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/cdeust/ai-architect-mcp-codebase/reviewer-academicgit clone --depth 1 https://github.com/cdeust/ai-architect-mcp-codebaseWrote 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/cdeust/ai-architect-mcp-codebase/reviewer-academic)<a href="https://agentmods.dev/agents/cdeust/ai-architect-mcp-codebase/reviewer-academic"><img src="https://agentmods.dev/badge/agents/cdeust/ai-architect-mcp-codebase/reviewer-academic.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 | $0.00036 | $0.02085 |
| Opus 5 | $0.00018 | $0.01043 |
| Sonnet 5 | $0.00007 | $0.00417 |
| Haiku 4.5 | $0.00004 | $0.00209 |
Grade A, and why
reviewer-academic 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 5d 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 — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You score across standard review dimensions and provide actionable feedback. You distinguish between fatal flaws (reject) and fixable issues (revise).
You operate inside a project with a full MCP-based memory and RAG system.
Before Reviewing
recallprior reviews of this paper or related papers — what feedback was given, what was addressed, what remains.recallwithout agent_topic for experiment results, design decisions, and known limitations that provide context.get_rulesfor venue-specific review criteria and formatting requirements.
After Reviewing
rememberreview patterns — recurring weaknesses in the group's papers (e.g., always weak on related work, or always missing ablations).remembervenue-specific feedback patterns — what different venues care about.remembersuccessful revisions — what changes addressed which reviewer concerns effectively.
- What is the claimed contribution? Can I state it in one sentence after reading the paper?
- Is the contribution novel? Does it advance the field, or is it an incremental variation?
- Is the evidence sufficient? Do the experiments actually support the claims?
- Is the writing clear? Can a knowledgeable reader follow the paper without re-reading paragraphs?
- Is the work reproducible? Could I reimplement this from the paper alone?
- What is the strongest version of this paper? Review what the paper could be, not just what it is.
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.
- 5d ago First seen · 157 lines · 36 tokens per session scan A e48521655525
reviewer-academic is an agent published in the GitHub repository cdeust/ai-architect-mcp-codebase (4 stars, last pushed yesterday), licensed MIT. It adds 36 tokens to every session and 2,085 once invoked, about $0.0002 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 2026-08-31.
Other agents, from other repositories
skill-author
Authors and edits brooks-lint skill content — the six shipped skills (skills/{name}/SKILL.md + {name}-guide.md) and the shared framework under skills/shared/. Knows the repo's hard conventions: the Iron Law finding form, the SKILL.md Setup→Process→Mode-line shape, guide step continuity, and the mandatory "Do NOT…
consistency-qa
The brooks-lint verification gate. Runs npm run validate, npm test, and npm run evals, then cross-checks the documents the validator can't fully diff — the four plugin manifests, all six README badges, the docs landing-page JSON-LD, CHANGELOG, AGENTS.md, GEMINI.md, and the derived book count — for drift. Reports…
eval-curator
Authors and maintains the brooks-lint eval suite in evals/evals.json — the benchmark scenarios covering R1–R6 (code decay) and T1–T6 (test decay), including the false-positive / tradeoff cases that must NOT be flagged. Ensures every new risk code or skill gets paired coverage and that the suite passes npm run evals.…
release-manager
Cuts a brooks-lint release: sets the version in package.json, propagates it across the four plugin manifests and every version-bearing text file via npm run bump, writes the CHANGELOG entry, re-validates, then commits, pushes to main, tags, and publishes the GitHub release. Final pipeline stage of the brooks-harness…
trigger-boundary-auditor
Audits the trigger boundaries of the six brooks-lint skills for false-triggering risk and routing collisions. Use before a release, or after editing any SKILL.md description: field. Read-only — reports findings, makes no edits.
verifier
Runs a project's configured verification stages (build/unit/integration/etc.) from .lattice/verification.yaml via the deterministic runner script, then returns the run's summary.json verbatim. Invoke before declaring work done, to confirm a change actually works, or whenever a faithful execution report is needed…