Archon: Command for Claude Code

.github/prompts/investigate-debug.prompt.md

investigate-debug is a command for Claude Code, GitHub Copilot from coleam00/Archon. It costs 20 tokens per session (3,106 once invoked), scanned A, original, MIT.

Investigate a GitHub issue or problem - analyze codebase, create plan, post to GitHub.

Command for Claude CodeGitHub Copilot

Written for Claude Code and GitHub Copilot: argument-hint in frontmatter, but also a Copilot chat mode or prompt. Also seen: agent in frontmatter; mentions subagents.

This is coleam00/Archon's own configuration. It tells Claude Code and GitHub Copilot how to work on Archon itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Archon configures →

About the project

Archon is a workflow engine for AI coding agents that turns development processes into YAML-defined sequences with phases, validation gates, and artifacts. Developers use it to run repeatable processes such as planning, implementation, testing, code review, and pull-request creation across projects. The catalogue entries provide commands, agents, skills, hooks, instructions, and settings for working with Archon.

coleam00/Archon · 23,398 stars · on GitHub · archon.diy

Reuse

Borrowing it

Nothing to install: this file belongs to coleam00/Archon. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/coleam00/Archon/dev/.github/prompts/investigate-debug.prompt.md
Clone the repo
git clone --depth 1 https://github.com/coleam00/Archon

Made for: Claude Code, GitHub Copilot.

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 investigate-debug

README.md
[![agentmods](https://agentmods.dev/badge/commands/coleam00/archon/investigate-debug/github.svg)](https://agentmods.dev/commands/coleam00/archon/investigate-debug)
Your own site
<a href="https://agentmods.dev/commands/coleam00/archon/investigate-debug"><img src="https://agentmods.dev/badge/commands/coleam00/archon/investigate-debug/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for investigate-debug

Your own site · 80×15
<a href="https://agentmods.dev/commands/coleam00/archon/investigate-debug"><img src="https://agentmods.dev/badge/commands/coleam00/archon/investigate-debug.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,106 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin unknown 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 5.1 $0.00020 $0.03106
Opus 5 $0.00010 $0.01553
Sonnet 5 $0.00004 $0.00621
Haiku 4.5 $0.00002 $0.00311

Measured today against content hash 25a93d26ce9e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

investigate-debug 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 today.

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.

.github/prompts/investigate-debug.prompt.md · 529 lines

How it starts

The opening of the file, as written. The whole thing — 529 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Investigate Issue

Input: ${input:issue:GitHub issue number, URL, or problem description}


Your Mission

Investigate the issue/problem and produce a comprehensive implementation plan that:

  1. Can be executed by /implement-fix
  2. Is posted as a GitHub comment (if GH issue provided)
  3. Captures all context needed for one-pass implementation

Golden Rule: The artifact you produce IS the specification. The implementing agent should be able to work from it without asking questions.


Phase 1: PARSE - Understand Input

1.1 Determine Input Type

Input Example Action
Issue number 123, #123 Fetch with gh issue view
URL github.com/.../issues/123 Extract number, fetch
Free-form text anything else Use as problem description
Blank (none) Use conversation context

If GitHub issue:

gh issue view {number} --json title,body,labels,comments,state,url,author

1.2 Extract Context

If GitHub issue:

  • Title: What's the reported problem?
  • Body: Details, reproduction steps, expected vs actual
  • Labels: bug? enhancement? documentation?
  • Comments: Additional context from discussion
  • State: Is it still open?

If free-form:

  • Parse as problem description
  • Note: No GitHub posting (artifact only)

1.3 Classify Issue Type

Type Indicators
BUG "broken", "error", "crash", "doesn't work", stack trace
ENHANCEMENT "add", "support", "feature", "would be nice"
REFACTOR "clean up", "improve", "simplify", "reorganize"
CHORE "update", "upgrade", "maintenance", "dependency"
DOCUMENTATION "docs", "readme", "clarify", "example"

1.4 Assess Severity/Priority, Complexity, and Confidence

Each assessment requires a one-sentence reasoning based on concrete findings.

For BUG issues - Severity:

Severity Criteria
CRITICAL System down, data loss, security vulnerability, no workaround
HIGH Major feature broken, significant user impact, difficult workaround
MEDIUM Feature partially broken, moderate impact, workaround exists
LOW Minor issue, cosmetic, edge case, easy workaround

Read the full file on GitHub · 529 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. today First seen · 529 lines · 20 tokens per session scan A 25a93d26ce9e

Subscribe to this mod's changes

investigate-debug is a command published in the GitHub repository coleam00/Archon (23,398 stars, last pushed today), licensed MIT. It adds 20 tokens to every session and 3,106 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 2026-09-08.