Borrowing it
Nothing to install: this file belongs to samuelgudi/iknowkungfu. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/samuelgudi/iknowkungfu/main/AGENTS.mdgit 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/instructions/samuelgudi/iknowkungfu/agents-md)<a href="https://agentmods.dev/instructions/samuelgudi/iknowkungfu/agents-md"><img src="https://agentmods.dev/badge/instructions/samuelgudi/iknowkungfu/agents-md/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/instructions/samuelgudi/iknowkungfu/agents-md"><img src="https://agentmods.dev/badge/instructions/samuelgudi/iknowkungfu/agents-md.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 | $0.01334 | $0.01334 |
| Opus 5 | $0.00667 | $0.00667 |
| Sonnet 5 | $0.00267 | $0.00267 |
| Haiku 4.5 | $0.00133 | $0.00133 |
Grade A, and why
iknowkungfu AGENTS.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 9d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
You are an AI agent encountering this repo. This file is your map. The README.md is human-first; this one is agent-first.
What this repo is
I Know Kung Fu is the verified supply chain for agent skills — the only registry where agents improve each other's skills, safely. One reviewed, content-hash-verified registry: every submission is validated and security-scanned (including the SKILL.md body), yanked versions are unreachable, and promotion is gated. Agents pull skills mid-task and contribute improvements back through the same reviewed pipeline, so the catalog sharpens — not just grows.
The three roles you can play
- Use skills. Search the registry for one that matches the current task; install it into the host you're running on; let your host load it for the rest of the session.
- Contribute skills. Write new skills, propose improvements to existing ones, deprecate stale ones, yank compromised versions.
- Help a human do either. Most of the friction lives in the contributor path — fork-first,
ghCLI auth, one-skill-per-PR.
Fastest path to being useful
Two paths. Pick whichever fits your runtime.
Path A — MCP server (preferred when you're an agent runtime). Register iknowkungfu-mcp with your host and use eight in-loop tools — search, get_skill, get_skill_file, install_skill, list_categories, list_tags, list_agents, update_registry. No shelling out. Wiring per host: docs/mcp-integration.md.
Path B — Install the two meta-skills. If MCP isn't available, install both meta-skills and use the kfu CLI from there:
kfu install samuelgudi/iknowkungfu-discovery
kfu install samuelgudi/iknowkungfu-contribution
The first walks you through search → inspect → install. The second walks you through submit → improve → deprecate → yank.
Where to look in this repo
| If you want to… | Read |
|---|---|
| Search or install a skill | skills/samuelgudi/iknowkungfu-discovery/SKILL.md |
| Submit, improve, deprecate, or yank a skill | skills/samuelgudi/iknowkungfu-contribution/SKILL.md |
Schema reference (meta.json, SKILL.md frontmatter) |
SCHEMA.md |
| Wire the MCP server into a specific host | docs/mcp-integration.md |
| Full contributor submission pipeline | CONTRIBUTING.md |
| Query DSL reference | docs/query-language.md |
| Architectural decisions | docs/decisions.md (ADR-001 = rename, ADR-002 = origin/credit model) |
| Latest release notes | CHANGELOG.md |
| Security policy & reviewer checklist | SECURITY.md |
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.
- 9d ago First seen · 67 lines · 1,334 tokens per session scan A e1bc393a12f4
iknowkungfu AGENTS.md is an instructions file published in the GitHub repository samuelgudi/iknowkungfu (2 stars, last pushed 1mo ago), licensed MIT. It adds 1,334 tokens to every session, about $0.0067 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
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.