audit-bugs

audit-bugs is a skill for Claude Code, Codex from TalonT-Org/AutoSkillit. It costs 62 tokens per session (1,171 once invoked), scanned A, original, MIT.

A report generator that studies past Claude Code investigations to find recurring bug patterns. It looks for repeated causes, missing architectural protections, and ways to detect similar problems earlier.

In plain words
What is it for?
Use it to review investigations since a chosen date, identify recurring root causes, find architectural gaps, and suggest proactive checks for future bugs.
Why use it?
It helps turn scattered debugging history into lessons about weaknesses that may affect the whole project. The analysis does not modify source code.

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/talont-org/autoskillit/audit-bugs
Any agent
npx skills add TalonT-Org/AutoSkillit --skill audit-bugs
Clone the repo
git clone --depth 1 https://github.com/TalonT-Org/AutoSkillit

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 audit-bugs

README.md
[![agentmods](https://agentmods.dev/badge/skills/talont-org/autoskillit/audit-bugs.svg)](https://agentmods.dev/skills/talont-org/autoskillit/audit-bugs)
Your own site
<a href="https://agentmods.dev/skills/talont-org/autoskillit/audit-bugs"><img src="https://agentmods.dev/badge/skills/talont-org/autoskillit/audit-bugs.svg" alt="Measured on agentmods" height="20"></a>
Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,171 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 $0.00062 $0.01171
Opus 5 $0.00031 $0.00585
Sonnet 5 $0.00012 $0.00234
Haiku 4.5 $0.00006 $0.00117

Measured 5d ago against content hash bd6fc64c6a84, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

audit-bugs 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 5d 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.

.claude/skills/audit-bugs/SKILL.md · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Bug Pattern Audit Skill

Mine Claude Code conversation logs for /investigate skill invocations to identify recurring bug patterns, architectural gaps, and proactive detection strategies.

When to Use

  • User says "audit bugs", "bug patterns", "analyze investigations", or "bug audit"
  • User wants to find recurring themes across past bug investigations
  • User wants proactive strategies to catch bugs before they manifest

Arguments

The user may provide a "since" date (e.g., 2/7, 2026-02-07, last week). If not specified, use AskUserQuestion to ask what the earliest lookback date should be before proceeding.

Critical Constraints

NEVER:

  • Modify any source code files
  • Create files outside temp/audit-bugs/ directory

ALWAYS:

  • Use subagents heavily for parallel log analysis
  • All output goes under temp/audit-bugs/ (create if needed)
  • Final report: temp/audit-bugs/bug_pattern_audit_{YYYY-MM-DD_HHMMSS}.md
  • Subagents must NOT create their own files - they return findings in their response text only
  • Do not change any code

Workflow

Step 1: Locate Project Logs

Claude Code stores conversation logs at ~/.claude/projects/ in a folder derived from the project's absolute path with / replaced by -.

Derive the log directory:

# Convert current working directory to Claude's folder naming scheme
PROJECT_PATH=$(pwd)
LOG_DIR="$HOME/.claude/projects/-${PROJECT_PATH//\//-}"
# Remove leading double dash if present
LOG_DIR="${LOG_DIR//--/-}"

Verify the directory exists and contains .jsonl files.

Step 2: Filter by Date and Investigate Skill

  1. Use find with -newermt to filter .jsonl files modified since the target date
  2. From those, grep -l '"skill".*"investigate"' to find files where the investigate skill was invoked (tool invocation pattern)
  3. Also grep -l '/investigate' to catch user-typed invocations
  4. Combine and deduplicate. Only use top-level files (not subagent logs under */subagents/)

Step 3: Dispatch Subagents for Parallel Analysis

Read the full file on GitHub · 136 lines

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. 5d ago First seen · 136 lines · 62 tokens per session scan A bd6fc64c6a84

Subscribe to this mod's changes

audit-bugs is a skill published in the GitHub repository TalonT-Org/AutoSkillit (5 stars, last pushed 6d ago), licensed MIT. It adds 62 tokens to every session and 1,171 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens