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/xiaotonng/pikiloomnpx agentmods add skills/xiaotonng/pikiloom/installWrote 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/xiaotonng/pikiloom/install)<a href="https://agentmods.dev/skills/xiaotonng/pikiloom/install"><img src="https://agentmods.dev/badge/skills/xiaotonng/pikiloom/install/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/xiaotonng/pikiloom/install"><img src="https://agentmods.dev/badge/skills/xiaotonng/pikiloom/install.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00039 | $0.00474 |
| Opus 5.5 | $0.00016 | $0.00190 |
| Sonnet 5.5 | $0.00008 | $0.00095 |
| Haiku 4.5 | $0.00004 | $0.00047 |
Grade A, and why
install scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Install & Publish pikiclaw
1. Run the release script
./scripts/release.sh
This script handles: version bump -> build -> npm link -> verify -> git commit/tag/push -> wait for CI.
If the script fails, diagnose and fix the issue, then re-run it.
2. Write release notes
After CI creates the GitHub Release, update it with meaningful release notes:
- Run
git log v<previous-version>..v<new-version> --oneline --no-mergesto collect all commits since the last release. - Summarize changes into categories (use only relevant ones, skip empty categories):
- New Features - new user-facing functionality
- Improvements - enhancements to existing features
- Bug Fixes - resolved issues
- Internal - refactors, dependency updates, CI changes
- Write concise, user-friendly descriptions (not raw commit messages).
- Update the GitHub Release using:
gh release edit v<new-version> --notes "$(cat <<'EOF' ## What's Changed ### New Features - description of feature ### Bug Fixes - description of fix **Full Changelog**: https://github.com/xiaotonng/pikiclaw/compare/v<previous-version>...v<new-version> EOF )" - Verify the release notes look correct:
gh release view v<new-version>.
Notes
npm linkcreates a global symlink - rebuild withnpm run buildafter code changes.- The
filesfield inpackage.jsoncontrols what gets published:dist/,LICENSE,README.md. - CI pipeline (
.github/workflows/release.yml): builds, publishes to npm, and creates GitHub Release onv*tag push. - To uninstall locally:
npm unlink -g pikiclaw.
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.
- 1mo ago First seen · 53 lines · 39 tokens per session scan A f4e0ec63f5d5
install is a skill published in the GitHub repository xiaotonng/pikiloom (295 stars, last pushed 7d ago), licensed MIT. It adds 39 tokens to every session and 474 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
ensemble-release
Automated release workflow orchestration with quality gates, smoke test integration, (Codex skill for /ensemble:release).
changelog-generator
Quick Reference - Parse conventional commits and generate categorized changelog.
draft-release-notes
Author the committed release-notes file for a Prisma 8 release (stable or 8.0.0-rc.N) by enumerating the merged PRs since the previous release v tag (stable or -rc.N), resolving opaque TML-NNNN: titles via Linear context (never copied verbatim), triaging public-worthiness, and writing categorized notes — breaking…
publish-npm-version
Cuts the next release of Prisma 8: bumps the root package.json version (on the v8 RC line: 8.0.0-rc.N → rc.N+1), propagates it to every workspace package, and opens a PR titled "chore(release): bump to ". When the maintainer merges the PR, the Publish to npm workflow runs automatically and ships the new version to npm…
codew-release-qa-sweep
Use before claiming Codewhale release work is done: run the full gate sweep and list the manual QA targets.
release
Skill "release" from Hmbown/Codewhale, covering release, invocation, non-goals and workflow.