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/test-coverage-improver/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/test-coverage-improver)<a href="https://agentmods.dev/skills/openai/openai-agents-python/test-coverage-improver"><img src="https://agentmods.dev/badge/skills/openai/openai-agents-python/test-coverage-improver/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/test-coverage-improver"><img src="https://agentmods.dev/badge/skills/openai/openai-agents-python/test-coverage-improver.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Snyk pass
- NVIDIA SkillSpector pass
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 | $0.00031 | $0.00488 |
| Opus 5.5 | $0.00012 | $0.00195 |
| Sonnet 5.5 | $0.00006 | $0.00098 |
| Haiku 4.5 | $0.00003 | $0.00049 |
Grade A, and why
test-coverage-improver 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 — 25 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test Coverage Improver
Use current coverage evidence to identify missing caller-visible behavior tests. Select this workflow for coverage measurement, coverage-metric regressions, or finding gaps from coverage artifacts. When the user already specifies the behaviors to test, use the ordinary implementation/review workflow without coverage measurement unless measurement is also requested. Adding tests alone does not trigger this skill or its final make coverage step.
Scope and authorization
For assessment or proposal-only requests, report gaps and suggested tests without editing. When the user requests test improvements or has approved a plan, implement the scoped tests and complete review and verification without asking again. Ask only when a new contract decision, expanded scope, or additional authority is needed. Coverage work never authorizes live API calls or broader sandbox access.
Workflow
- Inspect current
.coverage,coverage.xml, and any recorded command/environment evidence. Reuse them only when they represent the relevant source and test state. If missing or stale, runmake coverageunder the repository's verification sandbox and credential policy; this initial measurement precedes implementation review. Respect host-capacity guidance before broad measurement. - Identify uncovered behavior within the requested scope. Prioritize public behavior and meaningful error, cancellation, and lifecycle paths over percentage-only targets. Use
uv run coverage report -morcoverage.xmlto locate gaps. - For an assessment, report evidence and proposed scenarios. For authorized implementation, choose tests with independent expected results at the highest controllable caller boundary. Do not add tests that merely reproduce helper logic or enumerate unsupported permutations.
- Implement tests, run affected checks, and complete
$implementation-final-review. Keep iterative verification focused; do not repeatedly run full coverage while review is incomplete. - After clean review, run
make coveragefor the final measurement and$code-change-verificationfor the required SDK gates. These have different purposes; reuse an already valid final measurement rather than repeating it. Report coverage changes, verified behaviors, and material gaps that remain.
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 · -18 lines · -16 tokens per session effaadc82be4
- 1mo ago First seen · 43 lines · 47 tokens per session scan A 202367c31db3
test-coverage-improver is a skill published in the GitHub repository openai/openai-agents-python (30,339 stars, last pushed today), licensed MIT. It adds 31 tokens to every session and 488 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
jamjet-durability-patterns
Production durability patterns for AI agents on the JVM — crash recovery, audit trails, human-in-the-loop, and replay testing using JamJet runtime.
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…
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-testing
Python testing best practices using pytest including fixtures, parametrization, mocking, coverage analysis, async testing, and test organization. Use when writing or improving Python tests.
python-testing
Guidelines for writing and running tests in the Agent Framework Python codebase. Use this when creating, modifying, or running tests.
detect-framework
Detect Python agent frameworks from code imports and map them to Omnigent executor types. Load when the user has existing agent code to integrate.