implementation-strategy

A decision process for choosing the safest scope for changes to openai-agents-python. It checks what kind of interface or behavior is changing and identifies the existing code path that should remain the source of truth.

In plain words
What is it for?
Use it before implementation and before each batch of review changes. It helps decide whether to patch existing code, redesign, preserve compatibility, or reject unsupported cases.
Why use it?
It reduces accidental breaking changes and duplicate implementations. It also makes compatibility decisions explicit before coding or responding to review feedback.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/openai/openai-agents-python/implementation-strategy
Any agent
npx skills add openai/openai-agents-python --skill implementation-strategy
Clone the repo
git clone --depth 1 https://github.com/openai/openai-agents-python

Made for: Claude Code, Codex.

Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,577 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00047 $0.02577
Opus 5 $0.00023 $0.01288
Sonnet 5 $0.00009 $0.00515
Haiku 4.5 $0.00005 $0.00258

Measured yesterday against content hash 751085add152, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 yesterday.

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.

.agents/skills/implementation-strategy/SKILL.md · 158 lines

How it starts

The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Implementation Strategy

Workflow

  1. 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.
  2. Determine the latest release tag to use as the compatibility baseline from origin first, and only fall back to local tags when remote tags are unavailable:
    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"
    
    Report a local-tag fallback as potentially stale.
  3. Record the implementation scope contract below before coding.
  4. 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.
  5. Choose the smallest coherent change using the core decision rules. Add compatibility machinery only for a required supported boundary.
  6. Before editing each review-feedback batch, run the review gate against the complete branch diff, not only the latest revision.
  7. Before handoff, run the effectiveness check. If any answer is no, revise the design.

Implementation scope contract

Record these four items in the plan or working notes, and update them before widening or narrowing the implementation:

  1. Required behavior: The smallest user-visible scenario that must work.
  2. Compatibility requirements: Supported released behavior or a durable boundary that must remain usable.
  3. Intentionally unsupported cases: Nearby inputs or shapes to reject, including when and how rejection occurs.
  4. Supported alternative: An existing wrapper, override, adapter, configuration, or lower-level API; state none when absent.

If the intentionally unsupported cases cannot be stated clearly, do not start by adding a general resolver. First define a narrower behavior contract. If no adequate supported alternative exists, add one only when the task requires it; do not invent one speculatively.

Read the full file on GitHub · 158 lines

Files

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.

Changes

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.

  1. yesterday First seen · 158 lines · 47 tokens per session scan A 751085add152

Subscribe to this mod's changes

implementation-strategy is a skill published in the GitHub repository openai/openai-agents-python (29,075 stars, last pushed 4d ago), licensed MIT. It adds 47 tokens to every session and 2,577 once invoked, about $0.0002 per session on Opus 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.