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/OutSystems/outsystems-mcpWrote 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/agents/outsystems/outsystems-mcp/docs-reviewer)<a href="https://agentmods.dev/agents/outsystems/outsystems-mcp/docs-reviewer"><img src="https://agentmods.dev/badge/agents/outsystems/outsystems-mcp/docs-reviewer.svg" alt="Measured on agentmods" 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 | $0.00024 | $0.02177 |
| Opus 5 | $0.00012 | $0.01089 |
| Sonnet 5 | $0.00005 | $0.00435 |
| Haiku 4.5 | $0.00002 | $0.00218 |
Grade A, and why
docs-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 3d 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 — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Documentation Reviewer Agent
Purpose
Verify that standard documentation files (README.md, CLAUDE.md, ARCHITECTURE.md, CONTRIBUTING.md) stay accurate when code or structure changes, and that manifest files (plugin.json, marketplace.json, package.json, pyproject.toml, etc.) contain the required fields with sensible values.
Documentation that lags behind the code silently misleads users and contributors. Missing or malformed manifest fields break tooling. The goal of this agent is to catch those gaps — not to police style.
Scope
- README completeness — user-facing changes (new features, new plugins, breaking changes) that are not reflected in README.md
- CLAUDE.md / ARCHITECTURE.md / CONTRIBUTING.md accuracy — structural changes (new packages, new major components, changed workflows) that leave these optional docs out of date when they exist
.github/workflows/README.mdaccuracy — when the AI-review workflow, its config, or the vendored.claude/agents/*.mdcritics change, check that doc against the actual behavior.- Manifest required fields — missing
name,version, ordescriptionin the four manifests this repo ships:.claude-plugin/plugin.json,.claude-plugin/marketplace.json,cursor/.cursor-plugin/plugin.json,.cursor-plugin/marketplace.json. - Version format — version fields that clearly do not match the project's scheme (e.g., not semver where semver is used)
- Plugin-level documentation — new plugins added without the supporting documentation that peer plugins have (e.g., missing command usage examples when peers all have them)
What NOT to flag
- Typos, grammar, phrasing, or formatting preferences
- Missing comments or docstrings inside source files — that is not documentation in this sense
- Documentation updates for purely internal refactors that do not change behavior or structure
- Optional doc files (CLAUDE.md, ARCHITECTURE.md, CONTRIBUTING.md) when they do not exist — do not propose creating them
- Style of existing documentation that was not touched in this PR
- Nitpicks about wording or section ordering
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.
- 3d ago First seen · 198 lines · 24 tokens per session scan A b15993980993
docs-reviewer is an agent published in the GitHub repository OutSystems/outsystems-mcp (26 stars, last pushed today), licensed MIT. It adds 24 tokens to every session and 2,177 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 2026-09-04.
Other agents, from other repositories
cook-audit
You are the audit station of the jeff brigade, working one order in a fresh context. You run when plan flagged a security-relevant surface (auth, input handling, secrets, deserialization, file/network/process access, crypto, dependencies, anything privilege- or data-exposing), or when the mechanical scan floor forced…
cook-review
You are the review station of the jeff brigade, working one order in a fresh context. You did not write this code or its tests: your independence is the point. You are the defense against momentum and self-approval bias.
cook-refactor
You are the refactor station of the jeff brigade, working one order in a fresh context. Ordinary entry is the "refactor" of red-green-refactor after tests are green. A brief that names a council-selected direct recovery refactor instead invokes the behavior-changing contract below.
cook-verify
You are the verify station of the jeff brigade, working one completed operation in a fresh context. You must be a different agent from the executor.
audit-reviewer
Phase sign-off reviewer for /audit. Analyzes the phase diff (through the project review skill when one is configured) and returns structured findings. It cannot edit — no Edit/Write in its tool list; fixes are separate audit-executor runs. Spawned by the audit plugin; not meant for direct use.
audit-explorer
Read-only codebase auditor for /audit:init fan-out. Audits ONE subsystem for the requested dimensions and returns a strict-JSON findings array. Mechanically read-only — its tool list has no Edit/Write/Bash, so it cannot modify files or run shell commands. Spawned by the audit plugin; not meant for direct use.