Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/MichelKerkmeester/skilled-agent-harness_spec-driven-loopsnpx agentmods add skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/cli-cursorWrote 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/michelkerkmeester/skilled-agent-harness_spec-driven-loops/cli-cursor)<a href="https://agentmods.dev/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/cli-cursor"><img src="https://agentmods.dev/badge/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/cli-cursor/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/michelkerkmeester/skilled-agent-harness_spec-driven-loops/cli-cursor"><img src="https://agentmods.dev/badge/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/cli-cursor.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 | $0.00038 | $0.08915 |
| Opus 5 | $0.00019 | $0.04457 |
| Sonnet 5 | $0.00008 | $0.01783 |
| Haiku 4.5 | $0.00004 | $0.00891 |
Grade C, and why
cli-cursor scanned grade C with 3 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 today.
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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
command -v cursor-agent || echo "Not installed. Run: curl https://cursor.com/install -fsS | bash" Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
command -v cursor-agent || echo "Not installed. Run: curl https://cursor.com/install -fsS | bash" Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
ancestry = subprocess.check_output(['ps', '-o', 'command=', '-p', str(os.getppid())]).decode() How it starts
The opening of the file, as written. The whole thing — 417 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cursor CLI Orchestrator - Cross-AI Task Delegation
CRITICAL — SELF-INVOCATION PROHIBITED
This skill dispatches to the Cursor CLI binary (
cursor-agent). If the agent currently reading this skill is itself running insidecursor-agent(detection signals listed in §2), the skill MUST refuse to load and return the documented error message instead of generating anycursor-agentinvocation.A running CLI skill never dispatches itself. The cli-X skills are for cross-AI delegation only — never self-invocation.
Orchestrate Cursor's terminal coding agent (cursor-agent) for tasks that benefit from a second AI perspective, Cursor's native model (Composer), read-only plan/ask exploration, or its unique worktree/cloud-worker/plugin surfaces.
Core Principle: Use Cursor for what it does best. Delegate, validate, integrate. The calling AI stays the conductor.
1. WHEN TO USE
Activation Triggers
- Cross-AI Validation — code review second perspective, bug detection, an independent implementation attempt.
- Composer Dispatch — tasks that specifically want Cursor's own native model (
composer-2.5/composer-2.5-fast), or the Grok (4.5/4.6) / GLM 5.2 tiers already on the enforced allowlist (see §3 Model Selection). - Read-Only Exploration —
--mode plan(read-only planning) or--mode ask(read-only Q&A) when a task wants Cursor's analysis without any file writes. - Isolated Experimentation — Cursor's native git worktree isolation (
-w/--worktree) for a change the operator wants tried in a disposable checkout, documented inreferences/cursor-tools.mdas an opt-in escape hatch, not this packet's default dispatch shape. - Specialized Generation — explicit Cursor requests naming Grok (4.5 or 4.6) or GLM 5.2 specifically (the only non-Composer models on the enforced allowlist).
What ships with it
60 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.
- assets/prompt-quality-card.md 4.4 KB
- assets/prompt-templates.md 7.9 KB
- benchmark/README.md 4.6 KB
- benchmark/reports/2026-07-29--manual-testing-playbook--goal-hook/failed-runs.md 602 B
- benchmark/reports/2026-07-29--manual-testing-playbook--goal-hook/findings-and-recommendations.md 267 B
- benchmark/reports/2026-07-29--manual-testing-playbook--goal-hook/README.md 2.4 KB
- benchmark/reports/2026-07-29--manual-testing-playbook--goal-hook/results.csv 408 B
- benchmark/reports/2026-07-29--manual-testing-playbook--goal-hook/skill-benchmark-report.json 2.3 KB
- benchmark/reports/2026-07-29--manual-testing-playbook--goal-hook/skill-benchmark-report.md 3.5 KB
- benchmark/reports/2026-07-29--manual-testing-playbook--goal-hook/source.md 1.2 KB
- benchmark/reports/2026-08-08--manual-testing-playbook--agents-skills-rules/failed-runs.md 151 B
- benchmark/reports/2026-08-08--manual-testing-playbook--agents-skills-rules/findings-and-recommendations.md 199 B
- benchmark/reports/2026-08-08--manual-testing-playbook--agents-skills-rules/README.md 1.3 KB
- benchmark/reports/2026-08-08--manual-testing-playbook--agents-skills-rules/results.csv 276 B
- benchmark/reports/2026-08-08--manual-testing-playbook--agents-skills-rules/skill-benchmark-report.json 1.9 KB
- benchmark/reports/2026-08-08--manual-testing-playbook--agents-skills-rules/skill-benchmark-report.md 1.5 KB
- benchmark/reports/2026-08-08--manual-testing-playbook--agents-skills-rules/source.md 964 B
- benchmark/reports/2026-08-08--manual-testing-playbook--cursor-10/failed-runs.md 138 B
- benchmark/reports/2026-08-08--manual-testing-playbook--cursor-10/findings-and-recommendations.md 186 B
- benchmark/reports/2026-08-08--manual-testing-playbook--cursor-10/README.md 1.3 KB
