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 skills add s977043/river-review --skill security-basicgit clone --depth 1 https://github.com/s977043/river-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/s977043/river-review/security-basic)<a href="https://agentmods.dev/skills/s977043/river-review/security-basic"><img src="https://agentmods.dev/badge/skills/s977043/river-review/security-basic/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/s977043/river-review/security-basic"><img src="https://agentmods.dev/badge/skills/s977043/river-review/security-basic.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00023 | $0.00949 |
| Opus 5.5 | $0.00009 | $0.00380 |
| Sonnet 5.5 | $0.00005 | $0.00190 |
| Haiku 4.5 | $0.00002 | $0.00095 |
Grade A, and why
Baseline Security Checks 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 yesterday.
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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pattern declaration
Primary pattern: Reviewer Secondary patterns: Inversion Why: セキュリティチェックはチェックリスト型評価が主だが、セキュリティ無関係の変更では実行を止めるゲートが必要
Guidance
- Look for string-concatenated queries or unsafe ORM calls; require parameterization.
- Flag unescaped HTML sinks (
dangerouslySetInnerHTML/innerHTML) and missing sanitization. - Catch secrets or tokens hardcoded in code; prefer environment/config inputs.
- Ensure input validation and authz/CSRF/error handling paths exist without leaking sensitive detail.
- Open redirect: a return URL may pass a same-host check by a server-side parser (e.g. PHP
parse_url), then reachLocation/redirect()/href. Check that values containing\are rejected before that check.- PHP
parse_url('http://evil.example\\@self.example/', PHP_URL_HOST)returnsself.example. - Browsers (WHATWG URL) treat
\as/and navigate toevil.example. - If the value is decoded again after the check (double encoding, a later
urldecode), reject%5Cas well. - Rejecting
\/%5Calone is not enough. A check that skips values without aparse_urlhost letshttp:evil.exampleand/<TAB>/evil.examplethrough. Browsers resolve both toevil.example. - Raise confidence when a sibling implementation in the same repository already rejects
\/%5C.
- PHP
- Lexical-shape exemptions: when a diff adds or widens an allowlist that skips masking/validation because a value looks like a path or variable reference, check non-canonical forms that would wrongly hit it (
..segments, empty segments//, trailing delimiters, case variants,%2F, a second assignment on the same line), and expect tests pinning that those forms stay masked/rejected.
Non-goals
- テスト用ダミー値や意図された緩和を推測で脆弱と決めつけない。
Pre-execution Gate / 実行前ゲート
このスキルは以下の条件がすべて満たされない限りNO_REVIEWを返す。
- 差分にアプリケーションコード(api/, routes/, db/, auth/等)の変更が含まれている
- 差分がテストファイルやフィクスチャのみでない
- 外部入力の処理、認証/認可、データ永続化のいずれかに関連するコードが含まれている
ゲート不成立時の出力: NO_REVIEW: security-basic — セキュリティ関連のアプリケーションコード変更が検出されない
What ships with it
16 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.
- eval/promptfoo.yaml 4.8 KB
- fixtures/01-sql-injection-happy.md 955 B
- fixtures/02-false-positive-test.md 935 B
- fixtures/03-open-redirect-backslash-happy.md 1.5 KB
- fixtures/04-open-redirect-relative-path-allowlist-guard.md 1.7 KB
- fixtures/05-open-redirect-null-host-bypass-happy.md 1.8 KB
- fixtures/06-lexical-path-exemption-happy.md 1.5 KB
- golden/01-sql-injection-happy.md 592 B
- golden/02-false-positive-test.md 455 B
- golden/03-open-redirect-backslash-happy.md 1.1 KB
- golden/04-open-redirect-relative-path-allowlist-guard.md 569 B
- golden/05-open-redirect-null-host-bypass-happy.md 1.1 KB
- golden/06-lexical-path-exemption-happy.md 864 B
- prompt/system.md 5.2 KB
- prompt/user.md 2.1 KB
- README.md 3.6 KB
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.
- yesterday Changed · +1 lines 4443950ba2b5
- 10d ago Changed · +10 lines · +3 tokens per session 29f6bda520bd
- 1mo ago First seen · 55 lines · 20 tokens per session scan A 17fb602acbfa
Baseline Security Checks is a skill published in the GitHub repository s977043/river-review (7 stars, last pushed today), licensed MIT. It adds 23 tokens to every session and 949 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
python-services
Python patterns for CLI tools, async parallelism, and backend services. Use when building CLI apps, async/parallel Python, FastAPI services, background jobs, or configuring Python project tooling (uv, ruff, ty).
nodejs-backend
Node.js backend patterns: framework selection, layered architecture, TypeScript, validation, error handling, security, production deployment. Use when building REST APIs, Express/Fastify servers, microservices, or server-side TypeScript.
logic-review
Find logic bugs in a single file or function via semi-formal execution tracing (Premises → Trace → Divergence → Trigger → Remedy). Trigger when a user shares code and suspects something is wrong without naming a concrete failure — phrases like "review this", "does this look right", "check this function", "audit this…
ia-php-laravel
Modern PHP 8.4 and Laravel patterns: architecture, Eloquent, migrations, queues, testing. Use when working with Laravel, Eloquent, Blade, artisan, or building/testing a framework-based PHP app. Not for php-src internals, standalone PHP libraries, or general PHP language discussion.
php-laravel
Modern PHP 8.2+ and Laravel patterns: architecture, Eloquent, queues, Pest testing. Use when asked to "write PHP", "build a Laravel app", "fix Eloquent query", "add a queue job", "write a Pest test", or mentions PHP, Laravel, Eloquent, Blade, artisan, or migrations.
run-iteration-eval
Run the Logic-Lens content-eval pipeline for one iteration and produce a scored summary.json — use to measure a skill change. Wraps scripts/run-content-evals.sh (runner, costs tokens) and scripts/grade-iteration.py (grader, free, re-runnable). ALWAYS sync the plugin cache first. Use when the user wants to "run the…