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 scoped-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/scoped-audit)<a href="https://agentmods.dev/skills/emaraschio/cursor-commands/scoped-audit"><img src="https://agentmods.dev/badge/skills/emaraschio/cursor-commands/scoped-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/skills/emaraschio/cursor-commands/scoped-audit"><img src="https://agentmods.dev/badge/skills/emaraschio/cursor-commands/scoped-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 | $0.00099 | $0.01364 |
| Opus 5 | $0.00049 | $0.00682 |
| Sonnet 5 | $0.00020 | $0.00273 |
| Haiku 4.5 | $0.00010 | $0.00136 |
Grade A, and why
scoped-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.
How it starts
The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scoped audit
Role
You orchestrate a large, repetitive task as a scoped workflow. The goal is a trustworthy catalog of verified findings (and, only when asked and approved, a set of changes derived from them). Big surfaces are where agents hallucinate and burn tokens; this contract exists to prevent both.
When to use
Use this skill when the task is "do one thing" repeated across a large surface: audit every flag, catalog every call site, inventory every config, cross-check every doc, or migrate a pattern repo-wide. For a single requirement or a single-file change, use requirement-to-implementation instead.
Workflow
Run phases in order. Do not make changes until Phase 3 (approval) passes. Do not report a finding until Phase 6 (verification) confirms it.
Phase 0: Scope
- Restate the target surface and the question being asked in one sentence.
- Bound the surface: which directories, repos, file globs, or datasets are in and out of scope.
- Define what a single "finding" is and the exact pass/fail condition for it.
- If the surface or success condition is ambiguous, ask one focused question before proceeding (use
AskQuestionwhen available).
Phase 1: Plan (show before running)
Present the plan to the user and wait. The plan must show, explicitly:
- Stages: the ordered steps of the workflow.
- Subagent responsibilities: what each parallel subagent will inspect, and how the surface is partitioned across them.
- Verification method: how each finding will be confirmed against the source before it is reported.
- Files and commands to touch: read paths for the audit; for any proposed change, the write paths and commands.
- Smallest safe first pass: the scoped sample you will run before fanning out across the whole surface.
Phase 2: Scoped sample (first pass)
- Run the workflow against the scoped sample only, never the full surface first.
- Confirm the finding shape, the partition strategy, and the verification method actually work.
- Report sample results and the projected cost/scale of the full run. Surface the token-burn risk: parallel fan-out across a large surface compounds quickly.
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.
- 6d ago First seen · 116 lines · 99 tokens per session scan A 8015955c2751
scoped-audit is a skill published in the GitHub repository emaraschio/cursor-commands (9 stars, last pushed 1mo ago), licensed MIT. It adds 99 tokens to every session and 1,364 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
issue-creation
Trigger: issue creation, bug reports, feature requests, or issue approval. Create and triage GitHub issues from repository evidence.
sdd-tasks
Break an SDD change into implementation tasks. Trigger: orchestrator launches task planning for a change.
systemic-issue-triage
Trigger: new issue, bug report, triage, backlog, issue flood, community report, root cause, dead-end, blocked user. Attack issues by root class, never one-by-one; fixes must shrink the system, not grow it.
init-workspace-flow
Workflow for initializing or upgrading a workspace: context, discovery, documentation, etc.
arrange-workspace-flow
Workflow for arranging a workspace: layout, reference source code, business/technical context, ecosystem setup.
ijfw-workflow
Use when the user says: 'build', 'create', 'plan', 'new project', 'brainstorm', 'design', 'UI', 'website', 'dashboard', 'app', 'help me build', 'launch', 'book', 'campaign', or anything project-level. Skill body decides Quick vs Deep path.