Coordinates bounded subagent tasks, complete delegation briefs, and evidence-based integration. Applies to requests to delegate, parallelize independent work, or create specialist agents. Keeps small edits and tightly dependent work inline.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
1. Keep one coordinator accountable for scope, decisions, integration, and the final answer. Honor prohibitions on delegation. Delegate only authorized work that can be evaluated separately and whose benefit exceeds dispatch, context, verification, and integration costs. Handle a small edit, a dependent sequence, or work needing constant shared context yourself. Do not create agents merely to fill roles.
2. Map dependencies and shared resources before dispatch. Run independent questions or isolated changes in parallel. Start a dependent task only after its prerequisite artifacts or agreed interface contract are available. Assign one writer per file in a shared workspace. Separate checkouts do not isolate databases, services, credentials, or external effects. Preserve pre-existing user changes.
…
The line at the top of this page pins the label git:20261105.39988c5, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
GET https://markdownregistry.com/api/v1/artifacts/art_svrigwxgv6ndqzsp
GET https://markdownregistry.com/api/v1/resolve?ref=dayfinggg/openai-codex-agent-skills/delegation
GET https://markdownregistry.com/api/v1/blob/194642fbe5791b9ea4f8d5a4b4b7f39b4d17499229270efa229e25fb020d9cb6
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
dayfinggg/openai-codex-agent-skills · codex/skills/audit/SKILL.md · Audits npm, PyPI, and Go dependencies for supply-chain risk using resolved versions and registry or advisory evidence…
dayfinggg/openai-codex-agent-skills · codex/skills/backend/SKILL.md · Changes backend HTTP contracts, security boundaries, structured logs, and background jobs. Use when creating or editing…
dayfinggg/openai-codex-agent-skills · codex/skills/caching/SKILL.md · Designs and diagnoses Redis data structures and atomic operations, application cache keys and invalidation, and HTTP…
dayfinggg/openai-codex-agent-skills · codex/skills/design/SKILL.md · Designs module interfaces, dependency seams, and test boundaries when asked how to structure a module or make code…
dayfinggg/openai-codex-agent-skills · codex/skills/documentation/SKILL.md · Writes or updates READMEs, guides, API references, runbooks, ADRs, and changelogs for a specific reader. Use when the…
dayfinggg/openai-codex-agent-skills · codex/skills/go/SKILL.md · Implements and tests Go changes with module, context, goroutine, and race checks. Use when editing or creating .go…
dayfinggg/openai-codex-agent-skills · codex/skills/php/SKILL.md · Implements and tests PHP changes and repairs Composer dependencies. Use when editing or creating .php files, PHP…
dayfinggg/openai-codex-agent-skills · codex/skills/python/SKILL.md · Implements and tests Python changes with interpreter, typing, packaging, and asyncio checks. Use when editing or…
ilya-kozyrev/delamain · skills/delegation/SKILL.md · Show or change the delegation level 0-5 (0 - do everything yourself, subagents blocked by a hook; 3 - the default; 5 -…
