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.
git clone --depth 1 https://github.com/emaraschio/cursor-commandsWrote 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.
[](https://agentmods.dev/commands/emaraschio/cursor-commands/decision-audit)<a href="https://agentmods.dev/commands/emaraschio/cursor-commands/decision-audit"><img src="https://agentmods.dev/badge/commands/emaraschio/cursor-commands/decision-audit/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.
<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="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00020 | $0.00793 |
| Opus 5.5 | $0.00008 | $0.00317 |
| Sonnet 5.5 | $0.00004 | $0.00159 |
| Haiku 4.5 | $0.00002 | $0.00079 |
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 1mo 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.
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
- Read
.cursor/skill-contracts/decision-audit/SKILL.mdfor the full agent contract; if that file is missing, read~/.cursor/skill-contracts/decision-audit/SKILL.md. - Execute phases in order (Intake → Evidence → Ledger → Debt and edges → Pride gate → Halt).
- 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.
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.
- 1mo ago First seen · 49 lines · 20 tokens per session scan A 9c96f616e44d
decision-audit is a command published in the GitHub repository emaraschio/cursor-commands (9 stars, last pushed 5d ago), licensed MIT. It adds 20 tokens to every session and 793 once invoked, about $0.0001 per session on Opus 5.5. 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.
Other commands, from other repositories
ship-and-observe
Take merged, green code to a verified, monitored production release — deploy, confirm the revision is live, smoke-test, observe, and roll back if needed.
deadcode
Find dead code with a configured Knip baseline, then delete it by category behind a ratchet.
refactor
Systematic refactoring: analyze → split → extract → verify behavior, with no truncation or omitted lines.
arch-boundaries
Install mechanically-enforced architecture boundaries that fail CI on spaghetti imports.
auth-flows
Read-only audit of app-layer auth — route×gate matrix, getSession vs getUser, middleware-as-only-gate.
housekeep-gates
Consolidate accreted CI gates into one aggregator required check — apply phase by phase.