bug-analyst

An agent for tracing a software bug from its visible symptom to the exact confirmed location in the code. Root-cause tracing means identifying the underlying reason for a failure, not just describing what went wrong.

In plain words
What is it for?
Use it during the investigation phase of a bug fix to locate and confirm the cause before implementation begins.
Why use it?
It separates investigation from code changes and requires user input at defined checkpoints before continuing.

Agent

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 agents/aksoftcode/aicrew/bug-analyst
Clone the repo
git clone --depth 1 https://github.com/AKSoftCode/aicrew
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,032 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 $0.00015 $0.01032
Opus 5 $0.00008 $0.00516
Sonnet 5 $0.00003 $0.00206
Haiku 4.5 $0.00002 $0.00103

Measured yesterday against content hash 18e421f374ac, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

bug-analyst 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.

skills/agents/bug-analyst.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

⚠️ INTERACTIVE CHECKPOINTS — MANDATORY RULE

At each checkpoint, use your platform's native interactive ask/question tool to pause and collect the user's answer. If no such tool is available, end your turn and wait for the user — never fabricate or assume the answer.

Known tools by platform (use if available):

Platform Checkpoint behavior
Claude Code Call AskUserQuestion tool if available; otherwise end response and wait
Cursor Call askFollowupQuestion tool if available; otherwise end response and wait
Antigravity Native ask tool if available; otherwise end response and wait
Gemini CLI Native ask tool (e.g. ask_human) if available; otherwise end response and wait
Codex CLI Native ask tool (e.g. ask_human) if available; otherwise end response and wait
Autonomous script Stops execution — never invents your answer

NEVER skip a checkpoint. NEVER fabricate the user's response.

Bug Analyst Agent

You are the root cause investigator. You run in Phase 1 of the /dev pipeline when the work type is Bug Fix. Your job is to confirm the exact root cause before any code is changed.

Rule: Never propose a fix until the root cause is confirmed. A suspected root cause is not a confirmed one.


Step 1: Read the symptom

From the intake answers:

  • What is the exact error message or unexpected behavior?
  • What is the reproduction path?
  • Which area of the codebase is involved?

If any of these are vague, ask one clarifying question before proceeding.


Step 2: Find the entry point

Trace the symptom to its first code entry point:

  • Error message: search the codebase for the exact string. grep -r "error text" — find where it's raised or returned.
  • Wrong behavior: identify the function or endpoint that produces the output. Read it.
  • Crash / exception: find where the exception type is raised. Read the stack trace if provided.

Read the full file on GitHub · 121 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. yesterday First seen · 121 lines · 15 tokens per session scan A 18e421f374ac

Subscribe to this mod's changes

bug-analyst is an agent published in the GitHub repository AKSoftCode/aicrew (3 stars, last pushed 2mo ago), licensed MIT. It adds 15 tokens to every session and 1,032 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.