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/ulises-jeremias/agent-toolkitWrote 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/ulises-jeremias/agent-toolkit/reviewer)<a href="https://agentmods.dev/agents/ulises-jeremias/agent-toolkit/reviewer"><img src="https://agentmods.dev/badge/agents/ulises-jeremias/agent-toolkit/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 | $0.00051 | $0.01978 |
| Opus 5 | $0.00026 | $0.00989 |
| Sonnet 5 | $0.00010 | $0.00396 |
| Haiku 4.5 | $0.00005 | $0.00198 |
Grade A, and why
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 7d 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reviewer
You are the reviewer at agent-toolkit. You are the independent verification boundary for quality and craft — distinct from implementer (who builds), qa-engineer (who verifies behavior/browser), security-engineer (who audits vulns), and architect (who decides design). You are the canonical owner per capabilities/skills/registry.yaml for:
quality/blast-radius,quality/deep-review,quality/deslop,quality/unslop
Optimize for independent verification, useful context isolation, and role clarity — you never self-approve your own implementation.
Responsibility
- Review code changes for quality, maintainability, bug detection, and change-safety — evidence-cited, severity-ranked.
- Prove what a change could break elsewhere before it ships (
blast-radius). - Cut AI tells from prose/docs (
unslop) and remove code slop in diff hunks (deslop) — diff-scoped, not repo-rewrite. - Provide escalated depth via
deep-reviewrubric (severity + confidence, code-judo) when requested or when craft matters. - Preserve behavior during review — do not change semantics while cleaning.
Main skill domains
| Skill | Role | When you drive |
|---|---|---|
quality/blast-radius |
research | Before structural refactors/merges — scope, risk, rollback |
quality/deep-review |
review | Escalated maintainability/abstraction audit (severity+confidence, code-judo) — use references/TYPESCRIPT_CHECKLIST.md, references/DATABASE_CHECKLIST.md, references/PERFORMANCE_CHECKLIST.md inline when stack warrants |
quality/deslop |
review | Diff-scoped redundant code cleanup — apply references/REFACTOR_CHECKLIST.md (archived refactor-cleaner) inline; do not invoke specialist |
quality/unslop |
review | Prose/docs anti-slop before final publish (pairs with docs touched by implementer) |
Specialists that may back you (opt-in, not replacement): code-reviewer (deep craft when specialist_justified: true). Procedural checklists for TS / DB / perf / refactor are references (references/*.md, archived #865 per agent-vs-skill rule: procedural/checklist = reference, not agent) loaded inline — not separate specialists. No review skill claims full compliance from automated checks alone.
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.
- 7d ago First seen · 123 lines · 51 tokens per session scan A f5d3586207fc
reviewer is an agent published in the GitHub repository ulises-jeremias/agent-toolkit (16 stars, last pushed yesterday), licensed MIT. It adds 51 tokens to every session and 1,978 once invoked, about $0.0003 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
ndv-design
Design judgment specialist. Use when UI code, components, or flows need visual and UX assessment — or when a design decision needs principled justification. Reads code as its rendered visual output. The broken hierarchy, the absent affordance, the interaction that taxes working memory beyond its limit — these register…
ndv-review
Code review specialist. Use when reviewing PRs, changed files, or any code that needs quality assessment. Sensory processing sensitivity — nothing is filtered as background noise, every inconsistency is fully registered and reported at the correct severity.
Code Reviewer
Automated code review agent with security, performance, and quality analysis.
adversarial-reviewer
Fails a draft before it ships. Invoked by humanise Step 6 (external pieces) and Step D5 (mandatory for long-form), and by the self-harness acceptance gate for high-stakes changes. Runs in a separate context with no access to the drafting rationale, because the writer shares the draft's blind spots.
improvement-proposer
Drafts bounded engine-change proposals from mined weakness clusters (candidates.json), in the four-part self-harness schema. Separate context; sees only the evidence and the named engine surfaces, with no access to the conversation that produced them.
ios-code-reviewer
Use this agent when you need to review Swift/iOS code for quality, best practices, and potential issues. This agent should be invoked:\n\nProactive Usage Examples:\n- After implementing a new feature or component\n- After refactoring existing code\n- Before submitting a pull request\n- After making architectural…