claude-skills is a large collection of reusable skills, commands, plugins, and supporting resources for coding agents across engineering, business, research, compliance, and productivity work. It is used by people who want agents such as Claude Code, Codex, Gemini CLI, or Cursor to follow specialized workflows. The catalogue contains selected skills and settings from the collection.
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/update-docsgit clone --depth 1 https://github.com/alirezarezvani/claude-skillsWrote 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/commands/alirezarezvani/claude-skills/update-docs)<a href="https://agentmods.dev/commands/alirezarezvani/claude-skills/update-docs"><img src="https://agentmods.dev/badge/commands/alirezarezvani/claude-skills/update-docs.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00007 | $0.01761 |
| Opus 5 | $0.00003 | $0.00881 |
| Sonnet 5 | $0.00001 | $0.00352 |
| Haiku 4.5 | $0.00001 | $0.00176 |
Grade A, and why
update-docs 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 5d 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.
Copies of this mod
2 near-identical copies found in the catalogue:
- update-docs — 100% identical, 0 lines differ
- update-docs — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.
After completing any skill creation, agent creation, or command creation in this repository, run the full post-creation sync pipeline below. Execute every step — never skip a task. If something is unclear or a step fails, ask the user for guidance before continuing.
Step 1: Inventory what changed
Scan the working tree to identify what was added, modified, or deleted:
git status --short
Classify each change:
- New skill — a new folder containing
SKILL.mdunder a domain directory - New agent — a new
.mdfile underagents/ - New command — a new
.mdfile undercommands/ - Modified skill/agent/command — updated existing files
- Deleted skill/agent/command — removed files
Report the inventory to the user before proceeding.
Step 2: Cross-platform CLI sync
Ensure all platforms have compatible versions of every skill, agent, and command.
2a. Codex CLI
Run the Codex sync script to regenerate symlinks and the skills index:
python3 scripts/sync-codex-skills.py --verbose
Verify the output: check .codex/skills-index.json for correct total_skills count and that new skills appear in the index.
2b. Gemini CLI
Run the Gemini sync script:
python3 scripts/sync-gemini-skills.py --verbose
Verify: check .gemini/skills-index.json for correct total count. New skills, agents, and commands should all have corresponding entries and symlinks under .gemini/skills/.
2c. OpenClaw
Verify that scripts/openclaw-install.sh will pick up the new skills. The install script uses the same directory structure, so no separate sync is needed — but confirm the new skill directories are not excluded by any filter in the script.
Report sync results (skill counts per platform) to the user.
Step 3: Claude Code plugin marketplace
3a. Domain-level plugin.json
For each domain that had changes, update the domain's .claude-plugin/plugin.json:
- Update
descriptionwith accurate skill/tool/reference counts - Update
versionif needed - Verify
sourcepaths are correct
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.
- 5d ago First seen · 229 lines · 7 tokens per session scan A eb557a7e4d02
update-docs is a command published in the GitHub repository alirezarezvani/claude-skills (25,477 stars, last pushed 5d ago), licensed MIT. It adds 7 tokens to every session and 1,761 once invoked, about $0.0000 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 2026-08-30.
Other commands, from other repositories
load-session
Load a synced session summary for context.
sessions
List synced sessions from GitHub.
sync-enable
Enable session sync to GitHub for cross-device continuation.
statusline
Configure which sections appear in the Claude Code statusline.
devops
Launch the DevOps specialist for CI/CD and deployment.
plan
Launch the project planning agent for strategic task decomposition.