Borrowing it
Nothing to install: this file belongs to shirenchuang/agentbro. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/shirenchuang/agentbro/main/.agents/skills/agentbro-release/SKILL.mdgit clone --depth 1 https://github.com/shirenchuang/agentbroWrote 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/shirenchuang/agentbro/agentbro-release)<a href="https://agentmods.dev/skills/shirenchuang/agentbro/agentbro-release"><img src="https://agentmods.dev/badge/skills/shirenchuang/agentbro/agentbro-release.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 6 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Data Exfiltration · line 239 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 246 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- low Supply Chain · line 239 Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.Fix: Avoid downloading and executing remote scripts. Use trusted packages from PyPI/npm. If remote fetch is required, verify checksums and use HTTPS.
- low Supply Chain · line 246 Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.Fix: Avoid downloading and executing remote scripts. Use trusted packages from PyPI/npm. If remote fetch is required, verify checksums and use HTTPS.
- low Supply Chain · line 253 Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.Fix: Avoid downloading and executing remote scripts. Use trusted packages from PyPI/npm. If remote fetch is required, verify checksums and use HTTPS.
- low Supply Chain · line 260 Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.Fix: Avoid downloading and executing remote scripts. Use trusted packages from PyPI/npm. If remote fetch is required, verify checksums and use HTTPS.
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 | $0.00046 | $0.02564 |
| Opus 5 | $0.00023 | $0.01282 |
| Sonnet 5 | $0.00009 | $0.00513 |
| Haiku 4.5 | $0.00005 | $0.00256 |
Grade A, and why
agentbro-release 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 8d 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.
- If `gh` is not authenticated, use the public GitHub API with `curl` for read-only checks. How it starts
The opening of the file, as written. The whole thing — 273 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AgentBro Release
Use this repository-scoped skill for AgentBro release work. Keep unrelated local changes out of commits.
Safety Rules
- Start with
git status --short --branch. If unrelated files are dirty, do not stage them. - Never reuse or force-move an existing release tag. If a published release is wrong, make the next patch version.
- Do not edit signing keys, certificates, entitlements, or release secrets.
- Do not bump versions in feature PRs. Only bump for an actual release.
- Do not leave
devbehind the latest stable release. Every stable release must be merged back through a PR todev. - If
ghis not authenticated, use the public GitHub API withcurlfor read-only checks.
Version Selection
Use semantic versioning when choosing the next release number:
- Bug fixes and small reliability fixes bump the third number:
X.Y.Z->X.Y.(Z+1). - Minor/user-facing feature releases bump the middle number and reset patch:
X.Y.Z->X.(Y+1).0. - Major breaking releases bump the first number and reset the rest:
X.Y.Z->(X+1).0.0.
When the maintainer explicitly asks for a version, use that version after confirming the tag does not already exist locally or remotely.
Version Files
All four must match:
package.jsonsrc-tauri/tauri.conf.jsonsrc-tauri/Cargo.tomlsrc-tauri/Cargo.lock
After editing the first three, update the lockfile with:
cargo update --manifest-path src-tauri/Cargo.toml -p agentbro
Run:
pnpm release:check
Standard Release Flow
- Fetch current remote state:
git fetch origin main dev --tags
- If releasing from
dev, merge it tomainonly afterdevis pushed:
git checkout main
git pull --ff-only origin main
git merge --no-ff origin/dev -m "Merge branch 'dev' into main"
- If
mainchanged while working, pull it before creating the release commit. Stash only your own release edits if needed:
git stash push -u -m "release-work"
git pull --ff-only origin main
git stash pop
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.
- 8d ago First seen · 273 lines · 0 tokens per session scan A cbde95a313d6
agentbro-release is a skill published in the GitHub repository shirenchuang/agentbro (213 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 46 tokens to every session and 2,564 once invoked, about $0.0002 per session on Opus 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 2026-08-30.
Other skills, from other repositories
release-verification
A release-verification checklist for software versions and packages. It covers changelogs, tests, packaging, installation smoke checks, version-control actions, publishing, and checks after release.
audit-release
A pre-release review assistant that checks whether a software package or plugin is ready to publish.
orchestrate-release-engineer
Run the final release gate: fresh-clone simulation, artifact freshness, packaging hygiene, documentation accuracy. Use in the final hour. Catches the defects that make a working submission fail on someone else's machine.
git-release-manager
Use when the user explicitly asks to prepare, tag, publish, push, or audit a Git release. Inspect branch, worktree, version metadata, changelog, tests, and release artifacts first, obtain confirmation for irreversible release actions, and record a recovery path.
github
Interact with GitHub using the gh CLI. Use for issues, PRs, CI runs, releases, and advanced API queries.
changelog-scan
Scan recent merges/PRs/commits for release note content. Structured output for drafter.