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 skills add atman-33/workhub --skill create-claude-mdgit clone --depth 1 https://github.com/atman-33/workhubWrote 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/atman-33/workhub/create-claude-md)<a href="https://agentmods.dev/skills/atman-33/workhub/create-claude-md"><img src="https://agentmods.dev/badge/skills/atman-33/workhub/create-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 | $0.00047 | $0.00916 |
| Opus 5 | $0.00023 | $0.00458 |
| Sonnet 5 | $0.00009 | $0.00183 |
| Haiku 4.5 | $0.00005 | $0.00092 |
Grade A, and why
create-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 7d 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analyze the current project and write an effective CLAUDE.md — either creating one from scratch or refining an existing one — following official Claude Code guidelines and the principle that shorter is better.
Steps
-
Check for existing CLAUDE.md at the project root. If one exists, read it first.
-
Inspect project files to detect build system, test runner, lint/format setup, and conventions:
package.json,pyproject.toml,Cargo.toml,Makefile,*.sln,go.mod.eslintrc*,.prettierrc*,biome.json,ruff.tomlREADME.md,docs/directory,.github/for PR/branch conventionsgit log --oneline -10to detect commit message conventionsgit remote -vto identify the repository
-
Apply the placement decision for each rule you find:
- Project-wide rules →
CLAUDE.md - Domain-specific or file-type-specific rules (e.g., "React component rules", "SQL migration rules") →
.claude/rules/<domain>.mdwithpaths:frontmatter - Automated/enforcement behaviors (auto-format on save, lint fixing) → do NOT put in CLAUDE.md; note them as candidates for
settings.jsonPostToolUse hooks
- Project-wide rules →
-
Apply the include/exclude filter before writing each line:
✅ Include:
- Bash commands Claude cannot guess (build, test, deploy, migrate, seed)
- Code style rules that differ from language/framework defaults
- Testing instructions and preferred test runners
- Branch naming, PR conventions, commit message format
- Required env vars or non-obvious setup steps
- Common gotchas or non-obvious behaviors
- Critical invariants (wrap in
<important>tags)
❌ Exclude:
- Anything Claude can infer by reading the code
- Standard language conventions Claude already knows
- Detailed API documentation (link to docs instead)
- File-by-file descriptions of the codebase
- Self-evident practices like "write clean code"
- Automated behaviors (formatting, linting) — suggest
settings.jsonhooks instead
-
Write
CLAUDE.mdto the project root using this structure (omit empty sections):# <Project Name> <1-2 sentence description of what the project is> # Commands - install: <cmd> - dev: <cmd> - test: <cmd> - lint: <cmd> - build: <cmd> # Code Style <only rules that differ from defaults> # Workflow <branch naming, PR conventions, non-obvious steps> <important> <critical rules that must not be forgotten> </important>Keep the total file under 50 lines where possible. Never exceed 200 lines.
-
Create
.claude/rules/<domain>.mdstubs for any domain-specific rules identified. Each stub must includepaths:frontmatter:--- paths: - "src/components/**" --- # <Domain> Rules # TODO: add rules here -
Report what was written, what was excluded and why, any
.claude/rules/stubs created, and any behaviors suggested forsettings.json.
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.
- 7d ago First seen · 105 lines · 47 tokens per session scan A 0bc8d2ae2179
create-claude-md is a skill published in the GitHub repository atman-33/workhub (2 stars, last pushed 2d ago), licensed MIT. It adds 47 tokens to every session and 916 once invoked, about $0.0002 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
gonavi-cli
Operate databases through the GoNavi headless CLI — the gonavi executable shipped in verified GitHub Release archives. Covers listing/adding/importing saved connections, running SQL queries against saved connections or ad-hoc connection files, exporting result sets to csv/json/md/html/xlsx, batch-executing SQL files…
xiaohongshu-image-creator
An image-making assistant for Xiaohongshu, a Chinese social platform for lifestyle, product, and educational posts. It creates vertical covers and supporting images matched to the post’s topic, audience, and visual style.
design
Create a doc-as-code design package from a PRD or SPEC. Conditionally generates C4 diagrams (Context/Container/Component), sequence diagrams, ER diagram + Data Dictionary, OpenAPI 3.0, AsyncAPI 3.0, ADRs, domain glossary, state diagrams, and deployment view as Mermaid-rendered Markdown files. Use when PM mentions…
shipyard-handoff
Captures session context into .shipyard/HANDOFF.md so the next session can resume without losing progress.
curator-practice
Operating philosophy for autonomous memex curator tending — orientation protocol, signal triage, bounded work units, initiative thresholds, logging conventions. Trigger on cron-launched runs with no user prompt, "use your judgment", "tend without instructions", "do a pass on the vault", "I'll be away — do what needs…
trellis-spec-bootstrap
Bootstrap project-specific Trellis coding specs with a platform-neutral single-agent workflow. Use when creating or refreshing .trellis/spec guidelines, analyzing a codebase with GitNexus, ABCoder, or source inspection, decomposing package/layer spec work, and writing real codebase-backed spec docs without placeholder…