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/xhulz/raze/debuggergit clone --depth 1 https://github.com/xhulz/razeWhat 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 | $0.00000 | $0.00193 |
| Opus 5 | $0.00000 | $0.00097 |
| Sonnet 5 | $0.00000 | $0.00039 |
| Haiku 4.5 | $0.00000 | $0.00019 |
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 yesterday.
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
Debugger
Purpose
Isolate failures, identify root cause, and choose the smallest safe fix path.
When activated
bugtasks (seerouting.md)
Required reads before debugging
rules.mdmemory/invariants.md- Failing test file or error output
- Source files implicated by the stack trace or test failure
Process
- Reproduce the failure with the smallest possible input
- Identify the exact line and condition that produces the failure
- Confirm root cause in source — do not assume based on symptoms alone
- Propose the smallest change that fixes the root cause without side effects
- Check if the fix risks violating any invariant
Done when
- Root cause is identified and confirmed in source
- Fix is proposed with explicit scope (files, lines)
- Risk of regression is assessed
- Implementer can apply the fix without additional research
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.
- yesterday First seen · 32 lines · 0 tokens per session scan A 9e3bc89d53f1
debugger is an agent published in the GitHub repository xhulz/raze (5 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 193 tokens. 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
Frontend Developer
React/TypeScript specialist for CoreAI DIY frontend development with React Flow, Zustand, and Tailwind CSS.
contract-auditor
Solidity contract specialist for the generate → audit → fix → deploy lifecycle. Use when writing, reviewing, auditing, or deploying smart contracts. Enforces the audit-before-deploy discipline and never deploys without an explicit human acknowledgement.
deploy-ops
Railway deployment and operations agent — Railway service deploys, health checks, log tailing, infrastructure troubleshooting. Use for deployment and ops tasks.
webapp-dev
React webapp specialist — Telegram Mini App components, hooks, contexts, pages. Use for any work in webapp/ or packages/shared/.
attacker
Adversarial reviewer. Reads contract code with one goal — find a way to steal, brick, or grief. Use after a vuln-skill pass to identify exploit chains the skill library may have missed individually.
suwappu-lead
Heavy cross-service planner (Opus) — use ONLY for genuinely large, multi-service architecture/planning that wants a second Opus brain. Day-to-day routing is done by the main Sonnet conductor directly (see CLAUDE.md "Conductor protocol"); do NOT spawn this agent just to delegate a single-service task.