OpenAI Agents SDK is a Python framework for building workflows in which multiple AI agents use tools, delegate tasks, follow safety checks, and involve people when needed. Developers use it to create and monitor agent, sandbox, realtime, and voice applications.
Borrowing it
Nothing to install: this file belongs to openai/openai-agents-python. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/openai/openai-agents-python/main/.agents/skills/release-candidate-prep/SKILL.mdgit clone --depth 1 https://github.com/openai/openai-agents-pythonWrote 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/openai/openai-agents-python/release-candidate-prep)<a href="https://agentmods.dev/skills/openai/openai-agents-python/release-candidate-prep"><img src="https://agentmods.dev/badge/skills/openai/openai-agents-python/release-candidate-prep/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/openai/openai-agents-python/release-candidate-prep"><img src="https://agentmods.dev/badge/skills/openai/openai-agents-python/release-candidate-prep.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Snyk pass
- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 169 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- medium Excessive Agency · line 69 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00028 | $0.04006 |
| Opus 5.5 | $0.00011 | $0.01602 |
| Sonnet 5.5 | $0.00006 | $0.00801 |
| Haiku 4.5 | $0.00003 | $0.00401 |
Grade A, and why
release-candidate-prep scanned grade A with 0 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 26d ago.
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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Release Candidate Preparation
Use this skill only when the user explicitly invokes $release-candidate-prep and supplies a release version without a leading v, for example VERSION=0.20.1. This skill is the manual fallback for the GitHub Actions release workflow. Ordinary bot releases use .github/workflows/release-candidate.yml; do not invoke this local worktree procedure inside Actions.
For normal Release Please releases, use $final-release-review <release PR URL> instead.
Do not create a manual candidate to review or finish the bot PR.
Non-negotiable boundaries
- Treat explicit invocation as authorization to fetch
origin/main, create one dedicated detached release worktree, run branch-free release-readiness gates there, create or replace the localrelease/v<version>in that worktree only after those gates pass, update the five release-owned files, and create one local commit. If the branch already exists locally or remotely, the required final local state is still exact currentorigin/mainplus only the new release commit; an existing local branch may be replaced only when it is not checked out in another worktree. - Keep the user's source checkout on its existing clean
maincommit. Do not fast-forward it, switch its branch, or materialize release files there. Leave the dedicated release worktree in place for green handoff, blocked review, or recoverable failure. - Never push, open or edit a pull request, add labels or milestones, create a release, or otherwise mutate GitHub. Never run
gh. - Own exactly
pyproject.toml,uv.lock,.release-please-manifest.json,src/agents/version.py, andtests/fixtures/released_api_contract.json. Runtime, documentation, workflow, or other repository changes must land onmainbefore release preparation. - Do not stash, delete, overwrite or remove an existing worktree, or work around unrelated local changes. Fail before branch creation when the initial checkout is dirty or is not on
main, the dedicated worktree is not clean and detached at refreshedorigin/main, an existing local release branch is checked out in another worktree, the prospective packaged-contract gate fails after the allowed dependency-bootstrap recovery, the planning review blocks, ororigin/mainadvances after those gates run. - Treat
$final-release-reviewas the controlling release checker, not only as a report generator. Its planning gate must be green before branch creation, and its final-candidate gate must inspect the materialized worktree and be green before PR-ready handoff. Any candidate content, commit, or base change invalidates the previous green result. - Remove inherited
OPENAI_API_KEYfrom every child command. Release preparation does not require a live OpenAI API request. - Stop after the local commit, final release review, and copy-ready handoff. The user owns the push and pull-request creation.
What ships with it
2 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.
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.
- 26d ago Changed · +3 lines ea52a37b39af
- 28d ago Changed 25da796ac519
- 29d ago Changed · +2 lines 0ea446751dd5
- 1mo ago Changed · -59 tokens per session 25018e5328f4
- 1mo ago First seen · 179 lines · 87 tokens per session scan A 2d506f9785f7
release-candidate-prep is a skill published in the GitHub repository openai/openai-agents-python (30,339 stars, last pushed today), licensed MIT. It adds 28 tokens to every session and 4,006 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
django-6-upgrade-guide
Plan, audit, or complete an upgrade from Django 5.x to Django 6. Verify runtime and dependency compatibility, deprecations, settings, databases, migrations, tests, and deployment. Do not use for general Django work, earlier upgrades, frontend styles, or unrelated maintenance.
scope-creep-detector
Analyzes git diffs against a stated intent to detect scope creep, unrelated files, broad pull requests, changes that grew beyond a fix, dependency additions, public API renames, config or CI edits, oversized hunks, and formatting-only files. Use when the user asks whether a change grew beyond the fix, a PR is too…
mem0-test-integration
Verify a Mem0 integration produced by /mem0-integrate. Runs in the same workspace on the same branch (loose coupling) — installs dependencies, runs the repo's native test suite, then exercises a real end-to-end smoke flow against the user's API key. Produces a scorecard. TRIGGER when: user has just run /mem0-integrate…
otto-pr-review-loop
Run Polly and OCR on a PR until all findings settle.
resolve-drive-pr
Drive an open PR through Polly/OCR, validation, and maintainer handoff.
describe-pr
Only use when the user explicitly invokes this skill by name.