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 skills/cmdr-chara/codex-toolkit/typescript-quality-enforcernpx skills add cmdr-chara/codex-toolkit --skill typescript-quality-enforcergit clone --depth 1 https://github.com/cmdr-chara/codex-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/skills/cmdr-chara/codex-toolkit/typescript-quality-enforcer)<a href="https://agentmods.dev/skills/cmdr-chara/codex-toolkit/typescript-quality-enforcer"><img src="https://agentmods.dev/badge/skills/cmdr-chara/codex-toolkit/typescript-quality-enforcer.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 | $0.00129 | $0.03010 |
| Opus 5 | $0.00064 | $0.01505 |
| Sonnet 5 | $0.00026 | $0.00602 |
| Haiku 4.5 | $0.00013 | $0.00301 |
Grade A, and why
typescript-quality-enforcer 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 4d 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 — 286 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TypeScript Quality Enforcer
Turn recurring TypeScript/JavaScript quality failures into evidence-backed, deterministic enforcement. Diagnose the repository first, stage adoption second, and fix the violated invariant rather than the lint message.
Trigger boundary
Use this skill for:
- auditing an existing TypeScript/JavaScript repository for type-evidence loss, unsafe assertions, broad contracts, suppressions, weak boundary parsing, and test seams;
- installing or configuring the bundled anti-slop Oxlint rules after an approved proposal;
- migrating an existing anti-slop setup without blindly replacing project-specific policy;
- reducing repeated
any,unknown, unsafe dictionary, assertion, reflection, or module-mocking patterns when the goal is stronger permanent enforcement; - tightening TypeScript compiler/lint discipline when the repository-specific migration cost is part of the decision.
Do not trigger for:
- explaining a concrete runtime failure with unknown cause—use
debugging-investigator; - upgrading TypeScript, Oxlint, a framework, runtime, or public contract as the primary task—use
codebase-evolution-controller; - a defined behavior-preserving refactor that is already chosen—use
review-and-refactor-code; - a named measured performance problem—use
optimize-codebase-performance; - broad web/mobile production readiness where TypeScript quality is only one concern—use the relevant builder;
- deciding whether the integrated release can ship—use
verification-and-release.
Required inputs
Obtain or state:
- repository root, working-tree state, and protected user work;
- TypeScript/JavaScript source boundaries and excluded generated/vendor code;
- package manager, manifests/lockfiles, TypeScript configuration, lint configuration, and existing lint/typecheck commands;
- current compiler/lint baseline, known failures, and CI enforcement;
- whether anti-slop or equivalent project-local rules already exist;
- product/runtime compatibility constraints and public type/API boundaries;
- whether the task is audit-only or an exact previously proposed adoption/remediation stage has been approved.
What ships with it
27 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.
- agents/openai.yaml 322 B
- assets/anti-slop/index.ts 2.2 KB runs code
- assets/anti-slop/LICENSE 1.0 KB
- assets/anti-slop/rules/no-chained-type-assertions.ts 2.5 KB runs code
- assets/anti-slop/rules/no-conditional-empty-object-spread.ts 1.5 KB runs code
- assets/anti-slop/rules/no-known-value-widening.ts 7.6 KB runs code
- assets/anti-slop/rules/no-module-mocking.ts 3.0 KB runs code
- assets/anti-slop/rules/no-object-parameters.ts 4.2 KB runs code
- assets/anti-slop/rules/no-reflect-apply.ts 926 B runs code
- assets/anti-slop/rules/no-reflect-get.ts 939 B runs code
- assets/anti-slop/rules/no-runtime-typeof.ts 1.8 KB runs code
- assets/anti-slop/rules/no-shape-in-symbol-names.ts 1.2 KB runs code
- assets/anti-slop/rules/no-unknown-parameters.ts 3.3 KB runs code
- assets/anti-slop/rules/no-unknown-returns.ts 4.0 KB runs code
- assets/anti-slop/rules/no-unknown-type-aliases.ts 3.5 KB runs code
- assets/anti-slop/rules/no-unsafe-dictionary-type.ts 3.9 KB runs code
- assets/anti-slop/rules/no-widen-then-assert.ts 12 KB runs code
- assets/anti-slop/rules/require-safety-comment-for-type-assertion.ts 1.9 KB runs code
- assets/anti-slop/shared/dictionary-types.ts 17 KB runs code
- assets/anti-slop/shared/lexical-type-parameters.ts 1.8 KB runs code
- assets/anti-slop/shared/reflect-method.ts 1.3 KB runs code
- references/adoption-strategy.md 4.1 KB
- references/anti-slop-vendor-manifest.json 1.9 KB
- references/upstream-provenance.md 2.4 KB
- references/violation-remediation.md 4.0 KB
- scripts/install.mjs 906 B runs code
- scripts/typescript_quality_inventory.py 12 KB runs code
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.
- 4d ago First seen · 286 lines · 129 tokens per session scan A 7bf8759c79c3
typescript-quality-enforcer is a skill published in the GitHub repository cmdr-chara/codex-toolkit (2 stars, last pushed 7d ago), licensed MIT. It adds 129 tokens to every session and 3,010 once invoked, about $0.0006 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 skills, from other repositories
neo4j-driver-javascript-skill
Neo4j JavaScript/TypeScript Driver v6 — driver lifecycle, executeQuery, managed transactions (executeRead/executeWrite), session.run, Integer handling, JSON serialization, record access, async/await patterns, TypeScript types, error handling, and connection setup for Node.js and browser. Use when writing JS/TS code…
boss-advanced
Advanced Boss orchestration patterns — Agent Teams leadership, 6-section delegation template, Skill vs Agent conflict resolution, Guardian pattern, and AI-slop detection.
gstack-sprint
3-Phase Sprint workflow — design → execute → review with user interaction at decision points.
boss-briefing
Vault health check — workflow pattern analysis, profile sync, session gap recovery, persona rule proposals.
briefing-vault
Initialize, manage, and search the per-project .briefing/ vault. Obsidian-compatible persistent knowledge base.
manage-skills
세션 변경사항을 분석하여 검증 스킬 누락을 탐지합니다. 기존 스킬을 동적으로 탐색하고, 새 스킬을 생성하거나 기존 스킬을 업데이트한 뒤 CLAUDE.md를 관리합니다.