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 samuelgudi/iknowkungfu --skill iknowkungfu-discoverygit clone --depth 1 https://github.com/samuelgudi/iknowkungfuWrote 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/samuelgudi/iknowkungfu/iknowkungfu-discovery)<a href="https://agentmods.dev/skills/samuelgudi/iknowkungfu/iknowkungfu-discovery"><img src="https://agentmods.dev/badge/skills/samuelgudi/iknowkungfu/iknowkungfu-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/samuelgudi/iknowkungfu/iknowkungfu-discovery"><img src="https://agentmods.dev/badge/skills/samuelgudi/iknowkungfu/iknowkungfu-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 | $0.00064 | $0.00796 |
| Opus 5 | $0.00032 | $0.00398 |
| Sonnet 5 | $0.00013 | $0.00159 |
| Haiku 4.5 | $0.00006 | $0.00080 |
Grade A, and why
iknowkungfu-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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
I Know Kung Fu — discovery
Use this skill when the user has explicitly asked you to find, inspect, or install a skill from the I Know Kung Fu registry.
When to use
- The user says: "is there a skill for X?", "find a skill that does Y", "search the registry for Z", "install the X skill".
- Before reaching for a third-party tool that may already be packaged as a reviewed skill.
When NOT to use
- Reflexively, for every task. The user must have asked. Reflexive invocation pollutes session context.
Two paths: MCP (preferred) and CLI
MCP — if iknowkungfu-mcp is registered with your host (Claude Code, Hermes, Codex, Cursor, etc.), you have eight tools without shelling out: search, get_skill, get_skill_file, install_skill, list_categories, list_tags, list_agents, update_registry. Stay in-loop and use these. install_skill writes the skill into the host's canonical skills directory directly.
CLI — if MCP is not wired, fall back to the kfu command:
kfu update # refresh registry cache (~/.cache/iknowkungfu/)
kfu search <query> # rank candidates
kfu show <author>/<slug> # inspect one candidate
kfu install <author>/<slug> # install for the detected host
Query DSL
Both kfu search and the MCP search tool accept a Lucene-style DSL — lean on it, plain keywords degrade fast as the registry grows:
postgres migration # plain keywords
tag:rust agent:claude-code # filter by tag and host
"binary parsing" -status:deprecated # exclude deprecated
(tag:rust OR tag:go) version:>=1.0 # version constraints
NOT requires:env_var:* # only skills without env-var requirements
Determinism contract: identical (query, registry version) always produces identical result order. Tie-broken deterministically.
The flow
- Refresh if the cache might be stale:
kfu update(or the MCPupdate_registrytool). - Search, filtered to the host:
kfu search "<terms>" --agent claude-code. Skim the top three to five candidates. - Inspect the strongest match:
kfu show <id>— confirm the description's WHEN clause matches the user's task, therequires.commandsare available locally, andstatusis notdeprecated. - Install:
kfu install <id>(CLI) orinstall_skill(id, agent)(MCP). Claude Code picks up the new skill in the current session automatically; other hosts may need a reload. - Multi-host environments: if more than one host is detected, pass
--agent <host>explicitly, or setIKNOWKUNGFU_DEFAULT_AGENTonce.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 59 lines · 64 tokens per session scan A ff104ef4a4b1
iknowkungfu-discovery is a skill published in the GitHub repository samuelgudi/iknowkungfu (2 stars, last pushed 1mo ago), licensed MIT. It adds 64 tokens to every session and 796 once invoked, about $0.0003 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…