Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/iwasa-kosui/kamae-tsnpx agentmods add skills/iwasa-kosui/kamae-ts/kamae-reviewWrote 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/skills/iwasa-kosui/kamae-ts/kamae-review)<a href="https://agentmods.dev/skills/iwasa-kosui/kamae-ts/kamae-review"><img src="https://agentmods.dev/badge/skills/iwasa-kosui/kamae-ts/kamae-review/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/iwasa-kosui/kamae-ts/kamae-review"><img src="https://agentmods.dev/badge/skills/iwasa-kosui/kamae-ts/kamae-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00105 | $0.01237 |
| Opus 5 | $0.00053 | $0.00619 |
| Sonnet 5 | $0.00021 | $0.00247 |
| Haiku 4.5 | $0.00011 | $0.00124 |
Grade A, and why
kamae-review 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Kamae Code Review
Adversarial review against the kamae principles. The knowledge base lives in ../kamae/; this skill links rather than duplicates.
Step 0: Load applicable rules
Before any other step, glob and Read rules in priority order:
.claude/rules/*.md(project-level overrides at the working-tree root)~/.claude/rules/*.md(user-global preferences)../../rules/defaults/*.mdrelative to thisSKILL.md(plugin defaults)
For each file:
- Read the YAML frontmatter. Skip the rule unless
applies-toiskamae-reviewor*. - Group by
name. For eachname, keep only the highest-tier instance (1 > 2 > 3); within a tier the lexicographically last filename wins. - A
check-togglerule withenabled: falseremoves the named check from the walk in step 3 below. - A
conventionrule sets project-specific expectations the review respects (e.g., a designated location for Branded Types).
If no rules are found, proceed with all checks active. See ../../rules/README.md for the rule format.
Review Procedure
-
Load principle knowledge. Before reading any code under review, read:
../kamae/SKILL.md— principle index- The validation library guide matching the project's
package.jsonunder../kamae/validation-libraries/(zod.md/valibot.md/arktype.md) - The Result library guide matching the project's
package.jsonunder../kamae/result-libraries/(neverthrow.md/byethrow.md/fp-ts.md/option-t.md) - Each topic file under
../kamae/cited by the checklist sub-files you read.
-
Read the files under review.
-
Walk the checklist. Read each checklist sub-file in order; match findings to its items.
checklist/domain-modeling.md— Discriminated Unions, Companion Objects, Branded Types, file structure, domain-owned ports, separate single-operation resolvers/stores (items 1.x)checklist/state-transitions.md— pure state transitions, exhaustiveness (items 2.x)checklist/error-handling.md— Result types, error-boundary classification, DU error types (items 3.x)checklist/boundary.md— schema validation, noasassertions, schema-derived types (items 4.1, 4.2, 4.4)checklist/pii-protection.md—Sensitive<T>for PII (item 4.3)checklist/declarative-and-tests.md— array operations, events, fixtures (items 5.x, 6.x)
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 Changed 0733a61bd7c6
- 12d ago First seen · 89 lines · 105 tokens per session scan A 910227f4aa24
kamae-review is a skill published in the GitHub repository iwasa-kosui/kamae-ts (55 stars, last pushed 5d ago), licensed MIT. It adds 105 tokens to every session and 1,237 once invoked, about $0.0005 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 skills, from other repositories
no-bare-casts
Writing as in TypeScript or TSX production code, modifying a file that contains a bare as cast, silencing a type error with a cast, encountering as unknown as, or reviewing a cast site.
coding-standards
Universal coding standards, best practices, and patterns for TypeScript, JavaScript, React, and Node.js development.
splitting-oversized-modules
Split an oversized Python module (a thousand-plus-line logic.py, models.py, api.py, or its test file) into a package of one module per concern, mechanically and provably without changing behavior. Use on a request to split / break up / decompose a god module or move functions out of one, once a human has agreed to…
plankton-code-quality
Write-time code quality enforcement using Plankton — auto-formatting, linting, and Claude-powered fixes on every file edit via hooks.
typescript-style-guide
Apply, review, and explain the opinionated conventions in the TypeScript Style Guide. Use automatically only when TypeScript conventions are part of the requested task, including type modelling, discriminated unions, function APIs, variables and state, naming, source organization, React props, component APIs, state…
architecture-audit
Systematic architecture audit and refactoring methodology for Rust + TypeScript codebases. Use when performing refactoring, cleanup, unification, code review, dead code removal, module reorganization, or tech debt elimination. Ensures no naming confusion, semantic overloading, hidden defaults, duplicate logic, or…