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 Team-Deepiri/deepiri-axiom --skill read-the-damn-docsgit clone --depth 1 https://github.com/Team-Deepiri/deepiri-axiomWrote 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/team-deepiri/deepiri-axiom/read-the-damn-docs)<a href="https://agentmods.dev/skills/team-deepiri/deepiri-axiom/read-the-damn-docs"><img src="https://agentmods.dev/badge/skills/team-deepiri/deepiri-axiom/read-the-damn-docs/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/team-deepiri/deepiri-axiom/read-the-damn-docs"><img src="https://agentmods.dev/badge/skills/team-deepiri/deepiri-axiom/read-the-damn-docs.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 | $0.00062 | $0.00599 |
| Opus 5.5 | $0.00025 | $0.00240 |
| Sonnet 5.5 | $0.00012 | $0.00120 |
| Haiku 4.5 | $0.00006 | $0.00060 |
Grade A, and why
read-the-damn-docs 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Read the damn docs
Do not guess when authoritative docs can answer. Search, open, and read current official docs before coding.
Source: BuilderIO/skills (read-the-damn-docs). MIT.
Docs-first triggers
- User asks for latest / current / official / recommended / look it up
- Needed docs are not already in the repo or supplied
- Adding, upgrading, configuring, or importing a package/SDK/CLI/provider
- Fast-moving surfaces (AI SDKs, React/Next, Stripe, GitHub, auth, cloud)
- Auth, secrets, webhooks, billing, PII, migrations, rate limits, compliance
- Errors mentioning deprecation, unknown options, version mismatch
- Local ADRs, OpenAPI, schemas, or package READMEs define the contract
- Expensive-to-reverse choices (schema, wire formats, public IDs, events)
- About to write "usually", "probably", or "from memory" for an external API
What counts as docs
- Local repo docs, specs, ADRs, schemas, tests
- Official product docs, API refs, migration guides, changelogs, SDK types
- Registry version checks (
npm view <pkg> versionor equivalent) - Source/types when official docs are incomplete (evidence, not folklore)
Avoid Stack Overflow / blogs / memory as the primary source when official docs exist.
Workflow
- Name the surface (package, version, endpoint, CLI, config, feature)
- Web-search official docs unless already local / URL-supplied
- Read the closest docs; verify package major before install/import
- Extract only needed facts (options, imports, limits, breaking changes)
- Implement/answer from those facts; call out doc↔code drift
- Verify with the smallest useful check
- Cite docs or local files that shaped the answer
When local is enough
Brief local reads are fine for existing helpers, nearby tests, typed interfaces. Proceed normally for trivial syntax/typos with no external contract.
If docs unavailable
Say so plainly before relying on memory. Narrow uncertainty; do not present results as confirmed-current.
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 · 60 lines · 62 tokens per session scan A 784d870c455c
read-the-damn-docs is a skill published in the GitHub repository Team-Deepiri/deepiri-axiom (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 62 tokens to every session and 599 once invoked, about $0.0002 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 2026-10-26.
read-the-damn-docs compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| read-the-damn-docsTeam-Deepiri/deepiri-axiom | Skill | 2 | yesterday | Apache-2.0 | A | 62 | Claude Code |
| orbit-notionnexu-io/open-design | Skill | 106k | yesterday | Apache-2.0 | A | 117 | Claude Code, Codex |
| agentmailpaperclipai/paperclip | Skill | 111k | yesterday | MIT | A | 30 | Claude Code, Codex |
| Cortexdanielmiessler/LifeOS | Skill | 20k | yesterday | MIT | A | 184 | Claude Code |
| rowboat-spacesrowboatlabs/rowboat | Skill | 18k | yesterday | Apache-2.0 | A | 60 | Claude Code, Codex |
| feishuHmbown/CodeWhale | Skill | 41k | 6d ago | MIT | A | 33 | Claude Code, Codex |
| pinchtab-mcppinchtab/pinchtab | Skill | 11k | 10d ago | MIT | A | 52 | Claude Code, Codex |