Borrowing it
Nothing to install: this file belongs to jerseycheese/Narraitor. 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/jerseycheese/Narraitor/main/.claude/skills/narraitor-docs-and-writing/SKILL.mdgit clone --depth 1 https://github.com/jerseycheese/NarraitorWrote 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/jerseycheese/narraitor/narraitor-docs-and-writing)<a href="https://agentmods.dev/skills/jerseycheese/narraitor/narraitor-docs-and-writing"><img src="https://agentmods.dev/badge/skills/jerseycheese/narraitor/narraitor-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/jerseycheese/narraitor/narraitor-docs-and-writing"><img src="https://agentmods.dev/badge/skills/jerseycheese/narraitor/narraitor-docs-and-writing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 23 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00128 | $0.01181 |
| Opus 5 | $0.00064 | $0.00590 |
| Sonnet 5 | $0.00026 | $0.00236 |
| Haiku 4.5 | $0.00013 | $0.00118 |
Grade A, and why
narraitor-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 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Docs & writing
1. Purpose
Keep the written record honest and in-voice: docs describe verified state, stale claims get marked not deleted-silently, and corrections append rather than rewrite.
2. When to use
Any doc edit; any PR/issue/comment prose; discovering doc-vs-code contradictions; recording corrections.
3. When not to use
- Deciding WHETHER a claim is true →
narraitor-change-control/narraitor-validation-and-qa. This skill is how to WRITE it. - Don't proactively create new doc files — update existing docs of record (house rule).
4. Inputs required
The doc, the code evidence for every claim you'll write, and (for corrections) the original wrong claim verbatim.
5. Procedure
Where docs live: committed record = public_docs/ (ADRs, guides, roadmap), README.md, DESIGN.md; templates at public_docs/templates/ (architecture-decision, feature-implementation, technical-guide, pr-content). docs/ is a gitignored personal planning vault — never cite it as record. Skills (.claude/skills/) are procedures, not status docs — project status lives in issues/roadmap.
Status language (forbidden without evidence): "done / fixed / verified / validated / integrated / reliable / complete" follow the change-control table — each needs a named artifact. Absent evidence, write what is true: "implemented, unit-green, not yet app-verified".
Evidence labels for doc claims: known (verified on a stated date), observed, candidate, unverified, stale-risk, owner-confirmation-needed. Date volatile claims: "as of 2026-07-04 (develop @ 4bec88e6)".
Marking stale content: when you find a stale claim you can't immediately fix, mark it in place — > STALE-RISK (2026-07-04): X below contradicts <file/evidence>; verify before use. — and flag it (issue or PR note). Known standing stale spots: DESIGN.md's /dev/design-system* canon refs; public_docs/features/ai-systems.md model name; ADR-007 (correctly historical).
Append-only corrections (template: templates/correction-append.md): never rewrite a wrong claim to look like it was always right. Append the correction with date, why it was wrong, actual state, evidence. History of being wrong is data.
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.
- 10d ago First seen · 61 lines · 128 tokens per session scan A b3b2cd71f4a7
narraitor-docs-and-writing is a skill published in the GitHub repository jerseycheese/Narraitor (30 stars, last pushed today), licensed MIT. It adds 128 tokens to every session and 1,181 once invoked, about $0.0006 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
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…