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 Tasachii/Tasachii-Tools --skill craft-readmegit clone --depth 1 https://github.com/Tasachii/Tasachii-ToolsWrote 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/tasachii/tasachii-tools/craft-readme)<a href="https://agentmods.dev/skills/tasachii/tasachii-tools/craft-readme"><img src="https://agentmods.dev/badge/skills/tasachii/tasachii-tools/craft-readme/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/tasachii/tasachii-tools/craft-readme"><img src="https://agentmods.dev/badge/skills/tasachii/tasachii-tools/craft-readme.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 | $0.00313 | $0.03086 |
| Opus 5 | $0.00156 | $0.01543 |
| Sonnet 5 | $0.00063 | $0.00617 |
| Haiku 4.5 | $0.00031 | $0.00309 |
Grade A, and why
craft-readme 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 10d 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 — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
craft-readme
Writes project READMEs in a calm, precise, understated house style. English prose, fact-only, table-heavy, with native UI strings preserved exactly as the app shows them.
Top rule — never invent facts
Do not write test counts, bundle sizes, feature lists, version numbers, commands, or URLs that have not been verified. Three options, in order:
- Read the real source —
package.json, lockfiles, config,src/,docs/. - Ask the user when a fact cannot be read.
- Leave a TODO —
<!-- TODO: verify test count -->— when neither is possible.
A marked TODO is always correct; a confident guess is a defect. Vague claims ("fast", "lots of tests", "blazingly") are banned — concrete numbers only.
Workflow
1 — Choose the archetype and audience
The house style is one voice, but the shape changes with what you are documenting. Pick the closest archetype first and read its exemplar — that is the structure to follow:
| Archetype | Exemplar | What leads | What matters most |
|---|---|---|---|
| End-user app (GUI/PWA/mobile, has a live demo or screenshots) | references/example-tododesu.md |
Lead paragraph → Try it now → screenshots | Features grouped by area, the experience |
| Library / package (imported by other code) | references/example-library.md |
Quickstart (install + 5-line usage) | API table, compatibility, zero-config use |
| Public OSS project (accepts contributions) | references/example-oss-library.md |
Quickstart + a Contents TOC | Badges, API, Contributing/Security/Conduct sibling files |
| Backend service / API (deployed, not imported) | references/example-service.md |
Quickstart (run it: docker compose up) |
Env-var + endpoint tables, deploy, health |
| CLI tool | example-tododesu.md (its CLI section) |
Quickstart (install + first command) | Command reference block, flags |
If the project mixes archetypes (e.g. an app and a CLI, like TodoDesu), follow the dominant one and borrow sections from the others.
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 196 lines · 313 tokens per session scan A 92e17f0ca366
craft-readme is a skill published in the GitHub repository Tasachii/Tasachii-Tools (2 stars, last pushed 1mo ago), licensed MIT. It adds 313 tokens to every session and 3,086 once invoked, about $0.0016 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…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…