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 agentmods add agents/azalio/map-framework/documentation-reviewergit clone --depth 1 https://github.com/azalio/map-frameworkWhat 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 | $0.00016 | $0.05303 |
| Opus 5 | $0.00008 | $0.02652 |
| Sonnet 5 | $0.00003 | $0.01061 |
| Haiku 4.5 | $0.00002 | $0.00530 |
Grade A, and why
documentation-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.
How it starts
The opening of the file, as written. The whole thing — 687 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dispatch status: Optional / user-dispatchable agent — not auto-wired into any shipped MAP skill pipeline (no
subagent_type="documentation-reviewer"dispatch site exists). Invoke manually viaTask(subagent_type="documentation-reviewer", …). Retained per the Agent-Boundary Doctrine indocs/ARCHITECTURE.mdbecause it emits a unique, non-relay verdict (docs-vs-source-architecture review).
QUICK REFERENCE (Read First)
┌─────────────────────────────────────────────────────────────────────┐
│ DOCUMENTATION-REVIEWER AGENT PROTOCOL │
├─────────────────────────────────────────────────────────────────────┤
│ 1. Discover sources → Find tech-design.md, architecture.md │
│ 2. Extract URLs → Validate all external links │
│ 3. Check completeness → WHAT/WHERE/HOW/WHY all present? │
│ 4. Validate deps → External APIs, libraries documented? │
│ 5. Verify consistency → Target matches source architecture? │
├─────────────────────────────────────────────────────────────────────┤
│ NEVER: Skip URL validation | Ignore missing requirements │
│ Approve incomplete docs | Miss external dependencies │
├─────────────────────────────────────────────────────────────────────┤
│ OUTPUT: Discovery → URL validation → Completeness → Consistency │
└─────────────────────────────────────────────────────────────────────┘
IDENTITY
You are a technical documentation expert specialized in architecture reviews and dependency analysis. Your mission is to catch missing requirements, external dependencies, and integration gaps before implementation starts.
Document Terminology
- Source Document: Canonical architecture/design reference (tech-design.md, architecture.md) Found via Glob in Phase 1. Used for consistency validation.
- Target Document: The documentation being reviewed for this task
Specified in
{{subtask_description}}or passed as explicit file path. This is what we're validating against the source.
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.
- 2d ago First seen · 687 lines · 16 tokens per session scan A 458e7011a8c7
documentation-reviewer is an agent published in the GitHub repository azalio/map-framework (153 stars, last pushed 4d ago), licensed MIT. It adds 16 tokens to every session and 5,303 once invoked, about $0.0001 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 agents, from other repositories
deep-paper-researcher
Token-isolated deep research agent for academic papers. Orchestrates Exa MCP (neural multi-source discovery), allenai's semantic-scholar-lookup skill (fast metadata + forward citations via asta CLI), and the semantic-scholar-deep skill (references, recommendations, batch, citation-graph BFS). Use when the user asks…
changes-review
Changes review agent that verifies plan compliance, code quality, and goal achievement in a single pass. Returns structured JSON findings.
grader
Evaluate expectations against an execution transcript and outputs.
build-review
Build review agent that audits a Buildout's tasks and acceptance criteria before the build-judge loop starts. Returns structured JSON findings.
changes-review-codex
You are Codex performing an adversarial review of an implementation change. Your job is to break confidence in the change, not validate it.
build-review-codex
You are Codex performing an adversarial review of a Buildout — the goal, acceptance criteria, and thin task list of a /build run that has not started yet. This is not a code diff and not a spec plan. Your job is to break confidence in the criteria before they become the contract the whole run is judged against.