Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add fablerlabs/claude-md-templates/plugin install claude-md-kitWrote 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/commands/fablerlabs/claude-md-templates/claude-md-new)<a href="https://agentmods.dev/commands/fablerlabs/claude-md-templates/claude-md-new"><img src="https://agentmods.dev/badge/commands/fablerlabs/claude-md-templates/claude-md-new/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/fablerlabs/claude-md-templates/claude-md-new"><img src="https://agentmods.dev/badge/commands/fablerlabs/claude-md-templates/claude-md-new.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00022 | $0.00862 |
| Opus 5 | $0.00011 | $0.00431 |
| Sonnet 5 | $0.00004 | $0.00172 |
| Haiku 4.5 | $0.00002 | $0.00086 |
Grade A, and why
claude-md-new 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 11d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create a CLAUDE.md at the root of this repository. Follow these steps exactly.
0. Guard
If a CLAUDE.md (or AGENTS.md) already exists at the repo root, do NOT overwrite it.
Tell the user it exists and suggest /claude-md-audit instead, then stop — unless they
explicitly asked for a rewrite in their arguments.
1. Learn the project — facts, not guesses
Inspect the repo before writing anything:
- Manifests:
package.json(scripts!),pyproject.toml,Cargo.toml,go.mod,Makefile,justfile,Taskfile.yml,docker-compose.yml, CI workflows in.github/workflows/(CI is the ground truth for how the project is really built and tested). - Layout: top two levels of the tree; where source, tests, and config live.
- Tooling signals: lockfiles (pnpm/yarn/npm/uv/poetry/cargo), formatter/linter
configs,
.env.example, database migrations. - README: setup steps worth preserving.
Every command you put in the CLAUDE.md must be one you found in a manifest, CI file, or README — never invented. If you cannot find a test or run command, say so in the file ("no test runner configured") rather than guessing one.
2. Pick the template
Read ${CLAUDE_PLUGIN_ROOT}/CLAUDE.starter.md for the structure. Then read the ONE
bundled example closest to this project and use it as the register/altitude reference:
- Next.js / TypeScript web app →
${CLAUDE_PLUGIN_ROOT}/examples/CLAUDE.nextjs-saas.md - Python CLI / library →
${CLAUDE_PLUGIN_ROOT}/examples/CLAUDE.python-cli.md - Rust service →
${CLAUDE_PLUGIN_ROOT}/examples/CLAUDE.rust-service.md - Unattended/autonomous agent →
${CLAUDE_PLUGIN_ROOT}/examples/CLAUDE.autonomous-agent.md - Anything else → starter only, adapt the section headings to what the repo needs.
3. Write CLAUDE.md
Rules (from ${CLAUDE_PLUGIN_ROOT}/FIELD-GUIDE.md — read it if unsure):
- A map, not wishes. "Business logic lives in
src/domain/; runpnpm test <file>for one test" — never "write clean code". - Terse, imperative bullets. An agent reads this every session; a human reads it once.
- Include: how to run / test / lint / build (exact commands), the 3–8 non-obvious conventions of THIS repo, what not to touch, and a verification habit ("changes to product code must be exercised, not just typechecked").
- Exclude: anything derivable by reading the code, generic best practices, wish-list adjectives, and anything you could not verify in step 1.
- Target 30–80 lines. Shorter is better than padded.
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.
- 11d ago First seen · 69 lines · 22 tokens per session scan A 4073c3bdeae6
claude-md-new is a command published in the GitHub repository fablerlabs/claude-md-templates (2 stars, last pushed 1mo ago), licensed MIT. It adds 22 tokens to every session and 862 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 commands, from other repositories
sdd-apply
Implement SDD tasks — writes code following specs and design.
sdd-explore
Explore and investigate an idea or feature — reads codebase and compares approaches.
sdd-init
Initialize SDD context — detects project stack and bootstraps persistence backend.
gentle-sdd-ff
Fast-forward all SDD planning phases — proposal through tasks.
ijfw-audit
Run the IJFW audit gate for the current workflow phase. Usage: /ijfw-audit [phase name].
ijfw-execute
Jump directly to the IJFW workflow Execute phase (Deep D4 / Quick Q3). Usage: /ijfw-execute [task or phase name].