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/jgamaraalv/ts-dev-kit/codebase-adapternpx skills add jgamaraalv/ts-dev-kit --skill codebase-adaptergit clone --depth 1 https://github.com/jgamaraalv/ts-dev-kitWhat 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 | $0.00147 | $0.03060 |
| Opus 5 | $0.00073 | $0.01530 |
| Sonnet 5 | $0.00029 | $0.00612 |
| Haiku 4.5 | $0.00015 | $0.00306 |
Grade B, and why
codebase-adapter scanned grade B with 1 finding 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 2d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
**Available MCPs** — read `.claude/settings.json` in project root (and `~/.claude/settings.json` as fallback). Extract `mcpServers` keys. How it starts
The opening of the file, as written. The whole thing — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pre-injected project snapshot (verify in phase 2 — do not skip discovery):
Working directory: !pwd
Lockfile detected: !ls bun.lock pnpm-lock.yaml yarn.lock package-lock.json 2>/dev/null | head -1 || echo "none"
Agents installed: !ls .claude/agents/ 2>/dev/null | tr '\n' ' ' || ls agents/ 2>/dev/null | tr '\n' ' ' || echo "(not found)"
MCP servers configured: !python3 -c "import json; s=json.load(open('.claude/settings.json')); print(', '.join(s.get('mcpServers',{}).keys()) or '(none)')" 2>/dev/null || echo "(not found)"
package.json:
!cat package.json 2>/dev/null || echo "(not found)"
You MUST NOT change:
- Any
<phase_*>logic or step sequences - Dispatch protocols, decomposition rules, execution mode decisions
- Core agent principles, role descriptions, or behavior narratives
- Output template formats or section headers
- Skill descriptions or their trigger conditions
- XML tag structures (
<workflow>,<domain_areas>,<skill_map>, etc.)
<phase_1_locate_plugin> Find the plugin root. Try in order:
skills/execute-task/SKILL.mdexists in current directory → user is inside the ts-dev-kit repo.node_modules/@jgamaraalv/ts-dev-kit/→ installed via npm.- Search upward and in siblings for a directory containing
plugin.jsonwith"name": "ts-dev-kit".
Store the resolved plugin root. All edits in phases 3–5 use paths relative to it. </phase_1_locate_plugin>
<phase_2_project_discovery>
Determine the target project root ($ARGUMENTS if provided, otherwise current working directory).
Discover with Read, Glob, Grep — verify everything, assume nothing.
Package manager — detect from lockfile: bun.lock → bun, pnpm-lock.yaml → pnpm, yarn.lock → yarn, package-lock.json → npm.
Monorepo — check for workspaces in package.json, pnpm-workspace.yaml, or turbo.json. Record workspace names and their paths.
Tech stack — read package.json dependencies in root and each workspace:
- HTTP framework: Fastify, Express, Hono, Elysia, or none
- ORM/DB: Drizzle, Prisma, Kysely + database type (PostgreSQL, MySQL, SQLite)
- Frontend: Next.js (detect App Router via
app/directory), Vite + React, or none - Validation: Zod (check version — v3 imports
from "zod", v4 importsfrom "zod/v4"), Valibot - Queue: BullMQ, or none
- Cache: ioredis, @upstash/redis, or none
- Testing: Vitest or Jest; Playwright or Cypress
- Docker: check for
Dockerfileordocker-compose.yml
Project paths (verify with Glob — record exact paths):
- Backend source root (e.g.,
apps/api/src/,src/) - Routes/handlers directory
- DB schema + migrations directory
- DB client file (search for database connection setup)
- Redis client file (search for Redis instantiation)
- Frontend source root (e.g.,
apps/web/,src/) - Shared package: directory path and package name (e.g.,
packages/shared/,@acme/shared)
What ships with it
1 file 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.
- 2d ago First seen · 246 lines · 147 tokens per session scan B 20e22aaf1e52
codebase-adapter is a skill published in the GitHub repository jgamaraalv/ts-dev-kit (15 stars, last pushed 6mo ago), licensed MIT. It adds 147 tokens to every session and 3,060 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…