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.
git clone --depth 1 https://github.com/narailabs/doc-wikiWrote 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/rules/narailabs/doc-wiki/doc-wiki)<a href="https://agentmods.dev/rules/narailabs/doc-wiki/doc-wiki"><img src="https://agentmods.dev/badge/rules/narailabs/doc-wiki/doc-wiki/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/rules/narailabs/doc-wiki/doc-wiki"><img src="https://agentmods.dev/badge/rules/narailabs/doc-wiki/doc-wiki.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 | $0.01399 | $0.01399 |
| Opus 5.5 | $0.00560 | $0.00560 |
| Sonnet 5.5 | $0.00280 | $0.00280 |
| Haiku 4.5 | $0.00140 | $0.00140 |
Grade A, and why
doc-wiki 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 1mo 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wiki Skill
This project has a documentation wiki skill. Before searching the codebase with grep, find, or glob, check if the wiki has the answer by running wiki-query first.
Commands
/doc-wiki:init-- Bootstrap wiki scaffold (includes ecosystem onboarding in Phase 3):node skills/doc-wiki/scripts/init_wiki.js --path <wiki-root> --domain "<domain>" --name "<name>"/doc-wiki:ingest-- Fetch, extract, compile sources into wiki pages; use--refreshto re-fetch previously ingested sources/doc-wiki:query-- Two modes: synthesis (<question>) for summary-first search with--promote <file>to save answer as a page, or path mode (--from <a> --to <b>) for shortest-path traversal vianode skills/doc-wiki/scripts/graph_ops.js path --edges <wiki-root>/graph/edges.jsonl/doc-wiki:lint-- Health check:node skills/doc-wiki/scripts/lint_checks.js --wiki-root <wiki-root>/doc-wiki:edit-- Targeted page edit with diff preview/doc-wiki:stats-- Token efficiency:node skills/doc-wiki/scripts/event_logger.js stats --wiki-root <wiki-root> --since 7d
Script Paths
All TypeScript scripts live at: skills/doc-wiki/scripts/ and compile to .js siblings via npm run build.
| Script | Purpose |
|---|---|
init_wiki.ts |
Bootstrap wiki scaffold |
parse_config.ts |
Read/write wiki.config.yaml |
cache_manager.ts |
Content-hash cache for dedup |
extract_binary.ts |
Binary file extraction |
lint_checks.ts |
Structural lint checks |
quality_score.ts |
Page quality scoring (0.0-1.0) |
graph_ops.ts |
Graph traversal and path queries |
event_logger.ts |
Operation logging and stats |
mermaid_lint.ts |
Mermaid diagram validation |
daily_summary.ts |
Daily summary generation |
Agent Paths
Sub-agents at agents/. External-source fetching is handled by the connectors bundled inside narai-primitives and dispatched through its gather() planner — no per-service subagents in doc-wiki.
wiki-orm-agent-- ORM profile detectionwiki-mermaid-agent-- Mermaid diagram generationwiki-claude-md-agent-- CLAUDE.md maintenancewiki-readme-agent-- Sync repo-rootREADME.mdquickstart block againstwiki/getting-started.md; dispatched alongsidewiki-claude-md-agentin atlas Phase 8
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.
- 1mo ago First seen · 91 lines · 1,399 tokens per session scan A b7b9d1b73b79
doc-wiki is a cursor rule published in the GitHub repository narailabs/doc-wiki (14 stars, last pushed yesterday), licensed Apache-2.0. It adds 1,399 tokens to every session, about $0.0056 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 2026-08-30.
Other cursor rules, from other repositories
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
prefer-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
config-validation-and-normalization
Config validation and normalization responsibilities (defineConfig normalizes, the orm section schema validates and resolves paths, the loader reports per-section diagnostics).