decision-audit

decision-audit is a command for Claude Code, Cursor from emaraschio/cursor-commands. It costs 20 tokens per session (793 once invoked), scanned A, original, MIT.

A read-only record of the important choices, assumptions, alternatives, confidence levels, risks, and unfinished work in a coding session. It also includes a final check on whether the result is ready to stand behind.

In plain words
What is it for?
Use it after a build or focused coding session to inspect decisions and produce an audit without editing, committing, or deleting code.
Why use it?
It makes the reasoning behind completed work visible and helps uncover edge cases or technical debt before changes are revised.

Command for Claude CodeCursor

Written for Cursor and Claude Code: installed under .cursor/, but also a Claude Code command (commands/*.md).

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/emaraschio/cursor-commands/decision-audit
Clone the repo
git clone --depth 1 https://github.com/emaraschio/cursor-commands

Made for: Claude Code, Cursor.

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 decision-audit

README.md
[![agentmods](https://agentmods.dev/badge/commands/emaraschio/cursor-commands/decision-audit.svg)](https://agentmods.dev/commands/emaraschio/cursor-commands/decision-audit)
Your own site
<a href="https://agentmods.dev/commands/emaraschio/cursor-commands/decision-audit"><img src="https://agentmods.dev/badge/commands/emaraschio/cursor-commands/decision-audit.svg" alt="Measured on agentmods" 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 793 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 5.1 $0.00020 $0.00793
Opus 5 $0.00010 $0.00396
Sonnet 5 $0.00004 $0.00159
Haiku 4.5 $0.00002 $0.00079

Measured 6d ago against content hash 9c96f616e44d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

decision-audit 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 6d 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.

.cursor/commands/decision-audit.md · 49 lines

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Overview

After work has landed (or a scoped branch/session), list meaningful agent decisions and assumptions, surface why / alternatives / confidence, flag debt and edge cases, and ask the pride gate. Audit only; no code changes until the user says revise now. Full workflow: .cursor/skill-contracts/decision-audit/SKILL.md (user install: ~/.cursor/skill-contracts/decision-audit/SKILL.md).

Defaults

Setting Default
Scope Full session or current branch unless user narrows
Evidence Conversation + read-only git (status, diff, log) when repo present
Intensity Standard (single mode; no red-team variant in v1)
Execution Audit only; no edits, commits, or destructive commands in the same turn
Examples Generic names only (service-a, branch-1)

Steps

  1. Read .cursor/skill-contracts/decision-audit/SKILL.md for the full agent contract; if that file is missing, read ~/.cursor/skill-contracts/decision-audit/SKILL.md.
  2. Execute phases in order (Intake → Evidence → Ledger → Debt and edges → Pride gate → Halt).
  3. Report the decision ledger, debt/edge notes, pride gate, and halt line; do not revise code in the same turn.

Anti-patterns

  • Ledger of choices, not a line-by-line review. Trigger: auditing after a build. Wrong: dumping a file-by-file code review without naming decisions. Correct: list meaningful choices (architecture, API shape, libraries, deferred work) with why, alternatives, and confidence. Reason: the job is judgment autopsy, not another diff scavenger hunt.
  • Stay audit-only until revise now. Trigger: finishing the ledger or pride gate. Wrong: editing code, committing, or opening a PR in the same turn. Correct: deliver the audit and wait for an explicit revise now (with targets). Reason: ledger approval is not permission to mutate the branch.
  • Ground decisions in evidence. Trigger: filling the ledger. Wrong: inventing choices that have no support in conversation or diff. Correct: cite session or git evidence, or mark confidence low / none recorded. Reason: invented decisions fake accountability.
  • Always ask the pride gate. Trigger: closing the audit. Wrong: soft-selling ship readiness or skipping the two yes/no questions. Correct: ask whether the human is proud of the branch and would stand behind it in production. Reason: the pride gate is the cheap, high-signal filter this skill exists to force.
  • Stop when nothing has landed. Trigger: mid-task invocation with no finished work. Wrong: fabricating a ledger of completed decisions. Correct: state nothing finished, stop or ask whether to wait. Reason: auditing choices never made is theater.

Read the full file on GitHub · 49 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. 6d ago First seen · 49 lines · 20 tokens per session scan A 9c96f616e44d

Subscribe to this mod's changes

decision-audit is a command published in the GitHub repository emaraschio/cursor-commands (9 stars, last pushed 29d ago), licensed MIT. It adds 20 tokens to every session and 793 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.