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 endearqb/endearqb-skills --skill readme-first-buildergit clone --depth 1 https://github.com/endearqb/endearqb-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/endearqb/endearqb-skills/readme-first-builder)<a href="https://agentmods.dev/skills/endearqb/endearqb-skills/readme-first-builder"><img src="https://agentmods.dev/badge/skills/endearqb/endearqb-skills/readme-first-builder/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/endearqb/endearqb-skills/readme-first-builder"><img src="https://agentmods.dev/badge/skills/endearqb/endearqb-skills/readme-first-builder.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 | $0.00093 | $0.00623 |
| Opus 5 | $0.00046 | $0.00311 |
| Sonnet 5 | $0.00019 | $0.00125 |
| Haiku 4.5 | $0.00009 | $0.00062 |
Grade A, and why
readme-first-builder 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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
README First Builder
Purpose
Use this skill as a one-time initializer or upgrader for a project-level README First architecture. Do not use it as the default way to write every README after a project already has AGENTS.md; once initialized, the target project's own AGENTS.md becomes the operating protocol.
Canonical Source
Read references/readmefirst-source.md for the upstream repository and file roles. The canonical project is endearqb/ReadmeFirst:
README.md: principle and architecture explanation.AGENTS.md: executable agent protocol.
When network access is available, inspect the latest upstream files before initializing. If network is unavailable, explain that the initialization is based on the locally known structure and recommend a later sync.
Initialization Workflow
- Inspect the target project root and confirm whether
AGENTS.md,README.md, and.ai/already exist. - If
AGENTS.mdis missing, create it from the upstream ReadmeFirstAGENTS.mdcontent, then adapt only project-specific placeholders if necessary. - If
AGENTS.mdalready exists, merge the README First protocol into it without overwriting local rules. Keep stricter or project-specific local rules. - Ensure the root
README.mdacts as the project map: purpose, setup, commands, top-level directory responsibilities, and links to important directory READMEs. - Create
.ai/changes/and.ai/decisions/if missing. Add lightweight starter templates only when useful. - Add or update directory-level
README.mdfiles only for key long-lived directories. Do not cover generated, dependency, cache, build, log, or temporary directories. - Record the initialization in
.ai/changes/YYYY-MM-DD.md. - Verify paths and commands mentioned in the generated docs.
Existing File Rules
- Never overwrite an existing
AGENTS.mdorREADME.mdblindly. - Treat existing project rules as local authority unless they conflict with safety or the user's explicit request.
- Preserve user-authored prose and append or merge README First sections.
- If the upstream
AGENTS.mdconflicts with existing project instructions, report the conflict and choose the least destructive merge.
What ships with it
2 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.
- 11d ago First seen · 42 lines · 93 tokens per session scan A bf2387c3fd96
readme-first-builder is a skill published in the GitHub repository endearqb/endearqb-skills (19 stars, last pushed 7d ago), licensed MIT. It adds 93 tokens to every session and 623 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
taiyi-evolve
A workflow skill that compares the implemented code with the frozen design after development and testing. It records architecture changes and proposes updates to DESIGN.md, the document describing the intended system structure.
reply-to-pr-threads
Draft, confirm, and post replies to GitHub PR review threads. Handles per-category reply formatting, re-fetches thread resolution state so auto-resolved threads are skipped, and posts via GraphQL. Use when the user asks to "reply to PR threads", "post PR thread replies", or "draft PR reply messages".
answer-reviewer-questions
For each reviewer question on a PR, recall implementation reasoning and compose a raw answer. Use when the user asks to "answer reviewer questions", "draft answers to PR questions", or "explain reviewer questions".
evaluate-findings
Critically assess external feedback (code reviews, AI reviewers, PR comments) and decide which suggestions to apply using adversarial verification. Use when the user asks to "evaluate findings", "assess review comments", "triage review feedback", "evaluate review output", or "filter false positives".
create-project-skills
Scans an existing codebase and generates project-specific skills that capture inferred conventions such as naming, file organization, framework usage, data access, error handling, and testing style. Writes into the project's chosen skill directory (e.g., .claude/skills/, .agents/skills/, or a custom path). Use when…
retrospective-audit
Stage B of /prflow:retrospective-weekly: given a most-recent-first subset of one recurring pattern's occurrence-PR context bundles (bounded by auditbundlecap), re-derive the root cause and return one JSON object carrying a ranked findings array (one to three sub-patterns) — no edits, no worktree. Invoked as a subagent…