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/drag88/claude-dev-framework/rules-generatornpx skills add drag88/claude-dev-framework --skill rules-generatorgit clone --depth 1 https://github.com/drag88/claude-dev-frameworkWhat 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 | $0.00017 | $0.00664 |
| Opus 5 | $0.00009 | $0.00332 |
| Sonnet 5 | $0.00003 | $0.00133 |
| Haiku 4.5 | $0.00002 | $0.00066 |
Grade A, and why
rules-generator 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 2d 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rules Generator Skill
Auto-generate .claude/rules/ documentation for any codebase.
When to Activate
- No
.claude/rules/directory exists in the current project - User asks about codebase structure or architecture
- User asks "what does this project do"
- Starting work on an unfamiliar codebase
- User explicitly asks to generate rules
Actions
-
Load rulebook: Read
rules-templates/claudemd-rulebook.md(vendored into CDF) as the authoritative reference for rule framing (positive imperatives, explicit scope, why-statements, neutral tone). Falls back to the embedded principles in this file only if the rulebook is missing. -
Explore codebase using the Explore agent to understand:
- Directory structure and key files
- Tech stack (languages, frameworks, libraries)
- Architectural patterns and conventions
- Build/test/run commands
-
Generate
.claude/rules/files with YAML frontmatter on every file:architecture.md— Directory structure, key files, component relationships, data flow. Frontmatter:description:only (loads broadly).tech-stack.md— Languages, frameworks, libraries with purposes. Frontmatter:description:only.patterns.md— Architectural patterns, code conventions, error handling. Frontmatter:description:+paths:scoped to source dirs (e.g.["src/**", "lib/**"]).commands.md— Setup, build, test, lint, run commands. Frontmatter:description:only.- Project-type files (
api-conventions.md,component-conventions.md, etc.) — Always includepaths:scoped to the relevant directory glob so they only load when matching files are touched.
-
Frame rules as positive imperatives, with explicit scope and the why where non-obvious. Example: "Apply to every API route, including admin routes. Reason: centralized auth check." Avoid CAPS, MUST, CRITICAL, "ANY", "ALWAYS".
-
Confirm completion with a summary listing each generated file, its line count, and whether it is path-scoped or always-loaded.
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.
- 2d ago First seen · 60 lines · 17 tokens per session scan A e8b50ac234d4
rules-generator is a skill published in the GitHub repository drag88/claude-dev-framework (2 stars, last pushed 1mo ago), licensed MIT. It adds 17 tokens to every session and 664 once invoked, about $0.0001 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.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.