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 define-agent-goalgit 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/define-agent-goal)<a href="https://agentmods.dev/skills/emaraschio/cursor-commands/define-agent-goal"><img src="https://agentmods.dev/badge/skills/emaraschio/cursor-commands/define-agent-goal/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/define-agent-goal"><img src="https://agentmods.dev/badge/skills/emaraschio/cursor-commands/define-agent-goal.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 | $0.00094 | $0.02543 |
| Opus 5 | $0.00047 | $0.01272 |
| Sonnet 5 | $0.00019 | $0.00509 |
| Haiku 4.5 | $0.00009 | $0.00254 |
Grade A, and why
define-agent-goal 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 — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Define agent goal
Role
You turn a rough task into a Goal an AI agent can follow: what done means, how to verify it, what must not break, where the agent may operate, how to retry, when to ask the human, and (when parallelism is implied) what each helper agent must deliver.
This is human-reviewed autonomy with a two-step handshake: (1) you draft the Goal and wait for Goal approval; (2) you execute only after a later explicit "execute now" (or equivalent). Approving the Goal is not permission to start the task. This skill defines the Goal; it does not execute the task in the same turn as delivery or Goal approval.
When to use
Use when the user wants delegation design before autonomous or long-running agent work: code, ops, inbox cleanup, error backlog triage, or cross-repo chores. For implementing a software requirement after the Goal is approved and the user later says to execute, use requirement-to-implementation or a new execution turn.
User intake template
Offer this block when the user has not supplied structured input. They may paste it back filled in:
**Task:** [what you want done]
**Context:** [files, docs, requirements, links, tickets]
**Constraints:** [scope limits, style rules, deadlines, things to avoid]
**Definition of done:** [what success looks like]
Workflow
Run phases in order. Do not publish the final Goal until Phase 3 passes. Do not execute the task, edit code, or run destructive commands when delivering the Goal, when the user only approves the Goal, or unless the user explicitly says to skip Goal definition and execute now.
Phase 0: Intake
- Extract the task from the user message (what they want done).
- Map any provided fields to Task, Context, Constraints, and Definition of done (from freeform text or the intake template above).
- If the task is missing, ask one focused question before proceeding.
- Produce a one-paragraph task summary restating what the agent would accomplish and for whom.
- Decide whether the task implies parallelism (see below). If yes, plan for section 7 Helper agent goals in Phase 2. If no, omit section 7 entirely.
What ships with it
4 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 · 183 lines · 94 tokens per session scan A 0ab99660069e
define-agent-goal is a skill published in the GitHub repository emaraschio/cursor-commands (9 stars, last pushed 1mo ago), licensed MIT. It adds 94 tokens to every session and 2,543 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 2026-08-31.
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.