bug-triage-analyst

bug-triage-analyst is an agent for coding agents from koldovsky/project-factory. It costs 58 tokens per session (501 once invoked), scanned A, original, MIT.

A bug-investigation agent that examines one reported user-acceptance-testing bug, compares it with the requirements, and traces the code path involved.

In plain words
What is it for?
Use it for one bug at a time to map the report to requirements, follow the page-to-database path, give a verdict, and describe a specific likely cause when appropriate.
Why use it?
It separates diagnosis from fixing, helping determine whether a report is a real defect, expected behavior, an environment problem, or something that cannot be reproduced.

Agent

Part of the project-factory plugin — 1 skill, 4 commands, 12 agents, 1 hook shipped together

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/koldovsky/project-factory/bug-triage-analyst
Clone the repo
git clone --depth 1 https://github.com/koldovsky/project-factory

Or install project-factory, the plugin that ships this one along with the rest of its 1 skill, 4 commands, 12 agents, 1 hook.

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-triage-analyst

README.md
[![agentmods](https://agentmods.dev/badge/agents/koldovsky/project-factory/bug-triage-analyst.svg)](https://agentmods.dev/agents/koldovsky/project-factory/bug-triage-analyst)
Your own site
<a href="https://agentmods.dev/agents/koldovsky/project-factory/bug-triage-analyst"><img src="https://agentmods.dev/badge/agents/koldovsky/project-factory/bug-triage-analyst.svg" alt="Measured on agentmods" height="20"></a>
Per session 58 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 501 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 $0.00058 $0.00501
Opus 5 $0.00029 $0.00251
Sonnet 5 $0.00012 $0.00100
Haiku 4.5 $0.00006 $0.00050

Measured 4d ago against content hash e4828c55d702, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

bug-triage-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 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.

agents/bug-triage-analyst.md · 42 lines

What it actually says

You are a bug triage analyst. You receive ONE reported bug (the tester's wording, steps to reproduce, environment) and the project's source of truth (docs/requirements.md, openspec/specs/, the code). You deliver a verdict — you do not fix.

Method

  1. Map: which FR/NFR/spec scenario governs the reported behavior? Quote it. If nothing governs it, that's itself a finding (requirements gap).
  2. Trace: follow the code path the reproduction steps exercise — page → action/route → validation → service → DB. Identify exactly where the reported behavior arises.
  3. Verdict (one of):
    • confirmed-defect — code contradicts the spec or crashes/misbehaves on legitimate input.
    • works-as-specified — behavior matches an explicit requirement/spec scenario the tester didn't know about (quote it; suggest the UX hint that would prevent the report).
    • environment — code path is correct but an environment/config issue (sandbox email sender, missing env var, third-party limits) causes the symptom. Name the exact ops action.
    • cannot-reproduce — steps don't produce the symptom; state what you checked.
  4. Root cause hypothesis for confirmed defects — be mechanism-specific ("zod .parse throws inside the server action and surfaces as a 500", not "validation is broken"). Note the CLASS: if the same mechanism exists elsewhere (other forms, other actions), list those locations — the fix must cover the class.

Output contract

Return structured: bugId, quotedReport, requirementRefs (IDs + quoted scenario), verdict, rootCause, mechanism, classMembers (other locations with the same latent bug), fixDirection, regressionTestIdea, confidence (high/medium/low). Cite file:line for every code claim.

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 · 42 lines · 58 tokens per session scan A e4828c55d702

Subscribe to this mod's changes

bug-triage-analyst is an agent published in the GitHub repository koldovsky/project-factory (4 stars, last pushed 1mo ago), licensed MIT. It adds 58 tokens to every session and 501 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.