bug-hunters

bug-hunters is a skill for Claude Code, Codex from DeevsDeevs/agent-system. It costs 74 tokens per session (327 once invoked), scanned A, original, Apache-2.0.

A structured bug investigation process that reconstructs expected behavior and tests software against difficult cases. It reports likely bugs without fixing them.

In plain words
What is it for?
Use it for logic investigations, code-focused hunts, and reviews of C++ or Python code where you need confidence-scored bug findings.
Why use it?
It helps separate real correctness problems from misunderstandings by checking the specification, logic, and language-specific failure modes.

Skill for Claude CodeCodex

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 skills/deevsdeevs/agent-system/bug-hunters
Any agent
npx skills add DeevsDeevs/agent-system --skill bug-hunters
Clone the repo
git clone --depth 1 https://github.com/DeevsDeevs/agent-system

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for bug-hunters

README.md
[![agentmods](https://agentmods.dev/badge/skills/deevsdeevs/agent-system/bug-hunters.svg)](https://agentmods.dev/skills/deevsdeevs/agent-system/bug-hunters)
Your own site
<a href="https://agentmods.dev/skills/deevsdeevs/agent-system/bug-hunters"><img src="https://agentmods.dev/badge/skills/deevsdeevs/agent-system/bug-hunters.svg" alt="Measured on agentmods" height="20"></a>
Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 327 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 $0.00074 $0.00327
Opus 5 $0.00037 $0.00163
Sonnet 5 $0.00015 $0.00065
Haiku 4.5 $0.00007 $0.00033

Measured 4d ago against content hash dd2e4963c966, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

bug-hunters 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 4d 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.

bug-hunters/SKILL.md · 28 lines

What it actually says

Bug Hunters

Use a single skill with role selection. If the user specifies a hunter, use that role; otherwise start with the orchestrator and ask which mode applies.

Role Map

  • orchestratoragents/orchestrator.md
  • logic-hunteragents/logic-hunter.md
  • cpp-hunteragents/cpp-hunter.md
  • python-hunteragents/python-hunter.md

Workflow

  1. Read README.md and follow the “hunt, don’t fix” rule.
  2. Spawn a child agent with agent_type equal to the selected role (orchestrator, logic-hunter, cpp-hunter, python-hunter).
  3. If no role is specified, default to orchestrator.
  4. Choose mode:
    • Logic-first when the problem is algorithm/spec correctness.
    • Code-first when the problem is language-specific failures or UB.
  5. Pass mode and scope in the spawn message, then use wait for completion.
  6. Use adversarial validation and only report MEDIUM+ confidence findings.
  7. Present a bug report, not remediation.
Files

What ships with it

6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 4d ago First seen · 28 lines · 74 tokens per session scan A dd2e4963c966

Subscribe to this mod's changes

bug-hunters is a skill published in the GitHub repository DeevsDeevs/agent-system (40 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 74 tokens to every session and 327 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

plannotator-annotate

Open Plannotator's annotation UI for a file, folder, or URL, then address the returned annotations.

backnotprop/plannotator · 29 tokens

statistical-power

Sample-size and statistical power calculations for planning studies. Use whenever someone asks "how many subjects/samples/replicates do I need", wants an a priori power analysis, a minimum detectable effect (MDE), a power curve, or needs to justify a sample size for a grant, IRB protocol, or pre-registration. Covers…

xintaofei/codeg · 190 tokens

review-work

Post-implementation review orchestrator. Launches 5 parallel background sub-agents: Oracle (goal/constraint verification), Oracle (code quality), Oracle (security), unspecified-high (hands-on QA execution), unspecified-high (context mining from GitHub/git/Slack/Notion). All must pass for review to pass. MUST USE…

code-yeongyu/oh-my-openagent · 125 tokens

southwest

Search Southwest Airlines fares and points pricing via Patchright browser automation. SW is not in any GDS or API. Covers all fare classes, Companion Pass value, and fare drop monitoring.

borski/travel-hacking-toolkit · 40 tokens

chase-travel

Search Chase UR travel portal via Patchright for cash prices, points pricing, Points Boost offers, and Chase Edit hotel benefits. Use for pay-with-points portal comparison on Sapphire Reserve/Preferred.

borski/travel-hacking-toolkit · 44 tokens

remove-deadcode

Remove unused code from this project with ultrawork mode, LSP-verified safety, atomic commits. Triggers: remove dead code, dead code, cleanup, remove unused.

code-yeongyu/oh-my-openagent · 41 tokens