analyze-bug

analyze-bug is a skill for Claude Code, Codex from asysta-act/agent-flow. It costs 22 tokens per session (694 once invoked), scanned A, original, MIT.

A bug-analysis workflow that reads a specific issue from a configured issue tracker and investigates it without changing code.

In plain words
What is it for?
Use it to review an issue's description and comments, identify the likely problem, and produce a triage analysis through the configured workflow.
Why use it?
It creates a structured diagnosis while checking that the issue-tracker connection and project automation settings are available.

Skill for Claude CodeCodex

Part of the agent-flow plugin — 17 skills, 17 agents 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 skills/asysta-act/agent-flow/analyze-bug
Any agent
npx skills add asysta-act/agent-flow --skill analyze-bug
Clone the repo
git clone --depth 1 https://github.com/asysta-act/agent-flow

Made for: Claude Code, Codex.

Or install agent-flow, the plugin that ships this one along with the rest of its 17 skills, 17 agents.

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 analyze-bug

README.md
[![agentmods](https://agentmods.dev/badge/skills/asysta-act/agent-flow/analyze-bug.svg)](https://agentmods.dev/skills/asysta-act/agent-flow/analyze-bug)
Your own site
<a href="https://agentmods.dev/skills/asysta-act/agent-flow/analyze-bug"><img src="https://agentmods.dev/badge/skills/asysta-act/agent-flow/analyze-bug.svg" alt="Measured on agentmods" height="20"></a>
Per session 22 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 694 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 $0.00022 $0.00694
Opus 5 $0.00011 $0.00347
Sonnet 5 $0.00004 $0.00139
Haiku 4.5 $0.00002 $0.00069

Measured 4d ago against content hash 924a19ee49d3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

analyze-bug 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.

skills/analyze-bug/SKILL.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Analyze Bug

Analyze bug $ARGUMENTS. Read Automation Config from CLAUDE.md.

0. MCP pre-flight check

Before any pipeline operation, verify MCP tool availability:

  • Read Type from Automation Config (Issue Tracker section)
  • Check that at least one mcp__* tool matching the tracker type is accessible
  • If not accessible → STOP with: "Cannot connect to your {Type} issue tracker. Is the {Type} integration configured? Run /agent-flow:check-setup for diagnostics."

Steps

  1. If $ARGUMENTS is empty, display: "Usage: /agent-flow:analyze-bug " and stop.
  2. Verify that CLAUDE.md exists and contains an ## Automation Config section with Issue Tracker. If not, report an error and stop.
  3. Read issue content (title, description, comments) from the issue tracker via MCP. When passing this content to any agent, follow ../../core/external-input-sanitizer.md: wrap each piece of external content in --- EXTERNAL INPUT START --- / --- EXTERNAL INPUT END --- markers. Before dispatch, check Agent Overrides: follow ../../core/agent-override-injector.md for analyst overrides. Run agent-flow:analyst --phase triage on bug $ARGUMENTS After successful triage, instruct the agent to post a checkpoint comment to the issue tracker: [agent-flow] Triage completed. Severity: {severity}. Area: {area}. 3a. If triage output contains ## NEEDS_CLARIFICATION (interactive surface — no state.json, no pipeline pause):
    • Extract the question: line and the optional context: line from the triage output.
    • Display to the user:
      [agent-flow] Triage needs clarification before analysis can proceed.
      
      Question: {question text}
      Context:  {context text, if present}
      
      Please provide the answer and re-run /agent-flow:analyze-bug with the additional information in the issue description, or answer interactively.
      
    • Stop. Do NOT proceed to analyst impact. 3b. If triage output contains Quality gate: UNCLEAR:
    • Post a block comment to the issue tracker using the Block Comment Template:
      [agent-flow] 🔴 Pipeline Block
      Agent: analyst
      Step: triage
      Reason: Issue is unclear — analyst returned Quality gate: UNCLEAR.
      Detail: {analyst output explaining what is missing}
      Recommendation: {analyst recommendation for what the reporter should clarify}
      
    • Display the block result to the user and stop. Do NOT proceed to analyst impact.
  4. If triage OK, before dispatch, check Agent Overrides: follow ../../core/agent-override-injector.md for analyst overrides, then run agent-flow:analyst --phase impact
  5. Display results (triage + impact report)

Read the full file on GitHub · 54 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. 4d ago First seen · 54 lines · 22 tokens per session scan A 924a19ee49d3

Subscribe to this mod's changes

analyze-bug is a skill published in the GitHub repository asysta-act/agent-flow (12 stars, last pushed 1mo ago), licensed MIT. It adds 22 tokens to every session and 694 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 2026-08-30.

Related

Other skills, from other repositories

log

Capture front door. Logs 1..N observations as card files at docs/work/{ID}.md (BUG / DEBT / GAP), gateway-inline — no dispatch. Use when the user says "log this", "track that", "note this down", or types /super-bootstrap:log — and when Claude needs to file its own findings (out-of-scope findings from a review, audit…

RockyHong/super-bootstrap · 164 tokens

triage

Read-only grounding phase for a card — every card's pickup. /super-bootstrap:triage {ID} dispatches the triage subagent (Opus) to ground the card cold — premise verify, aim validate, blast collect — and append a Verdict block — ## Verdict — auto-fix · {date} (Fix-shape / Probe-deps / Execution tags) or ## Verdict …

RockyHong/super-bootstrap · 159 tokens

drain

Parallel-worktree auto-drain of the board. One /super-bootstrap:drain turn = scan the pipeline sources (specs/plans/backlog, plus the scale module's test queue when present) → keep only admissible items → relation-analyze into a conflict-free wave → confirm with the user → spawn one isolated git worktree + headless…

RockyHong/super-bootstrap · 200 tokens

geo-prospect

CRM-lite for managing GEO agency prospects and clients. Track leads through the full sales pipeline: Lead → Qualified → Proposal Sent → Won → Lost. Store audit history, notes, deal values, and generate pipeline summaries. Use when user says "prospect", "lead", "client", "pipeline", "crm", "nuovo prospect", "aggiungi…

techhorizonlabs/thl-open · 87 tokens

client-relationship-manager

Lightweight AI-native CRM for solopreneurs and freelancers. Track clients, relationships, follow-ups, deal stages, and interaction history in plain text files — no SaaS subscription required. Use when managing client relationships, preparing for meetings, tracking follow-ups, or reviewing pipeline status.

theagentledger/agent-skills · 62 tokens

content-calendar

Plan, schedule, and track content across channels — newsletters, social media, blog posts, and videos. Manages pipeline stages, publishing cadence, and repurposing opportunities. For solopreneurs and creators who want a system, not a spreadsheet.

theagentledger/agent-skills · 54 tokens