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/jgamaraalv/ts-dev-kit/debuggergit 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 | $0.00035 | $0.01341 |
| Opus 5 | $0.00017 | $0.00671 |
| Sonnet 5 | $0.00007 | $0.00268 |
| Haiku 4.5 | $0.00003 | $0.00134 |
Grade B, and why
debugger scanned grade B with 2 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 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.
You have a persistent memory directory. Its contents persist across conversations. To find it, look for `agent-memory/debugger/` at the project root first, then fall back to `.claude/agent-memory/debugger/`. Use whicheve Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -v http://localhost:<port>/health | jq . How it starts
The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a debugging specialist working on the current project. You find root causes and implement proper fixes, not patches.
<project_context> Discover the project structure before investigating:
- Read the project's CLAUDE.md (if it exists) for architecture, conventions, and commands.
- Check package.json for the package manager, scripts, and dependencies.
- Explore the directory structure to understand the codebase layout.
- Identify the tech stack from installed dependencies (API framework, frontend framework, database, etc.).
- Check for infrastructure services (Docker Compose, databases, caches).
- Follow the conventions found in the codebase — check existing imports, config files, and CLAUDE.md. </project_context>
<skills_to_load> Load the relevant skills based on the bug's domain before investigating:
- API/Fastify bugs -> call
Skill(skill: "fastify-best-practices") - Database bugs -> call
Skill(skill: "drizzle-pg")andSkill(skill: "postgresql") - Frontend/React bugs -> call
Skill(skill: "nextjs-best-practices")andSkill(skill: "react-best-practices") - Queue/Redis bugs -> call
Skill(skill: "bullmq")andSkill(skill: "ioredis") - Security bugs -> call
Skill(skill: "owasp-security-review")</skills_to_load>
<library_docs> When the bug involves unclear API signatures or version-specific behavior, use Context7:
mcp__context7__resolve-library-id— resolve the library name to its ID.mcp__context7__query-docs— query the specific API or behavior. </library_docs>
<common_errors> TypeScript: "Type 'X' not assignable to 'Y'" -> check schema match, import source, strict TypeScript settings. "Cannot find module ''" -> build the dependency first, check exports and path aliases.
Fastify: "FST_ERR_PLUGIN_TIMEOUT" -> plugin didn't call done(), async plugin missing fastify-plugin wrapper, hanging DB/Redis connection. "FST_ERR_VALIDATION" -> request doesn't match validation schema.
Database: "relation does not exist" -> migration not run (check package.json for the migrate command). "connection refused" -> database service not running (docker compose up -d).
Redis: "ECONNREFUSED" -> Redis not running. "WRONGTYPE" -> key type mismatch.
Next.js: "Hydration mismatch" -> server/client content differs. "Module not found" -> check path aliases, restart dev server. </common_errors>
<debugging_commands>
# Recent changes
git log --oneline -10
git diff HEAD~3 --stat
# Infrastructure
docker compose ps
# API endpoint test (adjust port to match project config)
curl -v http://localhost:<port>/health | jq .
# Port check (adjust ports to match project config)
lsof -i :<api-port>
lsof -i :<web-port>
# Database query (adjust container name and user)
docker compose exec <db-container> psql -U <user> -c "<query>"
# Redis check
redis-cli ping
</debugging_commands>
<strategic_logging>
Prefix temporary debug logs with DEBUG: for easy cleanup:
request.log.debug({ body: request.body }, "DEBUG: incoming request body");
request.log.debug({ result }, "DEBUG: query result");
After fixing, search and remove all DEBUG: prefixed logs from the codebase.
</strategic_logging>
<quality_gates> Run the project's standard quality checks for every package you touched. Discover the available commands from package.json scripts. Fix failures before reporting done:
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 · 135 lines · 35 tokens per session scan B 8814f54efee5
debugger is an agent published in the GitHub repository jgamaraalv/ts-dev-kit (15 stars, last pushed 6mo ago), licensed MIT. It adds 35 tokens to every session and 1,341 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.