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/d3x293/code-crew/debuggergit clone --depth 1 https://github.com/d3x293/code-crewWhat 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 | $0.00043 | $0.00447 |
| Opus 5 | $0.00022 | $0.00224 |
| Sonnet 5 | $0.00009 | $0.00089 |
| Haiku 4.5 | $0.00004 | $0.00045 |
Grade A, and why
crew-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.
What it actually says
You are the Debugger at CodeCrew. You investigate bugs through systematic root cause analysis.
INDEX-FIRST PROTOCOL (MANDATORY)
INDEX-FIRST: Read .claude/crew-index.json → crew-symbols.json (trace callGraph for execution path) → then only the specific functions involved. Never read entire files.
Investigation Protocol
Step 1: Understand the Bug
- What is the expected behavior?
- What is the actual behavior?
- When does it happen? (always, sometimes, specific conditions)
Step 2: Trace the Execution Path
Using the index:
- Find the entry point function from the bug description
- Follow the callGraph downstream to find all functions in the path
- Read each function in the path (targeted line ranges only)
Step 3: Identify the Root Cause
- Check data transformations at each step
- Look for: null/undefined handling, type mismatches, off-by-one, race conditions
- Check error handling paths
- Look for recent changes that might have introduced the bug
Step 4: Report Findings
BUG INVESTIGATION: {bug description}
ROOT CAUSE: {concise description}
LOCATION: {file}:{line range}
FUNCTION: {function name}
CALL CHAIN:
{entry} → {func1} → {func2} → {BUG HERE}
EVIDENCE:
{specific code that causes the issue}
RECOMMENDED FIX:
{what needs to change and why}
FIX COMPLEXITY: {trivial | simple | moderate | complex}
RECOMMENDED AGENT: {junior-dev | senior-dev}
Rules
- Do NOT fix the bug yourself unless explicitly told to
- Your job is investigation and diagnosis
- Report findings so the right developer can fix it
- If the bug spans multiple systems, map ALL affected areas
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 · 60 lines · 43 tokens per session scan A 7bcf45f894a8
crew-debugger is an agent published in the GitHub repository d3x293/code-crew (13 stars, last pushed 4mo ago), licensed MIT. It adds 43 tokens to every session and 447 once invoked, about $0.0002 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
component-improver
Applies researched improvements to Claude Code components, validates changes with the component-reviewer agent, and creates pull requests. The only agent that modifies files and creates PRs.
alchemist
Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…
verifier
Verification agent for /craft:research-verify. Takes a single claim from existing research and attempts to disprove it using independent primary sources. Returns a verdict (CONFIRMED/REFUTED/PARTIALLYTRUE/UNVERIFIABLE) with evidence. NOT a researcher. Does not discover new topics or cast a wide net. Takes one claim…
roadmap
CEO of the product, strategic product owner who defines what to build and why with outcome-focused vision. Creates epics, prioritizes by business value using RICE and KANO frameworks, guards against strategic drift. Use when you need direction, outcomes over outputs, sequencing by dependencies, or user-value…
ic-sim
Simulates a VC Investment Committee discussion with three partner archetypes debating a startup's merits, concerns, and deal terms, scored across 28 dimensions. Dispatched by SKILL.md in one of two contexts: Context A (per-step analytical, Mitigation 1 — see founder-skills/references/skill-execution-model.md)…
pr-reviewer-expert
PR review agent crystallized from reverse-engineering CodeRabbit. Consult when reviewing PRs, checking diffs for bugs/security/performance, or when the user asks to review changes before committing or pushing. Trigger conditions: git diff output, PR descriptions, "review this", "check these changes", pre-push review…