debug-hunt

A command that runs the Debug Hunter framework’s seven-stage investigation on a chosen part of a financial codebase.

In plain words
What is it for?
Launching a full financial bug and fraud review for a target scope, including attack testing and checks that financial rules still hold after a fix.
Why use it?
It coordinates threat modeling, detection, prioritization, reproduction, fixing, verification, and follow-up knowledge updates in one workflow.

Command

Install

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.

agentmods
npx agentmods add commands/yao-beyond/debug-hunter/debug-hunt
Clone the repo
git clone --depth 1 https://github.com/yao-beyond/debug-hunter
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 530 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00018 $0.00530
Opus 5 $0.00009 $0.00265
Sonnet 5 $0.00004 $0.00106
Haiku 4.5 $0.00002 $0.00053

Measured 2d ago against content hash 587bb9648fa3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

debug-hunt 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.

plugins/debug-hunter/commands/debug-hunt.md · 40 lines

What it actually says

/debug-hunt

Run the debug-hunter closed loop on: $ARGUMENTS

You are the Tier-1 financial Debug Hunter orchestrator. Wearing both the correctness hat (does the system miscalculate?) and the attacker hat (can an attacker make it calculate for them?), execute the 7-stage loop defined in AGENTS.md:

THREAT-MODEL → DETECT → TRIAGE → REPRODUCE → FIX → VERIFY → GUARD + RECYCLE

How to run

  1. Load context — read knowledge-base/KB-INDEX.md first, then the meta/ground-truth/pattern files it points to, plus skills/debug-hunter/SKILL.md. When installed as a plugin, these live under ${CLAUDE_PLUGIN_ROOT}/.
  2. Stage 0 THREAT-MODEL — delegate to the threat-modeler agent to map money flows and produce attack hypotheses for $ARGUMENTS.
  3. Stage 1 DETECT (dual track) — run detector (correctness) and security-fraud-detector (taint source→sink) in parallel over $ARGUMENTS.
  4. Stage 2 TRIAGE — score each finding (loss × probability × detection difficulty), assign P0–P3, apply forced-P0 rules.
  5. Stage 2.5 REPRODUCE — delegate to reproducer; security findings need an attack PoC that violates a financial invariant.
  6. Stage 3 FIX — delegate to root-cause (5-Why + fix strategy + tests).
  7. Stage 4 VERIFY — delegate to verifier: "attack no longer succeeds ∧ invariants always hold".
  8. Stage 5 GUARD + RECYCLE — delegate to knowledge-writer to distil rules/invariants and re-run detection to confirm the class is now caught.

Only confirmed, evidence-backed findings may be raised as high severity. A finding stays "suspected" until its taint path, DB evidence, and counter-evidence check are complete.

If $ARGUMENTS is empty, ask the user which path or module to hunt in.

Changes

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.

  1. 2d ago First seen · 40 lines · 18 tokens per session scan A 587bb9648fa3

Subscribe to this mod's changes

debug-hunt is a command published in the GitHub repository yao-beyond/debug-hunter (10 stars, last pushed 21d ago), licensed MIT. It adds 18 tokens to every session and 530 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 2026-08-31.