codex-prompting

Name: codex-prompting
Author: contextosai

Use when improving Codex-style task prompts, AGENTS.md instructions, review briefs, subagent handoffs, or implementation requests so they are precise, scoped, testable, and safe for coding agents.

by contextosai(0) 0 installs

Free

Free account. Installing gives you the manifest plus copy-paste snippets.

See reviews

About

Imported from contextosai/SecondBrain-collab (skills/codex-prompting/SKILL.md). Install upstream with npx skills add contextosai/SecondBrain-collab --skill codex-prompting. Copyright stays with the author.

Codex Prompting

Purpose

Create prompts and instruction files that coding agents can execute without guesswork.

Instructions

State the objective, owned scope, and out-of-scope areas.
Name the exact files, registries, APIs, or commands the agent should inspect first.
Include constraints for safety, permissions, style, tests, and working-tree hygiene.
Add acceptance criteria that can be verified locally.
Prefer concrete commands over vague quality goals.
Keep the final prompt direct enough to paste into a coding-agent session.

Checklist

Goal and reason are explicit.
Ownership boundaries are explicit.
Required discovery steps are listed.
Validation commands and expected outcomes are listed.
Final handoff format is specified.

Use it

Copy one of these into your project. Installing also returns the manifest and these snippets.

# after Install: the listing is in your workspace's routing pool - a plan picks it for its slot
curl -s -X POST https://api.opensmartroute.ai/api/v1/route -H 'Authorization: Bearer $OSR_API_KEY' -H 'Content-Type: application/json' -d '{"text": "...", "plan": true}'

Manifest

An Open Capability Manifest: the router reads it to know what this does, what it costs and when to pick it.

contextosai-secondbrain-collab-codex-prompting.ocm.jsonjson

{
  "ocm": "1",
  "id": "contextosai-secondbrain-collab-codex-prompting",
  "kind": "skill",
  "name": "codex-prompting",
  "description": "Use when improving Codex-style task prompts, AGENTS.md instructions, review briefs, subagent handoffs, or implementation requests so they are precise, scoped, testable, and safe for coding agents.",
  "publisher": "contextosai",
  "version": "1.0.0",
  "capabilities": {
    "domains": [
      "general"
    ],
    "tags": [
      "skill-md",
      "github"
    ],
    "languages": [
      "en"
    ]
  },
  "quality_prior": 0.6,
  "examples": [
    "Use when improving Codex-style task prompts, AGENTS.md instructions, review briefs, subagent handoffs, or implementation requests so they are precise, scoped, testable, and safe for coding agents."
  ],
  "primary": false,
  "metadata": {
    "source": {
      "provider": "github",
      "repository": "https://github.com/contextosai/SecondBrain-collab",
      "path": "skills/codex-prompting/SKILL.md",
      "ref": "acec9678c05e80e859802a4e4e18f187e35d66b5",
      "url": "https://github.com/contextosai/SecondBrain-collab/blob/acec9678c05e80e859802a4e4e18f187e35d66b5/skills/codex-prompting/SKILL.md",
      "key": "contextosai/SecondBrain-collab/skills/codex-prompting/SKILL.md"
    }
  },
  "instructions": "# Codex Prompting\n\n## Purpose\n\nCreate prompts and instruction files that coding agents can execute without\nguesswork.\n\n## Instructions\n\n1. State the objective, owned scope, and out-of-scope areas.\n2. Name the exact files, registries, APIs, or commands the agent should inspect first.\n3. Include constraints for safety, permissions, style, tests, and working-tree hygiene.\n4. Add acceptance criteria that can be verified locally.\n5. Prefer concrete commands over vague quality goals.\n6. Keep the final prompt direct enough to paste into a coding-agent session.\n\n## Checklist\n\n- Goal and reason are exp",
  "cost": {
    "context_tokens": 193
  }
}

Fetch it by URL: GET /api/v1/registry/contextosai-secondbrain-collab-codex-prompting/manifest?version=1.0.0