-pro/.
File Locations
| File | Path |
|---|---|
| Changelog (EN) | supports/starcat-pro/CHANGELOG.md |
| Changelog (ZH) | supports/starcat-pro/CHANGELOG-ZH.md |
| Git repo (source) | Starcat root (the Xcode project) |
Step 0: Ask for Version Number (MANDATORY — Do This FIRST)
This is a blocking step. Before reading any git log or touching any file, you MUST know the target version number. If the user did not provide one in their invocation, immediately ask:
"Which version number should I use for this changelog entry? (e.g.,
1.2.0,1.1.1)"
Do NOT proceed to Step 1 until the user answers. Do NOT guess or assume a version number.
If the user's invocation already includes a version number (e.g., "update changelog for 1.2.0"),
validate that it matches X.Y.Z format. If it doesn't, ask the user to provide a valid format.
The version number must be in X.Y.Z format (semantic versioning) because release-direct.sh
requires this format.
Step 1: Determine Commit Range
# Latest tag
git tag --sort=-creatordate | head -1
# All commits since that tag (NO filtering, NO skip)
git log <latest-tag>..HEAD --oneline --no-merges
# Count
git log <latest-tag>..HEAD --oneline --no-merges | wc -l
If no tag exists, start from the first commit.
If there are 0 commits since the latest tag, stop and tell the user: "No new commits since . There's nothing to add to the changelog."
Step 2: Read EVERY Commit Message (Do NOT Skip Any)
# Full messages for ALL non-merge commits — every single one
git log <latest-tag>..HEAD --format="---COMMIT---%n%h%n%s%n%b" --no-merges
Critical rule: Read EVERY commit first. Then in Step 3a, filter out non-user-facing changes. Don't skip commits at read time — some commits with non-standard prefixes may still describe user-visible changes. The filtering happens AFTER reading, based on content.
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.
- 23d ago First seen · 345 lines · 98 tokens per session scan A 8c41107d509b
starcat-update-changelog is a skill published in the GitHub repository starcat-app/Starcat (201 stars, last pushed 4d ago), licensed MIT. It adds 98 tokens to every session and 3,356 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-23.
Other skills, from other repositories
git-wrapup
Land working-tree changes as logical commits — the work grouped by concern, topped by a release commit (version bump, changelog, regenerated artifacts). The work commits land first, then the version bump, verification, and the release commit on top. Stops at "committed locally on main" — or, when the project releases…
release-and-publish
Ship a release end-to-end across every registry the project targets (npm, MCP Registry, GitHub Releases for .mcpb bundles, GHCR). Runs the final verification gate, fast-forwards main when the release rode a release PR, creates the annotated tag on the commit main now points at, pushes commits and tags, then publishes…
release-pr-review
Review pass on an open release PR (release/ → main) — the step between git-wrapup and release-and-publish when a project releases in gated release PR mode. Reads the PR's commit range through the code-simplifier lens plus a correctness review, verifies whatever an automated reviewer left on the PR, lands fixes as…
release
Prepare, verify, and publish Sutando engine releases. Use when asked to prepare a release proposal, determine a version bump, audit release documentation, validate release gates, create a release PR, tag a confirmed release, or publish GitHub release notes. Preparation is safe and non-publishing; tagging and…
multi-repo-release
Prepares and validates GPT-RAG umbrella and multi-repository releases. Use whenever work involves release preparation, semantic versions, release branches, manifest or component pins, changelog release entries, tags, GitHub Release notes, or AI Landing Zone release alignment.
publish-plugins
(project) Use when editing any file under skills/ or plugins/ to bump the plugin version and check the manifests.