- benchmark/reports/2026-08-08--manual-testing-playbook--cursor-10/results.csv 247 B
- benchmark/reports/2026-08-08--manual-testing-playbook--cursor-10/skill-benchmark-report.json 1.8 KB
- benchmark/reports/2026-08-08--manual-testing-playbook--cursor-10/skill-benchmark-report.md 1.5 KB
- benchmark/reports/2026-08-08--manual-testing-playbook--cursor-10/source.md 951 B
- benchmark/reports/2026-08-08--manual-testing-playbook--cursor-11/failed-runs.md 138 B
- benchmark/reports/2026-08-08--manual-testing-playbook--cursor-11/findings-and-recommendations.md 186 B
- benchmark/reports/2026-08-08--manual-testing-playbook--cursor-11/README.md 1.3 KB
- benchmark/reports/2026-08-08--manual-testing-playbook--cursor-11/results.csv 200 B
- benchmark/reports/2026-08-08--manual-testing-playbook--cursor-11/skill-benchmark-report.json 1.8 KB
- benchmark/reports/2026-08-08--manual-testing-playbook--cursor-11/skill-benchmark-report.md 1.5 KB
- benchmark/reports/2026-08-08--manual-testing-playbook--cursor-11/source.md 951 B
- benchmark/reports/2026-08-08--manual-testing-playbook--cursor-12/failed-runs.md 397 B
- benchmark/reports/2026-08-08--manual-testing-playbook--cursor-12/findings-and-recommendations.md 432 B
- benchmark/reports/2026-08-08--manual-testing-playbook--cursor-12/README.md 1.3 KB
- benchmark/reports/2026-08-08--manual-testing-playbook--cursor-12/results.csv 243 B
- benchmark/reports/2026-08-08--manual-testing-playbook--cursor-12/skill-benchmark-report.json 1.8 KB
- benchmark/reports/2026-08-08--manual-testing-playbook--cursor-12/skill-benchmark-report.md 1.5 KB
- benchmark/reports/2026-08-08--manual-testing-playbook--cursor-12/source.md 951 B
- benchmark/reports/2026-08-08--manual-testing-playbook--cursor-13/failed-runs.md 138 B
- benchmark/reports/2026-08-08--manual-testing-playbook--cursor-13/findings-and-recommendations.md 186 B
- benchmark/reports/2026-08-08--manual-testing-playbook--cursor-13/README.md 1.3 KB
- benchmark/reports/2026-08-08--manual-testing-playbook--cursor-13/results.csv 251 B
- benchmark/reports/2026-08-08--manual-testing-playbook--cursor-13/skill-benchmark-report.json 1.8 KB
- benchmark/reports/2026-08-08--manual-testing-playbook--cursor-13/skill-benchmark-report.md 1.5 KB
- benchmark/reports/2026-08-08--manual-testing-playbook--cursor-13/source.md 951 B
- benchmark/reports/2026-08-08--manual-testing-playbook--cursor-14/failed-runs.md 138 B
- benchmark/reports/2026-08-08--manual-testing-playbook--cursor-14/findings-and-recommendations.md 186 B
- benchmark/reports/2026-08-08--manual-testing-playbook--cursor-14/README.md 1.3 KB
- benchmark/reports/2026-08-08--manual-testing-playbook--cursor-14/results.csv 249 B
- benchmark/reports/2026-08-08--manual-testing-playbook--cursor-14/skill-benchmark-report.json 1.8 KB
- benchmark/reports/2026-08-08--manual-testing-playbook--cursor-14/skill-benchmark-report.md 1.5 KB
- benchmark/reports/2026-08-08--manual-testing-playbook--cursor-14/source.md 951 B
- benchmark/reports/2026-08-08--manual-testing-playbook--cursor-15/failed-runs.md 138 B
- benchmark/reports/2026-08-08--manual-testing-playbook--cursor-15/findings-and-recommendations.md 186 B
- benchmark/reports/2026-08-08--manual-testing-playbook--cursor-15/README.md 1.3 KB
- benchmark/reports/2026-08-08--manual-testing-playbook--cursor-15/results.csv 252 B
- benchmark/reports/2026-08-08--manual-testing-playbook--cursor-15/skill-benchmark-report.json 1.8 KB
- benchmark/reports/2026-08-08--manual-testing-playbook--cursor-15/skill-benchmark-report.md 1.5 KB
- benchmark/reports/2026-08-08--manual-testing-playbook--cursor-15/source.md 951 B
- benchmark/reports/2026-08-08--manual-testing-playbook--cursor-16/failed-runs.md 138 B
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.
- today Changed · -8 lines 9c4090dfbc02
- 4d ago Changed d3c325601170
- 6d ago First seen · 425 lines · 38 tokens per session scan C d610f9363627
cli-cursor is a skill published in the GitHub repository MichelKerkmeester/skilled-agent-harness_spec-driven-loops (35 stars, last pushed yesterday), licensed MIT. It adds 38 tokens to every session and 8,915 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 3 findings (downloads and executes remote code, makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
prowler-commit
Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.
gh-auth-isolation
Safely manage multiple GitHub identities (EMU + personal) in agent workflows.
comet-github
A routing guide for Comet-related GitHub work. It directs requests about pull requests, issues, CI failures, ideas, and fixes to the appropriate review or implementation process.
github-skill
Work with GitHub via the gh CLI — clone repositories, create/list/merge pull requests, create/list issues, and run any other gh command (API calls, workflow runs, releases, repo administration). List operations return parsed JSON.
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
nvca-chart-release
Release NVCA Operator chart changes from the native monorepo source to the vendored Helm chart. Use when updating the vendored NVCA Operator chart, changing NVCA image refs, publishing helm-nvca-operator, or validating the chart against a self-managed control plane.