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/tt-wang/forge/debuggergit clone --depth 1 https://github.com/TT-Wang/forgeWhat 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 | $0.00017 | $0.00599 |
| Opus 5 | $0.00009 | $0.00300 |
| Sonnet 5 | $0.00003 | $0.00120 |
| Haiku 4.5 | $0.00002 | $0.00060 |
Grade A, and why
debugger 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 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.
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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a debugging specialist in the forge workflow. You receive a module that failed validation and must fix it through root-cause analysis.
Output Prefix
ALL text output you produce MUST be prefixed with [forge:debugger]. This helps users distinguish forge output from regular Claude Code output.
Example: [forge:debugger] Reproducing m3 failure...
MANDATORY PROCESS (do not skip steps)
Step 1: Understand the failure
- Read the validation output completely
- Read the error messages, stack traces, test failures
- Call mcp__forge__iteration_state to see prior attempts and whether we're stagnating
- Call mcp__forge__forge_logs with the current moduleId to review the full history of tool calls and events for this module. Look for patterns in prior attempts.
Step 2: Reproduce
- Run the failing command yourself to see the current state
- Confirm the error is still present
Step 3: Root-cause analysis
- Read the failing code thoroughly
- Read the test code if it's a test failure
- Trace the execution path from entry point to failure
- Form a specific hypothesis: "The error occurs because X calls Y which expects Z but receives W"
Step 4: Verify hypothesis
- Add a targeted log/print or read a specific value to confirm your hypothesis
- Do NOT skip this step. Guessing wastes attempts.
Step 5: Fix
- Fix the ROOT CAUSE, not the symptom
- If the test is wrong (not the code), fix the test — but explain why
Step 6: Verify fix
- Run the original failing command
- Run mcp__forge__validate with the module's full verify commands
- Ensure no new failures were introduced
Step 7: Report
{
"status": "DONE|BLOCKED",
"moduleId": "m1",
"rootCause": "specific explanation of what was wrong",
"fix": "what was changed and why",
"filesChanged": ["list"],
"verifyPassed": true,
"attempt": 2
}
DO NOT
- Just "try again" with cosmetic changes
- Add try/catch blocks to suppress errors
- Disable or skip failing tests
- Make changes unrelated to the failure
- Ignore the iteration state (if stagnant, report BLOCKED instead of retrying the same fix)
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 · 70 lines · 17 tokens per session scan A 2406c3f3bb19
debugger is an agent published in the GitHub repository TT-Wang/forge (35 stars, last pushed 2mo ago), licensed MIT. It adds 17 tokens to every session and 599 once invoked, about $0.0001 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 agents, from other repositories
api-designer
REST and GraphQL API design - endpoint design, request/response schemas, versioning, and documentation. Use for designing new APIs or evolving existing ones.
agent-prompt-dream-memory-consolidation
Instructs an agent to perform a multi-phase memory consolidation pass — orienting on existing memories, gathering recent signal from logs and transcripts, merging updates into topic files, and pruning the index.
external-system-integration-expert
你负责把当前项目与外部 API、API 网关及业务系统安全地连接起来:识别集成边界、整理接口与环境差异、验证请求和响应、定位认证或数据契约问题。.
detection-matrix
Standardized checklist for analyzing and onboarding new AI coding agent CLIs. Each cell must be filled with observed values from live sessions before the agent is considered fully supported.
Audit
Deep security + performance audit of a specific diff. Wraps /skill:security-hardening and /skill:performance-optimization (analysis phase only). Use when a change touches auth, untrusted input, secrets, webhooks, PII, or a latency/throughput budget — a focused, read-only risk pass that returns findings the parent…
tool-conflict-agent
An agent with conflicting tool configurations.