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/implementation-strategy/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/implementation-strategy)<a href="https://agentmods.dev/skills/openai/openai-agents-python/implementation-strategy"><img src="https://agentmods.dev/badge/skills/openai/openai-agents-python/implementation-strategy/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/implementation-strategy"><img src="https://agentmods.dev/badge/skills/openai/openai-agents-python/implementation-strategy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Snyk pass
- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 Anti-Refusal · line 64 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
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 | $0.00022 | $0.02665 |
| Opus 5.5 | $0.00009 | $0.01066 |
| Sonnet 5.5 | $0.00004 | $0.00533 |
| Haiku 4.5 | $0.00002 | $0.00266 |
Grade A, and why
implementation-strategy scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implementation Strategy
Workflow
- Identify the surface you are changing or reviewing: released public API, unreleased branch-local API, internal helper, persisted schema, wire protocol, CLI/config/env surface, or docs/examples only.
- When released compatibility is relevant, determine the latest release tag from
originfirst, falling back to local tags only when remote tags are unavailable. Reuse an already verified baseline within the task unless new release evidence or changed scope makes it stale:
Report a local-tag fallback as potentially stale.BASE_TAG="$(.agents/skills/final-release-review/scripts/find_latest_release_tag.sh origin 'v*' 2>/dev/null || git tag -l 'v*' --sort=-v:refname | head -n1)" echo "$BASE_TAG" - Record the implementation scope contract below before coding.
- Identify the nearest existing implementation pipeline and the functions, types, or modules that are the source of truth for each affected concern. Prefer adapting the required input into that pipeline over creating parallel schema, metadata, validation, naming, or execution machinery.
- Choose the smallest coherent change using the core decision rules. Add compatibility machinery only for a required supported boundary.
- Revisit the review gate when feedback changes supported behavior, compatibility, ownership, protocol paths, implementation shape, or test permutations, or triggers a complexity reset. Otherwise retain the scope contract and proceed with the focused fix.
- Before handoff, run the effectiveness check. If any answer is no, revise the design.
Implementation scope contract
Record these four items in the existing plan or working notes, and update them before widening or narrowing the implementation. A local fix can use one concise paragraph; mark unaffected dimensions as not applicable rather than inventing unsupported cases or creating another document:
- Required behavior: The smallest user-visible scenario that must work.
- Compatibility requirements: Supported released behavior or a durable boundary that must remain usable.
- Intentionally unsupported cases: Nearby inputs or shapes to reject, including when and how rejection occurs.
- Supported alternative: An existing wrapper, override, adapter, configuration, or lower-level API; state
nonewhen absent.
What ships with it
1 file 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.
- 1mo ago Changed · +2 lines · -25 tokens per session b3f478176db4
- 1mo ago First seen · 158 lines · 47 tokens per session scan A 751085add152
implementation-strategy is a skill published in the GitHub repository openai/openai-agents-python (30,339 stars, last pushed today), licensed MIT. It adds 22 tokens to every session and 2,665 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.
python-backend
Production Python async patterns including asyncio TaskGroup, FastAPI dependency injection and middleware, SQLAlchemy 2.0 async sessions, and database connection pool tuning. Python 3.11+ runtime concerns such as ExceptionGroup, cancellation semantics, and session rollback. Use when building async services, wiring…
python-engineering-guidelines
General Python engineering standards for writing, reviewing, and refactoring maintainable code. Use when Codex works on Python code, especially in medium/large projects, runtime adapters, APIs, SDK integrations, async services, stateful systems, or refactors where readability, explicit typing, module boundaries, side…
plugin-system
Generic plugin system for Python applications. Auto-discovery, validation, fault tolerance. Zero dependencies (Python stdlib only).
publish-python-package-pypi
Configure or troubleshoot PyPI publication for PDM packages with GitHub Actions and Trusted Publishing. Use this skill for the Python package in a mixed-language repository. Do not use it for applications or repositories without a Python distribution. Do not use it for generic CI, containers, or token uploads unless…
pn-python-scaffolding
Scaffolds new Python API projects (FastAPI, Flask, Django) or routes. Use when adding a new route/module; covers project layout, env/secrets, validation, error handling, and idiomatic Python patterns.