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/claudemd-generatornpx skills add drag88/claude-dev-framework --skill claudemd-generatorgit clone --depth 1 https://github.com/drag88/claude-dev-frameworkWrote 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/drag88/claude-dev-framework/claudemd-generator)<a href="https://agentmods.dev/skills/drag88/claude-dev-framework/claudemd-generator"><img src="https://agentmods.dev/badge/skills/drag88/claude-dev-framework/claudemd-generator.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 | $0.00022 | $0.01457 |
| Opus 5 | $0.00011 | $0.00728 |
| Sonnet 5 | $0.00004 | $0.00291 |
| Haiku 4.5 | $0.00002 | $0.00146 |
Grade A, and why
claudemd-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 4d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md Generator Skill
Auto-generate CLAUDE.generated.md from project rules.
When to Activate
.claude/rules/exists but noCLAUDE.mdorCLAUDE.generated.mdin project root- User asks "generate claude.md" or similar
- User asks "create project documentation"
- After
/cdf:rules generatecompletes (auto-chain)
What It Does
Executes the /cdf:rules claudemd behavioral flow. The command definition in commands/rules.md is the single source of truth for:
- What gets extracted from which rule files
- The output template and structure
- Line budget and guidelines
Design Principles (current-Claude-aligned, from the vendored rulebook + Anthropic docs)
- Every line must pass: "Would removing this cause Claude to make mistakes?" If not, cut it.
- Target 80-180 lines — under 200 is the documented sweet spot. First 200 lines get prioritized by Claude.
- Progressive disclosure — CLAUDE.md has essentials;
.claude/rules/has details. Workflow content lives inworkflow.md, not duplicated in root. - No duplication — if content lives in
.claude/rules/(auto-loaded), do not repeat it. Conflicts between files cause the model to pick one arbitrarily. - Concrete and verifiable — "Run
npm testand paste the output" beats "test your changes." Vague checks get silently skipped. - No code style — let linters handle formatting.
- Open with a Role sentence — One sentence anchoring tone and scope ("You are a senior X engineer working on Y...").
- No tool/subagent authorization boilerplate — current models parallelize and dispatch subagents natively. Do not emit
<use_parallel_tool_calls>blocks or a "Tool and subagent policy" section; deleting such blocks is the upgrade. - Spend the tokens on gotchas — invariants, traps, incident-derived knowledge, each with the why. Never restate what
lsor package.json shows. - Frame rules as positive imperatives — "Use X" beats "Never Y." Prohibitions waste tokens and invite pattern-matching.
- State scope explicitly on non-obvious rules — "Apply to every component, including third-party wrappers" beats "apply to components."
- Tone down forceful language — Avoid CAPS, MUST, CRITICAL, "ANY", "ALWAYS". Forceful negatives cause overcompliance and hostile reading. Reserve absolutes for security/secrets/irreversible operations.
- Provide the why behind non-obvious constraints — models generalize correctly from explained constraints.
- Use
@importsfor top-level docs (@README.md) rather than restating them.
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.
- 4d ago First seen · 80 lines · 22 tokens per session scan A 0bd873f7ae7a
claudemd-generator is a skill published in the GitHub repository drag88/claude-dev-framework (2 stars, last pushed 1mo ago), licensed MIT. It adds 22 tokens to every session and 1,457 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.
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…