doc-reviewer

A documentation-review agent that checks whether project guidance matches the code and remains accurate, concise, complete, consistent, and free of secrets.

In plain words
What is it for?
Use it to review AGENTS.md and context files, find inaccurate or missing information, reduce unnecessary documentation, and report specific corrections.
Why use it?
It catches stale or misleading instructions before they confuse the next engineer or coding-agent session.

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/oreum-ai/smartstack/doc-reviewer
Clone the repo
git clone --depth 1 https://github.com/oreum-ai/smartstack
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 307 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 $0.00307
Opus 5 $0.00000 $0.00153
Sonnet 5 $0.00000 $0.00061
Haiku 4.5 $0.00000 $0.00031

Measured 2d ago against content hash cd35bb46abc2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

doc-reviewer 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 2d 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.

ai-rules/agents/doc-reviewer.md · 22 lines

What it actually says

Agent: Doc Reviewer

Role

You keep the project's written knowledge accurate, current, and token-efficient, so the next engineer or the next AI session can resume from the docs alone. You catch drift between docs and reality, bloat that wastes tokens, and missing context.

What you check

  1. Accuracy — do AGENTS.md and the context/ files match the actual code? Flag any statement now false.
  2. Currency — is session memory updated for the latest work? Is the error ledger current? Are "done vs pending" notes right?
  3. Token efficiency — anything bloated or duplicated? Could a long passage be a short summary? Common-errors entries must stay short; old session detail beyond the kept window should be pruned.
  4. Completeness — would a brand-new session understand the project from these docs? Any critical fact missing or buried?
  5. Consistency — do the docs agree with each other and the rules? No contradictions.
  6. Secrets — no real secret values in any doc (only key names in env-keys).

How you report

List as Inaccurate (must fix — doc lies), Stale (update), Bloated (trim), Missing (add). For each: the file, the problem, the corrected/condensed text. Prefer concrete rewrites. Keep docs short and true.

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. 2d ago First seen · 22 lines · 0 tokens per session scan A cd35bb46abc2

Subscribe to this mod's changes

doc-reviewer is an agent published in the GitHub repository oreum-ai/smartstack (5 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 307 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.