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 instructions/7xmohamed/kata/claude-mdgit clone --depth 1 https://github.com/7xmohamed/KataWrote 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/7xmohamed/kata/claude-md)<a href="https://agentmods.dev/instructions/7xmohamed/kata/claude-md"><img src="https://agentmods.dev/badge/instructions/7xmohamed/kata/claude-md.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 5.1 | $0.00944 | $0.00944 |
| Opus 5 | $0.00472 | $0.00472 |
| Sonnet 5 | $0.00189 | $0.00189 |
| Haiku 4.5 | $0.00094 | $0.00094 |
Grade A, and why
Kata CLAUDE.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 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
1 near-identical copy found in the catalogue:
- Kata GEMINI.md — 98% identical, 12 lines differ
How it starts
The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Kata 1.1 ⚔️
Personal skill collection for Claude Code. Eight skills covering the complete engineering workflow: think, design, check, hunt, write, learn, read, health. Now with advanced Architecture, Security, and Synthesis modes.
Structure
skills/
├── RESOLVER.md -- central trigger → skill routing table
├── check/ -- code review before merging
│ ├── agents/ -- reviewer-security.md, reviewer-architecture.md
│ └── references/ -- persona-catalog.md
├── design/ -- production-grade frontend UI
├── health/ -- Claude Code config audit
│ └── agents/ -- inspector-context.md, inspector-control.md
├── hunt/ -- systematic debugging
├── learn/ -- research to published output
├── read/ -- fetch URL or PDF as Markdown
├── think/ -- design and validate before building
└── write/ -- natural prose in English
└── references/ -- write-en.md
.claude-plugin/
marketplace.json -- plugin registry for claude plugin distribution
Each skill has a SKILL.md (loaded on demand by Claude). Supporting content lives in subdirectories. skills/RESOLVER.md is the human-readable index of "which trigger goes to which skill"; keep it in sync when you change a skill's scope.
Skill vs Script: Latent vs Deterministic
Before adding a new capability, decide which layer it belongs in. Kata's eight skills are all fat skills (Markdown carrying judgment). Anything that is pure verification, lookup, or table-driven enforcement belongs in scripts/ or rules/, not in a SKILL.md.
| Question | YES → | NO → |
|---|---|---|
| Does the user need the model to think, adapt, or ask? | Skill | Script / rule |
| Does the same input always produce the same output? | Script / rule | Skill |
| Does it depend on the user's project environment? | Skill | Script / rule |
| Is it a lookup, list, or status check? | Script / rule | Probably skill |
| Does behavior shift with conversation context? | Skill | Script / rule |
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 · 86 lines · 944 tokens per session scan A c512b409352b
Kata CLAUDE.md is an instructions file published in the GitHub repository 7xmohamed/Kata (2 stars, last pushed 2mo ago), licensed MIT. It adds 944 tokens to every session, about $0.0047 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
agman CLAUDE.md
Instructions for memandip/agman, covering claude.md — agman, what this project is, architecture — what you're editing, hard constraints (do not break these) and branch & pr workflow (required).
cli AGENTS.md
AGENTS.md instructions for awf-project/cli, covering claude.md, mcp integrations, serena mcp — symbolic code analysis & memory, claude-mem mcp — cross-session semantic memory and grepai mcp — semantic code search & call graph.
TaskWing CLAUDE.md
Claude Code instructions for josephgoksu/TaskWing, covering claude.md, cli binaries, project identity, how ai tools talk to taskwing (no mcp) and build & test commands.
TaskWing GEMINI.md
Gemini CLI instructions for josephgoksu/TaskWing, covering taskwing context for gemini, project overview, tech stack, architecture and core layers (internal/).
TaskWing AGENTS.md
AGENTS.md instructions for josephgoksu/TaskWing, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.
ccNexus AGENTS.md
AGENTS.md instructions for jackychanisnotme/ccNexus, covering agents.md, 项目概述, 当前产品阶段与最高优先级, 存量客户兼容性规则 and 未来服务器运营功能设计边界.