forensics

forensics is a command for Claude Code from spideynolove/claude-dotfiles. It costs 14 tokens per session (466 once invoked), scanned A, original, MIT.

A read-only investigation command for finding why a coding workflow became stuck or failed. It examines project history, unfinished changes, worktrees, and planning records.

In plain words
What is it for?
Use it after a plan stops progressing, an execution fails silently, costs appear unusual, or you need a post-mortem of recent development work.
Why use it?
It gathers the evidence needed to distinguish repeated failed work, missing completion records, abandoned changes, and other workflow problems without modifying project files.

Command for Claude Code

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 commands/spideynolove/claude-dotfiles/forensics
Clone the repo
git clone --depth 1 https://github.com/spideynolove/claude-dotfiles

Made for: Claude Code.

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 forensics

README.md
[![agentmods](https://agentmods.dev/badge/commands/spideynolove/claude-dotfiles/forensics.svg)](https://agentmods.dev/commands/spideynolove/claude-dotfiles/forensics)
Your own site
<a href="https://agentmods.dev/commands/spideynolove/claude-dotfiles/forensics"><img src="https://agentmods.dev/badge/commands/spideynolove/claude-dotfiles/forensics.svg" alt="Measured on agentmods" height="20"></a>
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 466 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 $0.00014 $0.00466
Opus 5 $0.00007 $0.00233
Sonnet 5 $0.00003 $0.00093
Haiku 4.5 $0.00001 $0.00047

Measured 4d ago against content hash c1e489f9b91e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

forensics 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.

.claude-global-backup/commands/forensics.md · 69 lines

What it actually says

/forensics — Workflow Post-Mortem

Post-mortem investigation for stuck or failed workflows. Read-only — never modifies project files.

Step 1: Get Problem Description

If $ARGUMENTS is empty, ask: "What went wrong? e.g., 'got stuck on phase 3', 'plan execute failed silently', 'costs seem high'."

Step 2: Gather Evidence

# Commit timeline and frequency
git log --oneline -30
git log --format="%H %ai %s" -30

# Most-edited files (stuck-loop signal)
git log --name-only --format="" -20 | sort | uniq -c | sort -rn | head -20

# Uncommitted work (crash/interruption signal)
git status --short && git diff --stat

# Orphaned worktrees
git worktree list

Also read if they exist:

  • .planning/STATE.md — current position, blockers, last session
  • .planning/ROADMAP.md — phase progress
  • .planning/phases/*/ — check for missing SUMMARY.md or VERIFICATION.md per phase

Step 3: Detect Anomalies

Anomaly Signal
Stuck loop Same file in 3+ consecutive commits, similar messages
Missing artifact Phase appears complete but no SUMMARY.md
Abandoned work Large time gap + STATE.md shows "In progress"
Orphaned worktree git worktree list path no longer active

Step 4: Write Report

Save to .planning/forensics/report-TIMESTAMP.md:

# Forensics Report: [Problem]
**Date:** [timestamp]
**Confidence:** HIGH / MEDIUM / LOW

## Summary
[1-2 sentence diagnosis]

## Anomalies Found
- [TYPE] [description]

## Root Cause
[Most likely cause]

## Recommended Actions
1. [Action]
2. [Action]

Present report inline. Offer deeper investigation if needed.

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 · 69 lines · 14 tokens per session scan A c1e489f9b91e

Subscribe to this mod's changes

forensics is a command published in the GitHub repository spideynolove/claude-dotfiles (2 stars, last pushed 3mo ago), licensed MIT. It adds 14 tokens to every session and 466 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.