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 commands/alirezarezvani/claude-skills/readmegit clone --depth 1 https://github.com/alirezarezvani/claude-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 | $0.00000 | $0.01825 |
| Opus 5 | $0.00000 | $0.00912 |
| Sonnet 5 | $0.00000 | $0.00365 |
| Haiku 4.5 | $0.00000 | $0.00183 |
Grade A, and why
README 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 — 352 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Skills Slash Commands
Git workflow and quality assurance commands for the claude-skills repository.
🎯 Essential Commands
Git Workflow
/git:cm → Stage and commit (no push)
/git:cp → Stage, commit, and push
/git:pr → Create pull request
/git:clean → Delete merged branches (local + remote)
Quality Gates
/review → Run local quality checks
/security-scan → Run security validation
/update-docs → Post-creation sync (CLI platforms, marketplace, docs, GitHub Pages)
📋 Git Commands
/git:cm - Commit (No Push)
Purpose: Stage changes and create a conventional commit without pushing
Usage:
/git:cm
What it does:
- Shows
git status --short - Reviews each file diff for secrets
- Stages files intentionally
- Generates conventional commit message
- Creates commit (no push)
When to use: When you want to commit locally before pushing
/git:cp - Commit and Push
Purpose: Complete git workflow with quality checks
Usage:
/git:cp
What it does:
- Runs
/reviewfor quality checks - Stages changes
- Creates conventional commit
- Pushes to origin
- Triggers CI workflows
When to use: When ready to publish changes
/git:pr - Create Pull Request
Purpose: Create a PR from current branch
Usage:
/git:pr # PR to main
/git:pr dev # PR to dev branch
What it does:
- Verifies quality checks passed
- Creates PR using template
- Adds appropriate labels
- Shares PR link
When to use: After pushing changes and ready for review
🔒 Quality Commands
/review - Local Quality Gate
Purpose: Run all quality checks before pushing
Usage:
/review
What it checks:
- ✅ YAML linting (workflows)
- ✅ GitHub workflow schema validation
- ✅ Python syntax (all skill directories)
- ✅ Markdown link validation
- ✅ Dependency security audit (optional)
When to use: Before committing/pushing changes
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 · 352 lines · 0 tokens per session scan A 778f4b834409
README is a command published in the GitHub repository alirezarezvani/claude-skills (25,247 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,825 tokens. 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 commands, from other repositories
become
Agent crystallization command. Studies a tool, role, or person and produces a portable 9-section agent that inhabits the domain - with beliefs, scar tissue, and instincts.
cycle-start
Activate a cycle and start implementing its stories.
research-verify
Verify existing research findings against independent primary sources. Upgrades confidence from 'sources agree' to 'independently verified.'.
story-continue
Resume an interrupted story from where you left off.
story-archive
Move a story from a cycle back to the backlog.
memory-list
DEPRECATED: Use Serena listmemories instead. Lists recent memories from Forgetful with optional project filtering.