investigate

investigate is a command for Claude Code from abstractonion/cadence. It costs 26 tokens per session (227 once invoked), scanned A, original, MIT.

A read-only investigation mode for finding the likely cause of a bug or unexpected behavior. It ranks up to three hypotheses and supports them with evidence from the code, history, logs, or tests.

In plain words
What is it for?
Searching previous solutions and learnings, reproducing or tracing failures, citing relevant evidence, and recommending the next approved step.
Why use it?
It separates understanding the problem from changing code, helping avoid premature fixes based on guesses.

Command for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

Part of the cadence plugin — 38 skills, 15 commands, 5 agents shipped together

Good fit Searching previous solutions and learnings, reproducing or tracing failures, citing relevant evidence, and recommending the next approved step.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/abstractonion/cadence/investigate
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.

Clone the repo
git clone --depth 1 https://github.com/abstractonion/cadence

Made for: Claude Code.

Or install cadence, the plugin that ships this one along with the rest of its 38 skills, 15 commands, 5 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 investigate

README.md
[![agentmods](https://agentmods.dev/badge/commands/abstractonion/cadence/investigate.svg)](https://agentmods.dev/commands/abstractonion/cadence/investigate)
Your own site
<a href="https://agentmods.dev/commands/abstractonion/cadence/investigate"><img src="https://agentmods.dev/badge/commands/abstractonion/cadence/investigate.svg" alt="Measured on agentmods" height="20"></a>
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 227 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 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 5.1 $0.00026 $0.00227
Opus 5 $0.00013 $0.00113
Sonnet 5 $0.00005 $0.00045
Haiku 4.5 $0.00003 $0.00023

Measured 8d ago against content hash 4305f3829516, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

investigate 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 8d 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.

commands/investigate.md · 15 lines

What it actually says

Investigate

You are in investigation mode this turn. Do not edit code, apply fixes, or suggest patches yet. Before listing hypotheses, check prior solutions and learnings: search docs/solutions/ (filenames, Symptom, Tags), docs/learnings.md, and .cadence/learnings.md. Cite any match that fits the current symptoms. Then reproduce or trace the failing behavior and list up to three ranked hypotheses with concrete evidence (file paths, line ranges, log excerpts, test output). Cap yourself at three hypotheses — if none fit the evidence, say so and ask for more signal. Default to full context: ranked hypotheses with cited evidence and A/B/C fix options per propose-then-implement — do not offer or switch to compression. End with a recommended next step the user can approve.

Anchored in

  • investigate-before-fixing
  • propose-then-implement
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. 8d ago First seen · 15 lines · 26 tokens per session scan A 4305f3829516

Subscribe to this mod's changes

investigate is a command published in the GitHub repository abstractonion/cadence (4 stars, last pushed 3mo ago), licensed MIT. It adds 26 tokens to every session and 227 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.