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.
npx skills add emaraschio/cursor-commands --skill decision-auditgit 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/skills/emaraschio/cursor-commands/decision-audit)<a href="https://agentmods.dev/skills/emaraschio/cursor-commands/decision-audit"><img src="https://agentmods.dev/badge/skills/emaraschio/cursor-commands/decision-audit.svg" alt="Measured on agentmods" 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 | $0.00071 | $0.01517 |
| Opus 5 | $0.00036 | $0.00758 |
| Sonnet 5 | $0.00014 | $0.00303 |
| Haiku 4.5 | $0.00007 | $0.00152 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Decision audit
Role
You produce a post-execution decision ledger for work already completed in scope. You surface meaningful choices and assumptions the agent made, not a line-by-line code review. You end with a pride gate and a halt: do not change code, commit, or open a PR in the same turn. Ledger approval is not revise permission; wait for revise now (with targets).
When to use
Use when the user invokes /decision-audit, asks for a decision audit, choice ledger, or pride gate after a build, or wants a judgment autopsy of what the agent chose. For productivity and value accounting, use agent-work-receipt. For diff quality before approve, use code-review or light-review-existing-diffs. For pre-build assumption surfacing, use blind-spot-pass or define-agent-goal.
Audit charter
Audit judgment after the agent has already chosen. List meaningful decisions only. Do not invent choices without evidence. Do not change code until revise now.
Workflow
Run phases in order. Do not publish the ledger until evidence is gathered. Do not revise code in this turn.
Phase 0: Intake
- Parse a scope hint from the user message (e.g. "decision audit for the auth refactor on branch-1").
- If no scope hint, default to the full session or current branch when a repo is present.
- If the user invokes mid-task with no finished work yet, say so and stop or ask whether to wait. Do not hallucinate a ledger of completed decisions.
Phase 1: Evidence
Gather read-only evidence:
- Conversation: what the user asked for, what the agent chose, what was rejected or deferred
- Git (when a repo is present):
git status,git diff,git logto ground landed choices - Files: only artifacts in scope that still reflect the chosen design
Do not invent decisions that have no support in conversation or diff. Prefer "none recorded" for alternatives when the session never considered them.
Phase 2: Ledger
List meaningful choices only. Include architecture, API shape, library picks, error-handling strategy, naming that locks an API, skipped tests, deferred work, and similar judgment calls. Skip trivial formatting noise and mechanical renames unless they lock a public contract.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 8d ago First seen · 138 lines · 71 tokens per session scan A 5235e74fd6e6
decision-audit is a skill published in the GitHub repository emaraschio/cursor-commands (9 stars, last pushed 1mo ago), licensed MIT. It adds 71 tokens to every session and 1,517 once invoked, about $0.0004 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.
Other skills, from other repositories
grok-build-supervisor
Initialize the persistent local proxy, then immediately ensure a visible Grok Build TUI for the current workspace when /grokexecute on activates, and continuously supervise that coding-agent session through a user-level Supervisor daemon as the user sends work, waits for completion, reconnects from another host task…
cursor-delegate
Delegate bounded light-to-medium implementation, investigation, documentation, configuration, testing, and tooling work to Cursor Bridge after the primary agent owns direction and risk boundaries. Also use when the user explicitly asks to create, keep, continue, inspect, or close the same Cursor execution session…
grok-executor-mode
Explicit Grok executor on/off control and task-local execution policy. Accept a direct user invocation with exactly on or off; never infer activation from ordinary requests, quoted examples, or partial matches.
cce-routing
Use Cursor Bridge's read-only cursorcontextengine for unfamiliar project understanding when the exact code location is unknown or the task requires tracing behavior, symbols, callers and callees, data flow, registrations, interface implementations, ownership boundaries, or cross-module relationships. Trigger for…
grok-executor-off
Explicitly disable Grok executor mode for this task without cancelling work or closing its terminal. Select this skill directly; no argument is required.
grok-executor-on
Explicitly enable Grok executor mode for this task and prepare its visible terminal. Select this skill directly; no argument is required.