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 instructions/destynova2/cli-code-skills/claude-mdgit clone --depth 1 https://github.com/Destynova2/cli-code-skillsWhat 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 | $0.01058 | $0.01058 |
| Opus 5 | $0.00529 | $0.00529 |
| Sonnet 5 | $0.00212 | $0.00212 |
| Haiku 4.5 | $0.00106 | $0.00106 |
Grade A, and why
cli-code-skills CLAUDE.md 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 2d 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — cli-code-skills
Skills installation
Skills are installed as copies in ~/.claude/skills/ for Claude Code,
~/.codex/skills/ for Codex, and ~/.jcode/skills/ for Jcode (global,
available in all projects). Jcode is only touched when ~/.jcode exists.
Source of truth is this repo (~/workspace/cli-code-skills/).
After modifying a skill in this repo, copy it to every runtime:
scripts/install_skills.sh
Or install only one runtime:
scripts/install_skills.sh --claude
scripts/install_skills.sh --codex
scripts/install_skills.sh --jcode
The installer removes each destination skill before copying it. That avoids stale files when a reference is renamed or deleted.
The safe direction is repo → runtime. If a runtime copy was edited in place and
that edit is not yet in the repo, the installer refuses to overwrite it
(exit 3) rather than destroy it. It tracks this with a .skills-manifest written
into each runtime skills root at install time.
scripts/install_skills.sh --check # report divergence, change nothing
scripts/install_skills.sh --pull-claude # copy Claude in-place edits back into the repo
scripts/install_skills.sh --pull-codex # copy Codex in-place edits back into the repo
scripts/install_skills.sh --pull-jcode # copy Jcode in-place edits back into the repo
scripts/install_skills.sh --force # overwrite even runtime-ahead edits
If you (or a session) edited a skill directly in ~/.claude/skills/, run
--pull-claude to bring it back into the repo, review git diff, validate, and
commit — then a normal install re-syncs both runtimes.
Shared files (gotchas.md and shared/) are referenced by root SKILL.md
files as ../<name> and by references/ files as ../../<name>.
The installer copies them to the skills root for every runtime.
Do NOT use symlinks — use real copies.
Validation
Before committing or installing changes, run:
python3 scripts/validate_skills.py
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.
- 2d ago First seen · 99 lines · 1,058 tokens per session scan A dfdb38deeb04
cli-code-skills CLAUDE.md is an instructions file published in the GitHub repository Destynova2/cli-code-skills (5 stars, last pushed 10d ago), licensed MIT. It adds 1,058 tokens to every session, about $0.0053 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 instructions, from other repositories
claude-sdlc-harness AGENTS.md
AGENTS.md instructions for BaseInfinity/claude-sdlc-harness, covering codex review guidelines, project overview, ai setup lanes, review focus areas and 1. sdlc compliance.
claude-sdlc-harness CLAUDE.md
Claude Code instructions for BaseInfinity/claude-sdlc-harness, covering sdlc harness - claude instructions, project overview, what this repo contains, what this repo does not have and test dependencies.
vibe-check-mcp CLAUDE.md
Claude Code instructions for kesslerio/vibe-check-mcp, covering first: quick interrupt, standard testing (90% of cases) and mock testing when needed (test factory available).
vibe-check-mcp AGENTS.md
AGENTS.md instructions for kesslerio/vibe-check-mcp, a project described as: Stop AI coding disasters before they cost you weeks. Real-time anti-pattern detection for vibe coders who love AI tools but need a safety net to avoid expensive overengineering traps.
vibe-check-mcp GEMINI.md
Gemini CLI instructions for kesslerio/vibe-check-mcp, a project described as: Stop AI coding disasters before they cost you weeks. Real-time anti-pattern detection for vibe coders who love AI tools but need a safety net to avoid expensive overengineering traps.
mcp-server-excel coverage-prevention-strategy.instructions.md
Instructions for sbroenne/mcp-server-excel, covering generated surface coverage, contract change workflow, required checks and common incomplete changes.