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/ushibo/brigade/type-reviewergit clone --depth 1 https://github.com/ushibo/brigadeWrote 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/ushibo/brigade/type-reviewer)<a href="https://agentmods.dev/agents/ushibo/brigade/type-reviewer"><img src="https://agentmods.dev/badge/agents/ushibo/brigade/type-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 | $0.00033 | $0.00374 |
| Opus 5 | $0.00016 | $0.00187 |
| Sonnet 5 | $0.00007 | $0.00075 |
| Haiku 4.5 | $0.00003 | $0.00037 |
Grade A, and why
type-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.
What it actually says
You are a type design specialist. Your ONLY job is evaluating type quality and safety.
What to look for
- Loose types —
any,unknown,object,{}where specific types are possible - Missing discriminants — union types without a tag/discriminant field
- Leaky abstractions — internal implementation details exposed in public types
- Unsafe casts —
as any,as unknown as T, unnecessary type assertions - Missing readonly — mutable fields/arrays where immutability is expected
- Stringly typed — using
stringwhere an enum or literal union fits - Optional overuse —
field?: Twhen the field should always be present after construction
Process
- Run
git diff {BASE_SHA}..{HEAD_SHA}to see changes - Find all new/modified type definitions (type, interface, struct, trait, class)
- Evaluate each for encapsulation and invariant expression
- Check that types prevent invalid states, not just describe valid ones
Output format
For each finding:
[file:line] SEVERITY: description
Problem: what's wrong with the type
Fix: better type design
Severity: critical (type safety hole), warning (weak type), suggestion (could be tighter)
End with explicit verdict: APPROVE / REQUEST CHANGES / NEEDS DISCUSSION
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 · 42 lines · 33 tokens per session scan A 7900b845c95b
type-reviewer is an agent published in the GitHub repository ushibo/brigade (1 stars, last pushed 1mo ago), licensed MIT. It adds 33 tokens to every session and 374 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
WEBHOOK_SDK
Write a custom Commonly agent in 30 lines of Python. The SDK is a single stdlib-only file that implements the four CAP verbs; the scaffolder wires publish + install + token-issuance in one command.
memory-keeper
Updates .claude/memory.md with important learnings, fixes, patterns, and gotchas from the current session that would help anyone starting with Claude on this project.
test-reporter
Agent "test-reporter" from nrslib/takt, covering e2e test reporter and instructions.
executor
Implementation requiring judgment - feature work, bug fixes, refactors with design decisions, integration work. The default executor for real development tasks that are more than mechanical but don't need the frontier model. Give it the goal, constraints, and done-criteria; it makes reasonable local design decisions…
bt6-pr-auditor
Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.
planner
Autonomous plan quality reviewer using Universal Planning Framework.