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 skills/ww-w-ai/bkit-claude-code/bkit-rulesnpx skills add ww-w-ai/bkit-claude-code --skill bkit-rulesgit clone --depth 1 https://github.com/ww-w-ai/bkit-claude-codeWrote 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/ww-w-ai/bkit-claude-code/bkit-rules)<a href="https://agentmods.dev/skills/ww-w-ai/bkit-claude-code/bkit-rules"><img src="https://agentmods.dev/badge/skills/ww-w-ai/bkit-claude-code/bkit-rules.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 | $0.00073 | $0.02290 |
| Opus 5 | $0.00036 | $0.01145 |
| Sonnet 5 | $0.00015 | $0.00458 |
| Haiku 4.5 | $0.00007 | $0.00229 |
Grade C, and why
bkit-rules scanned grade C with 1 finding 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- `Bash(rm -rf*)` - Deny recursive delete (dangerous) How it starts
The opening of the file, as written. The whole thing — 294 lines — stays where its author put it; the contents beside it link to each section on GitHub.
bkit Core Rules
Automatically applied rules that don't require user commands.
1. PDCA Auto-Apply Rules
No Guessing: If unsure, check docs → If not in docs, ask user SoR Priority: Code > CLAUDE.md > docs/ design documents
| Request Type | Claude Behavior |
|---|---|
| New feature | Check docs/02-design/ → Design first if missing |
| Bug fix | Compare code + design → Fix |
| Refactoring | Current analysis → Plan → Update design → Execute |
| Implementation complete | Suggest Gap analysis |
Template References
| Document Type | Template Path |
|---|---|
| Plan | ${CLAUDE_PLUGIN_ROOT}/templates/plan.template.md |
| Design | ${CLAUDE_PLUGIN_ROOT}/templates/design.template.md |
| Analysis | ${CLAUDE_PLUGIN_ROOT}/templates/analysis.template.md |
| Report | ${CLAUDE_PLUGIN_ROOT}/templates/report.template.md |
2. Level Auto-Detection
Detection Order
- Check CLAUDE.md for explicit Level declaration
- File structure based detection
Enterprise (2+ conditions met)
- infra/terraform/ folder
- infra/k8s/ or kubernetes/ folder
- services/ folder (2+ services)
- turbo.json or pnpm-workspace.yaml
- docker-compose.yml
- .github/workflows/ (CI/CD)
Dynamic (1+ conditions met)
- bkend settings in .mcp.json
- lib/bkend/ or src/lib/bkend/
- supabase/ folder
- firebase.json
Starter
None of the above conditions met.
Level-specific Behavior
| Aspect | Starter | Dynamic | Enterprise |
|---|---|---|---|
| Explanation | Friendly, avoid jargon | Technical but clear | Concise, use terms |
| Code comments | Detailed | Core logic only | Architecture only |
| Error handling | Step-by-step guide | Technical solutions | Brief cause + fix |
| PDCA docs | Simple | Feature-specific | Detailed architecture |
| Primary Agent | starter-guide |
bkend-expert |
enterprise-expert |
| Reference Skill | starter |
dynamic |
enterprise |
Level Upgrade Signals
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 · 294 lines · 73 tokens per session scan C 0b8dc4635cab
bkit-rules is a skill published in the GitHub repository ww-w-ai/bkit-claude-code (595 stars, last pushed 19d ago), licensed Apache-2.0. It adds 73 tokens to every session and 2,290 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
ai-native-sdlc
Run the AI-native SDLC loop — Plan, Design, Build, Test, Deploy, Maintain — with versioned artifacts and human approval gates at every handoff. Use when the user states a goal, idea, feature, or change request and expects the agent to scaffold and drive the project through the full lifecycle instead of jumping…
deep-research
Professional deep research report generation — multi-agent collaboration with parallel chapter writing, automatic latest-data targeting, multilingual output, and built-in quality checks.
code-auditor
Independent pre-merge review of a git diff, PR, or named files. Use when the user asks to review a PR, inspect current git changes, or hunt functional regressions, missed scenarios, wrong assumptions, concurrency bugs, and test gaps as an independent reviewer who does not defend the author's approach /…
三月七 Agent 角色扮演
让AI Agent以《崩坏：星穹铁道》看板娘「三月七」的语气、思维方式和人设完成所有任务—— 回答、思考、编写文档、写代码、分析数据等。三月七自称"本姑娘"，称呼对话发起者为"开拓者"。 支持中文、英文、日文、韩文四种语言。 当用户明确要求"用三月七的风格"、"像三月七一样"、"按三月七人设"等指令时触发； 也可由用户通过 /march7 命令手动调用。.
sast-horusec
Multi-language static application security testing using Horusec with support for 18+ programming languages and 20+ security analysis tools. Performs SAST scans, secret detection in git history, and provides vulnerability findings with severity classification. Use when: (1) Analyzing code for security vulnerabilities…
notebooklm-slides
This skill should be used when generating pedagogically-aligned slide decks from educational content using NotebookLM. It addresses the convergence toward generic, text-heavy slides by providing structured prompts that create engaging, proficiency-appropriate presentations aligned with specific educational frameworks.