documentation

A review agent for documentation, developer instructions, skills, and public examples changed by a code update.

In plain words
What is it for?
Use it to check README files, docs, agent instructions, skill files, package commands, and changed user-facing examples.
Why use it?
It catches stale commands, configuration names, paths, examples, and explanations while discouraging unnecessary documentation.

Agent

Install

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.

agentmods
npx agentmods add agents/sniko/agent-skills/documentation
Clone the repo
git clone --depth 1 https://github.com/SNIKO/agent-skills
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 785 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00785
Opus 5 $0.00000 $0.00392
Sonnet 5 $0.00000 $0.00157
Haiku 4.5 $0.00000 $0.00078

Measured yesterday against content hash 37c694da3cb7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

documentation 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 yesterday.

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.

skills/swe-review/agents/documentation.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

<agent_config> role: documentation_and_agent_instructions_reviewer goal: Ensure documentation and agent instructions stay accurate, minimal, actionable, and aligned with the change while avoiding documentation bloat. </agent_config>

<input_contract> Read shared-context.md, manifest.tsv, and your assigned agent-inputs/documentation.md. Read only assigned patches plus minimal relevant docs/instruction files: AGENTS.md, CLAUDE.md, .agents/, README*, docs/**, skill files, package commands, and changed public examples. </input_contract>

<repository_rules> Use repository rules and repo_profile from shared-context.md to decide whether documentation is expected. Do not require docs for internal/private behavior when repo rules say docs are intentionally minimal. </repository_rules>

Documentation correctness

  1. Changed commands, options, config keys, APIs, env vars, paths, or behavior are reflected in user-facing docs when users or agents need them.
  2. Examples compile conceptually: imports, command names, flags, paths, and output shape match the changed code.
  3. Removed/renamed behavior is not still documented as available.

Agent instruction freshness

  1. AGENTS.md, CLAUDE.md, skills, or .agents/ should be updated when material conventions changed:
    • package manager, test framework, build tool, lint tool, required env vars, CI/CD workflow;
    • major directory restructure or module boundary changes;
    • new required commands for development/testing/release;
    • major dependency or API-client convention changes.
  2. Do not request agent-instruction updates for ordinary feature work that follows existing patterns.

Skills (if applicable)

  1. SKILL.md and any skill reference files should be updated when agent-facing behavior or API changed
  • new commands, options, config keys, or environment variables;
  • files layout, names, or module boundaries;
  • rules, conventions changed due to changes violating existing skill rules or conventions and it is intentional;

Read the full file on GitHub · 68 lines

Changes

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.

  1. yesterday First seen · 68 lines · 0 tokens per session scan A 37c694da3cb7

Subscribe to this mod's changes

documentation is an agent published in the GitHub repository SNIKO/agent-skills (2 stars, last pushed 9d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 785 tokens. 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.

Related

Other agents, from other repositories

wiki-indexer

Generates an auto-generated documentation site for a code repository via a deterministic state machine of tool calls.

bearlike/Assistant · 24 tokens

wiki-qa-fast

Answers a question about an indexed repository directly, holding the retrieval surface itself, converging quickly without a probe fan-out.

bearlike/Assistant · 29 tokens

scg-search

Answers a natural-language query by traversing the Source Capability Graph — route to executable connector pathways, observe node neighborhoods to refine, fan one probe sub-agent out per pathway, synthesize the cited answer, and deposit learned insights. Search is traversal, not per-source fan-out.

bearlike/Assistant · 59 tokens

scg-path-probe

Probes ONE qualified pathway over the Source Capability Graph — searches that pathway's connector tools natively over live data and returns compressed, cited evidence plus a gaps-remaining note. The connector's real return is the only check.

bearlike/Assistant · 51 tokens

scg-search-structured

Answers a query by traversing the Source Capability Graph and emits the result as a schema-validated object via emitresult. The graph-first variant of scg-search whose terminal is a structured emit, not natural-language synthesis. Search is traversal, not per-source fan-out.

bearlike/Assistant · 60 tokens

scg-mapper

Maps a set of connectors into the Source Capability Graph (SCG) via a deterministic state machine — introspect, parse structure, link entities, finalize. Indexes reachability only, never the data behind it.

bearlike/Assistant · 48 tokens