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 thienanblog/awesome-ai-agent-skills --skill documentation-guidelinesgit clone --depth 1 https://github.com/thienanblog/awesome-ai-agent-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/thienanblog/awesome-ai-agent-skills/documentation-guidelines)<a href="https://agentmods.dev/skills/thienanblog/awesome-ai-agent-skills/documentation-guidelines"><img src="https://agentmods.dev/badge/skills/thienanblog/awesome-ai-agent-skills/documentation-guidelines/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/thienanblog/awesome-ai-agent-skills/documentation-guidelines"><img src="https://agentmods.dev/badge/skills/thienanblog/awesome-ai-agent-skills/documentation-guidelines.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00071 | $0.01393 |
| Opus 5 | $0.00036 | $0.00696 |
| Sonnet 5 | $0.00014 | $0.00279 |
| Haiku 4.5 | $0.00007 | $0.00139 |
Grade A, and why
documentation-guidelines 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Documentation Guidelines
Goal
Treat documentation as durable semantic context for agents. Capture what code cannot safely explain alone: business intent, ownership, invariants, lifecycle, permissions, side effects, contracts, operational constraints, and decision rationale. Let source and tests own implementation detail and executable evidence.
Prefer compact facts over tutorial prose. Follow repository instructions and existing conventions; do not impose a standard directory tree.
Run this skill in the main conversation. Delegation can increase usage; do not use subagents unless the user explicitly approves the proposed agent count and scope. Ask again before expanding an approved scope.
Read only the relevant reference:
references/templates.mdfor module, feature, workflow, contract, or runbook docs.references/architecture.mdfor multi-owner routing, registries, and structure.references/audit-cleanup.mdfor broad audits, consolidation, or stale-doc removal.
Context Protocol
Start with documentation before broad source exploration:
- Read repository instructions and the nearest documentation router or index.
- Read the owner document for the relevant scope.
- Follow its required-context links for parent scope, contracts, dependencies, state models, decisions, and operational constraints.
- Use named source and test anchors to verify missing, risky, or plausibly stale facts; do not rediscover the whole system from code by default.
- Ask a targeted question only when docs, focused evidence, and history cannot resolve a fact or a product decision is required.
Do not cap reading by file count. Stop when the completeness gate passes, and do not follow merely related links after that point. Mark required context separately from additional context when the distinction prevents over-reading or missed dependencies.
Context Completeness Gate
Before relying on docs, be able to state the applicable:
- Business outcome, scope, non-goals, and terminology.
- Actors, permissions, preconditions, and triggers.
- Rules, invariants, lifecycle or state transitions, and failure paths.
- Inputs, outputs, persisted facts, public contracts, and compatibility constraints.
- Side effects, transaction boundaries, retries, and idempotency expectations.
- Ownership boundaries, upstream dependencies, and downstream consumers.
- Authoritative source and test anchors, plus unresolved or intentionally unspecified behavior.
What ships with it
3 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 · 132 lines · 71 tokens per session scan A 7066739aee1f
documentation-guidelines is a skill published in the GitHub repository thienanblog/awesome-ai-agent-skills (65 stars, last pushed 13d ago), licensed Apache-2.0. It adds 71 tokens to every session and 1,393 once invoked, about $0.0004 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…