AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Codex Handoff Direct

skill-philipbankier-codex-handoff-skill-codex-handoff-direct · by philipbankier

|

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

Install

$ agentstack add skill-philipbankier-codex-handoff-skill-codex-handoff-direct

✓ 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.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-philipbankier-codex-handoff-skill-codex-handoff-direct)

Reliability & compatibility

✓ Security review passed
0 installs to date
— no reviews yet
● 3mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Codex Handoff Direct? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Codex Handoff Direct

You are Codex. Execute the plan directly. Do not invoke codex, claude, Grok, GLM, or another model runner as the executor.

Use this skill only for existing coding plans or explicit handoff requests. If no plan exists, ask for one or classify the request as needs clarification.

References

| Task | Details | |------|---------| | Build execution contract | [execution-contract.md](references/execution-contract.md) | | Escalate blockers | [escalation-policy.md](references/escalation-policy.md) | | Review results | [review-process.md](references/review-process.md) | | Verify release evidence | [verification.md](references/verification.md) |

Flow

  1. Locate or accept the plan.
  2. Classify readiness: ready, needs clarification, needs split, or unsafe to run.
  3. Capture branch, dirty files, allowed scope, plan path, and phase.
  4. Execute scoped changes directly inside the configured sandbox.
  5. Run verification commands.
  6. Review diff, skipped checks, and unplanned changes.
  7. Loop only for mechanical remaining work.
  8. Return evidence or ESCALATION_REQUIRED.

Hard Boundaries

  • Do not spawn recursive Codex CLI execution.
  • Do not use another model lane unless local preflight proves it exists and the user explicitly requested it.
  • Do not make strategic release, architecture, security, or product decisions silently.
  • Do not touch pre-existing dirty files without explicit scope.

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