AgentStack
Sign in Publish
MCP servers Skills Toolkits Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

L3

skill-cookys-autopilot-l3 · by cookys

>

↗ Repository
— No reviews yet
0 installs
10 views
0.0% view→install

Install

$ agentstack add skill-cookys-autopilot-l3

✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • ✓ Prompt-injection patterns
  • ✓ Secret / credential exfiltration
  • ✓ Dangerous shell & filesystem operations
  • ✓ Untrusted network calls
  • ✓ Known-malicious package signatures

What it can access

  • ✓ Network access No
  • ✓ Filesystem access No
  • ✓ Shell / process execution No
  • ✓ Environment & secrets No
  • ✓ Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

Are you the author of L3? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

/l3 — CEO autonomy, inline

Terse front-door into autopilot:ceo-agent at Level 3: the CEO executes the goal itself on this thread and escalates only at the DOA boundary.

On invocation

  1. Invoke autopilot:ceo-agent with the four startup questions pre-filled (do

not re-ask on a clean goal):

  • OKR: derived from `` (restate a verifiable end-state if the goal lacks one).
  • Involvement: 3 = just-results (full autonomy, notify on done).
  • Scope mode: Hold (override: --expand → Expand).
  • No-go zones: none (override: -x , e.g. -x payments,auth).
  1. Execution posture: inline — no foreman dispatch. This is the /l3 engine

(and the --solo degradation target for /l4//l5).

  1. Then follow ceo-agent Execution exactly (size → project setup if L → phases →

finish-flow). The front-door only changes startup; it does not skip any gate.

See [../ceo-agent/references/level-front-door.md](../ceo-agent/references/level-front-door.md) for the full front-door semantics and [../ceo-agent/SKILL.md](../ceo-agent/SKILL.md) for DOA, Prime Directives, and quality gates.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet — be the first.

Write a review

Versions

  • v0.1.0 Imported from the upstream source.

More in Agent Skills