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 agentmods add skills/juan294/cc-rpi/github-clinpx skills add juan294/cc-rpi --skill github-cligit clone --depth 1 https://github.com/juan294/cc-rpiWhat 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 | $0.00028 | $0.00783 |
| Opus 5 | $0.00014 | $0.00392 |
| Sonnet 5 | $0.00006 | $0.00157 |
| Haiku 4.5 | $0.00003 | $0.00078 |
Grade A, and why
github-cli 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 yesterday.
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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub CLI
JSON Field Discovery
Wrong -- guess field names:
gh pr checks 42 --json conclusion # Unknown field
Right -- discover fields first:
gh pr checks 42 --json 2>&1 | head -5
PR Check Interpretation
Wrong -- exit code 0 means passed, raw output is readable:
gh pr checks 42 # exit 0 but checks still pending; "review: fail" looks like CI
Right -- use structured JSON, filter review, or --watch:
gh pr checks 42 --json name,state,conclusion | jq '.[] | select(.name != "review")'
gh pr checks 42 --watch
Release vs PR Flags
Wrong -- --body is for pr/issue create, not release:
gh release create v1.0.0 --body "notes"
Right -- releases use --notes:
gh release create v1.0.0 --notes "notes"
Label and Merge Settings
Wrong -- assume labels exist and merge method is allowed:
gh issue create --label "chore" --title "Fix" # label not found
gh pr merge 42 --merge # method not allowed
Right -- check or create first:
gh label list && gh label create "chore" --color "ededed"
gh api repos/{owner}/{repo} --jq '.allow_squash_merge, .allow_merge_commit'
When creating multiple issues, create them sequentially, not as parallel
tool calls -- a batch of parallel gh issue create calls that all hit the
same missing label fail together instead of surfacing once.
Deprecated Projects (Classic) API
Wrong -- an older gh version queries a removed field and errors:
gh issue view 42 --json projectCards # Projects (classic) is deprecated
Right -- upgrade gh first:
brew upgrade gh
CodeQL Requires GHAS
Wrong -- add a code-scanning workflow without checking GHAS is enabled:
# .github/workflows/codeql.yml added blindly -- fails CI on every push
Right -- confirm GHAS is enabled before adding the workflow:
gh api repos/{owner}/{repo}/code-scanning/alerts # non-403 = GHAS enabled
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.
- yesterday First seen · 134 lines · 28 tokens per session scan A df092250fbd9
github-cli is a skill published in the GitHub repository juan294/cc-rpi (5 stars, last pushed 12d ago), licensed MIT. It adds 28 tokens to every session and 783 once invoked, about $0.0001 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
claude-md-review
Audit a CLAUDE.md file for the patterns that actually degrade Claude Code's output — vagueness, unnamed files, stale facts, and bloat. Use when asked to review, audit, improve, shrink, or fix a CLAUDE.md, and when a project's results feel inconsistent or Claude keeps rediscovering the same context.
best-practices
Searchable knowledge base of 152+ programming best practices across 30+ languages and frameworks. BM25-powered search over curated resources from industry leaders (Google, Airbnb, Uber, Mozilla, Shopify, OWASP).
common-session-retrospective
Analyze conversation corrections to detect skill gaps and prepare targeted skill-library maintenance tasks. Use after any session with user corrections, rework, or retrospective requests. After finding correction loops, also load +common/common-learning-log to persist mistake entries to AGENTSLEARNING.md.
common-workflow-writing
Rules for writing concise, token-efficient workflow and skill files. Prevents over-building that requires costly optimization passes. Use when creating or editing workflow files, SKILL.md files, or new skill definitions.
JavaScript Tooling
Development tools, linting, and testing for JavaScript projects.
common-ui-design
Design distinctive, production-grade frontend UI with bold aesthetic choices. Use when building web components, pages, interfaces, dashboards, or applications in any framework (React, Next.js, Angular, Vue, HTML/CSS).