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 OneWave-AI/claude-skills --skill claude-md-writergit clone --depth 1 https://github.com/OneWave-AI/claude-skillsWrote 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/onewave-ai/claude-skills/claude-md-writer)<a href="https://agentmods.dev/skills/onewave-ai/claude-skills/claude-md-writer"><img src="https://agentmods.dev/badge/skills/onewave-ai/claude-skills/claude-md-writer/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/skills/onewave-ai/claude-skills/claude-md-writer"><img src="https://agentmods.dev/badge/skills/onewave-ai/claude-skills/claude-md-writer.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 | $0.00084 | $0.00917 |
| Opus 5.5 | $0.00034 | $0.00367 |
| Sonnet 5.5 | $0.00017 | $0.00183 |
| Haiku 4.5 | $0.00008 | $0.00092 |
Grade A, and why
claude-md-writer 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 27d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md Writer
A good project instruction file is the difference between an agent that guesses at your conventions and one that matches them on the first try. A bad one is a wall of generic advice that burns context every single turn.
Core Behavior
Write instructions that are true, specific to this repo, and impossible to derive by looking around. Everything else is waste — it costs tokens on every request and teaches nothing.
Target length: under 100 lines. If it is longer, it is documentation, and documentation belongs in docs/ with a pointer from here.
What Goes In
Commands that are not obvious. The actual dev, build, test, lint, and single-test commands for this repo — including the flags people always forget.
npm run dev # port 3000, needs .env.local
npm test -- <file> # single file; the bare `npm test` runs the whole suite (6 min)
Architecture in five lines. Where the entry point is, where the data layer lives, what talks to what. Enough that an agent knows which directory to open, not a tour of every folder.
Conventions that a linter will not catch. How errors are handled, how state is managed, which utility to reuse instead of writing a new one, the naming pattern for files in each directory.
Traps. The things that have cost someone an hour: the migration that must run before tests, the generated file that must be rebuilt after editing the source, the service that only works behind the VPN, the directory that looks dead but is imported dynamically.
Hard rules. The non-negotiables, stated as rules: never commit to main, never edit the generated index by hand, never add a dependency without asking, never use the deprecated client.
What Stays Out
- Generic programming advice. "Write clean code", "add tests", "handle errors" — every agent already does this, and saying it adds nothing but tokens.
- Anything the agent can read in seconds: the dependency list, the folder tree, what the framework is.
- Aspirations. Document what the repo does today, not what the refactor will make true. A file that describes a codebase that does not exist actively misleads.
- Long code samples. Point at the exemplary file instead: "follow the pattern in
src/lib/billing.ts".
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.
- 27d ago First seen · 78 lines · 84 tokens per session scan A 8c301424f3cb
claude-md-writer is a skill published in the GitHub repository OneWave-AI/claude-skills (349 stars, last pushed 15d ago), licensed MIT. It adds 84 tokens to every session and 917 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-20.
Other skills, from other repositories
stakeholder-communication
Communicate effectively with stakeholders across functions and seniority levels. Use this skill when writing status updates, preparing executive reviews, sharing technical decisions with non-technical audiences, managing up, communicating bad news, or designing the communication cadence for a project. Triggers on…
analytics-strategy
Design measurement frameworks including event taxonomy, KPI hierarchy, dashboard architecture, attribution models, and analytics implementation strategy. Use this skill whenever the user wants to plan analytics, design dashboards, build event taxonomies, define KPIs, set up tracking, or audit existing measurement.…
content-strategy
Develop a content strategy covering editorial positioning, content pillars, formats, calendar, governance, and topical authority planning. Use this skill whenever the user wants to plan a content program, define content pillars, build an editorial calendar, structure topic clusters, set up content governance, or align…
incident-response
Manage active production incidents through detection, triage, mitigation, communication, and resolution with structured roles and decision-making. Use this skill whenever the user has an active incident, a production issue, a service outage, a security incident, or needs to plan incident response procedures. Triggers…
agb-begriff-vorformuliert-305
Für AGB Begriff Vorformuliert 305: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route: agb-begriff-vorformuliert-305.
agb-rechtswahl-schweizer-recht-rom-i
Für AGB Rechtswahl Schweizer Recht Rom I: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route: agb-rechtswahl-schweizer-recht-rom-i.