Borrowing it
Nothing to install: this file belongs to richardthe3rd/cambridge-beer-festival-app. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/richardthe3rd/cambridge-beer-festival-app/main/.claude/skills/docs-and-writing/SKILL.mdgit clone --depth 1 https://github.com/richardthe3rd/cambridge-beer-festival-appWrote 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/richardthe3rd/cambridge-beer-festival-app/docs-and-writing)<a href="https://agentmods.dev/skills/richardthe3rd/cambridge-beer-festival-app/docs-and-writing"><img src="https://agentmods.dev/badge/skills/richardthe3rd/cambridge-beer-festival-app/docs-and-writing/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/richardthe3rd/cambridge-beer-festival-app/docs-and-writing"><img src="https://agentmods.dev/badge/skills/richardthe3rd/cambridge-beer-festival-app/docs-and-writing.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 | $0.00200 | $0.05824 |
| Opus 5.5 | $0.00080 | $0.02330 |
| Sonnet 5.5 | $0.00040 | $0.01165 |
| Haiku 4.5 | $0.00020 | $0.00582 |
Grade A, and why
docs-and-writing 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 2mo 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 — 445 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Docs and Writing
This skill governs every piece of writing this project keeps as a record:
docs/, ADRs, GitHub Issues, commit messages, PR titles/descriptions, and
completion summaries. If you are about to create a .md file, file an issue,
or write a commit message, read this first — there is one home for each kind
of fact, and conventions here feed automated systems (changelog generation,
PR-title CI gate) that silently misbehave if you improvise.
1. The docs-of-record taxonomy
docs/ has five top-level categories, indexed in docs/README.md. Each
answers a different question:
| Directory | Question it answers | Example |
|---|---|---|
docs/code/ |
"How does this work right now?" | docs/code/routing.md, docs/code/accessibility.md, docs/code/domain-architecture.md |
docs/adr/ |
"Why did we decide this, and what did we reject?" | docs/adr/0004-path-based-url-strategy.md |
docs/processes/ |
"What's the repeatable procedure?" | docs/processes/ci-cd.md, docs/processes/release.md |
docs/tooling/ |
"How do I set up this piece of infrastructure?" | docs/tooling/cloudflare-pages.md, docs/tooling/firebase.md |
docs/planning/ |
"What are we proposing to build?" (not yet decided/shipped) | docs/planning/my-festival/vision.md, docs/planning/rating-service/design.md |
docs/planning/archive/ |
"What did we propose and then finish or abandon?" | docs/planning/archive/deep-linking/, docs/planning/archive/patrol-firebase-testing/ |
docs/todos.md is a sixth, explicitly dead, category: it is archived
(banner: "Issues are now tracked in GitHub... preserved for historical
reference only. Do not add new items here."). GitHub Issues is the single
tracker for bugs/features/tasks — see §3.
The lifecycle rule
A planning doc has exactly two ways to stop being "active": it ships, or
it's abandoned. Either way, it moves to planning/archive/ and its durable
decision gets extracted into an ADR. A planning doc is not itself a decision
record — decisions belong in adr/ where they're indexed and searchable;
the planning doc is the working scratchpad kept for archaeology.
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.
- 2mo ago Changed · +24 lines 494add356eeb
- 2mo ago First seen · 421 lines · 200 tokens per session scan A 74a9575bcefd
docs-and-writing is a skill published in the GitHub repository richardthe3rd/cambridge-beer-festival-app (3 stars, last pushed today), licensed MIT. It adds 200 tokens to every session and 5,824 once invoked, about $0.0008 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 2026-08-31.
docs-and-writing compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| docs-and-writingrichardthe3rd/cambridge-beer-festival-app | Skill | 3 | today | MIT | A | 200 | Claude Code |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |