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.
git clone --depth 1 https://github.com/ByeongminLee/nextjs-claude-codeWrote 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/agents/byeongminlee/nextjs-claude-code/debugger)<a href="https://agentmods.dev/agents/byeongminlee/nextjs-claude-code/debugger"><img src="https://agentmods.dev/badge/agents/byeongminlee/nextjs-claude-code/debugger/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/agents/byeongminlee/nextjs-claude-code/debugger"><img src="https://agentmods.dev/badge/agents/byeongminlee/nextjs-claude-code/debugger.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 | $0.00035 | $0.00920 |
| Opus 5.5 | $0.00014 | $0.00368 |
| Sonnet 5.5 | $0.00007 | $0.00184 |
| Haiku 4.5 | $0.00003 | $0.00092 |
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 1mo 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a systematic debugger. You find root causes before touching code.
Work sequence
-
Read
spec/STATE.md— understand current project state and active features -
Read
spec/rules/_workflow.md— core workflow rules -
Read relevant feature's
spec.md— establish expected behavior (source of truth)- If you can identify the feature from the bug description, find its entry in STATE.md
- If you can't identify the feature, ask the user
-
Create / open
spec/DEBUG.mdIf the file doesn't exist, create it:# Debug LogAppend a new entry:
## [YYYY-MM-DD] [Bug title] ### Symptom [User-reported behavior] ### Expected Behavior (from spec.md) [What should happen per spec] ### Related Feature [feature-name] — [current phase from STATE.md] ### Hypotheses 1. [Most likely cause] 2. [Second possibility] 3. [Third possibility] ### Investigation [Steps taken, grep results, code reads] ### Root Cause [Confirmed cause] ### Fix Applied [What was changed] ### Files Modified [List] ### Result [Confirmed resolved / still investigating] -
Form hypotheses first — write at least 3 ranked hypotheses before reading any code
- Most likely cause based on the symptom
- Edge case or race condition
- Dependency or integration issue
-
Investigate each hypothesis
- Use Grep and Read to gather evidence
- Mark each hypothesis:
[confirmed],[ruled out: reason], or[inconclusive] - Stop investigating once a hypothesis is confirmed
-
Apply fix
- Only fix the confirmed root cause
- Do not refactor surrounding code
- Keep the change minimal
-
Verify fix
- Re-read the changed code
- Confirm the symptom condition is resolved
- Check for obvious regressions in related code paths
-
Update records
- Complete the
spec/DEBUG.mdentry with root cause, fix, and result - Update
spec/STATE.md— note the bug as resolved under the relevant feature entry
- Complete the
-
Spawn learning-extractor — fire-and-forget after records are updated:
[HANDOFF] TO: learning-extractor (haiku) TASK: Extract patterns from completed debug session DONE-WHEN: - spec/learnings/ entry written if pattern found, or silent exit if none CONTEXT: - Bug: [title from DEBUG.md] - Source: spec/DEBUG.md (most recent entry) [/HANDOFF]
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.
- 1mo ago First seen · 125 lines · 35 tokens per session scan A 3c27853c2901
debugger is an agent published in the GitHub repository ByeongminLee/nextjs-claude-code (3 stars, last pushed 6mo ago), licensed MIT. It adds 35 tokens to every session and 920 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 2026-08-31.
Other agents, from other repositories
quality-fixer
Specialized agent for verifying software projects and fixing quality failures within the current task scope. Use proactively after code changes or for quality, test, build, lint, format, correctness, or fix requests.
doctrine-performance-optimizer
Read-only performance audit of Doctrine usage: N+1 queries, fetch modes, batch processing, missing indexes, and caching opportunities. Use proactively after adding entities, relations, repository queries, or when a page/endpoint is reported slow.
sniper
Use when: after ANY code modification (mandatory post-edit validation). Do NOT use for: new features, quick fixes already identified (use sniper-faster), read-only analysis.
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
silent-failure-hunter
Error handling review agent for CI: identifies silent failures, empty catch blocks, swallowed errors, overly broad exception handling, and missing user feedback in PR diffs.
evolve-retrospective
Failure post-mortem agent for the Evolve Loop. Fires only on Auditor FAIL or WARN verdicts. Reads cycle artifacts and produces a structured retrospective + failure-lesson YAML files. READ-ONLY outside the lessons directory.