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 skills add vahidkaargar/it-department-skills --skill skills-discoverygit clone --depth 1 https://github.com/vahidkaargar/it-department-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/skills/vahidkaargar/it-department-skills/skills-discovery)<a href="https://agentmods.dev/skills/vahidkaargar/it-department-skills/skills-discovery"><img src="https://agentmods.dev/badge/skills/vahidkaargar/it-department-skills/skills-discovery/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/vahidkaargar/it-department-skills/skills-discovery"><img src="https://agentmods.dev/badge/skills/vahidkaargar/it-department-skills/skills-discovery.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00110 | $0.00974 |
| Opus 5 | $0.00055 | $0.00487 |
| Sonnet 5 | $0.00022 | $0.00195 |
| Haiku 4.5 | $0.00011 | $0.00097 |
Grade A, and why
skills-discovery 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 12d 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skills discovery — source of truth
Enforced when the opt-in guard hook is installed (see repo docs/hooks.md;
treat search-first as mandatory even without it). The hook
~/.claude/hooks/skills-discovery-guard.py runs on every
Bash call (PreToolUse) and denies (exit 2) raw enumeration of skill directories —
ls/find/tree against ~/.claude/skills, ~/.agents, ~/.cursor/skills,
~/.skills-archive, plugin caches, or bulk find -name SKILL.md / glob-cat of many
SKILL.md files. skillfind/rulesfind/build-index.py/skillserve.py are
allow-listed by name so the catalog's own tooling still works. This is the STRICT §3
rule (~/.ai/rules.md, propagates into AGENT_RULES.md + CLAUDE.md) — every agent
on this machine must comply, not just Claude Code.
Skills may live across many roots on this machine. NEVER enumerate them into context. Search first, read ONE SKILL.md.
Find a skill (any agent with shell access)
skillfind "<intent>" # ranked top-5, e.g. skillfind "nginx reload"
skillfind "<intent>" --json # machine-readable (name, path, score, category)
skillfind --get <name> # one skill: path + triggers
skillfind --category <slug> # browse one category
rulesfind "<topic>" # rules (.md/.mdc); --always = per-session token cost
Then: Read the single SKILL.md path returned. Follow it. Done.
- Hot set pre-listed (~1k tokens):
~/.agents/skills-catalog/CATALOG.md - Machine index:
~/.agents/skills-catalog/index.json(query via--json, don't load whole) - Archived skills searchable too; restore:
mv ~/.skills-archive/<name> ~/.claude/skills/<name>
HTTP API (optional, agents with no shell)
If skillserve.py is running (see repo docs for setup), on
http://127.0.0.1:3401 (bind localhost only):
/search?q=<intent>&n=5 · /get?name=<skill> (returns full SKILL.md body) ·
/catalog · /rules?q= · /rules?always=1 · /health.
No shell, no HTTP? (last fallback)
Read ~/.agents/skills-catalog/CATALOG.md (hot set), or grep
~/.agents/skills-catalog/index.json for keywords. Never walk skill dirs.
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.
- 12d ago First seen · 64 lines · 110 tokens per session scan A 14a95ac9bf6b
skills-discovery is a skill published in the GitHub repository vahidkaargar/it-department-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 110 tokens to every session and 974 once invoked, about $0.0006 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
test-driven-development
Drives development with tests using the red-green-refactor loop. Use when implementing any logic, fixing any bug, or changing any behavior. Use when you need to prove that code works, when a bug report arrives, or when you're about to modify existing functionality.
documentation-and-adrs
Records decisions and documentation. Use when you need to document an architecture decision (ADR) or the reasoning behind a design choice, when changing public APIs, shipping features, or when you need to record context that future engineers and agents will need to understand the codebase.
idea-refine
Refines raw ideas into sharp, actionable concepts through structured divergent and convergent thinking. Use when an idea is still vague, when you need to stress-test assumptions before committing to a plan, or when you want to expand options before converging on one. Triggers on "ideate", "refine this idea", or…
chinese-git-workflow
A reference for configuring Git with Chinese code-hosting services such as Gitee, Coding.net, GitLab China, and CNB, including SSH, HTTPS, credentials, CI, and repository mirroring.
skillshare-implement-feature
Implement a feature from a spec file or description using TDD workflow. Use this skill whenever the user asks to: add a new CLI command, implement a feature from a spec, build new functionality, add a flag, create a new internal package, or write Go code for skillshare. This skill enforces test-first development…
create-slack-app
Use when a developer wants to create, scaffold, or bootstrap a new Slack app or agent from scratch with the Slack CLI. Covers prerequisites, authentication, choosing a workspace to install into, and creating + running a project from a Bolt (JS or Python) template locally. Trigger on "create a Slack app", "new Bolt…