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.
npx skills add gohypergiant/agent-skills --skill accelint-ac-to-playwrightgit clone --depth 1 https://github.com/gohypergiant/agent-skillsWrote 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/gohypergiant/agent-skills/accelint-ac-to-playwright)<a href="https://agentmods.dev/skills/gohypergiant/agent-skills/accelint-ac-to-playwright"><img src="https://agentmods.dev/badge/skills/gohypergiant/agent-skills/accelint-ac-to-playwright/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/gohypergiant/agent-skills/accelint-ac-to-playwright"><img src="https://agentmods.dev/badge/skills/gohypergiant/agent-skills/accelint-ac-to-playwright.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 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 System Prompt Leakage · line 151 Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.Fix: Remove any instructions that reveal, print, or output system prompts or internal rules. System instructions should never be exposed to end users.
- medium MCP Rug Pull · line 176 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 181 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 222 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00123 | $0.00365 |
| Opus 5.5 | $0.00049 | $0.00146 |
| Sonnet 5.5 | $0.00025 | $0.00073 |
| Haiku 4.5 | $0.00012 | $0.00036 |
Grade A, and why
accelint-ac-to-playwright 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 29d 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.
What it actually says
AC To Playwright
Your Role
You are a router. Load the appropriate workflow file based on the user's request.
Route Detection
Assessment mode (triggers on):
- "review these AC"
- "evaluate these AC"
- "check if these AC are ready"
- "can these AC be converted as-is"
- "are these AC automation-ready"
- "assess these acceptance criteria"
Full conversion mode (triggers on):
- "convert these AC"
- "generate tests from AC"
- "turn AC into Playwright tests"
- "create test automation"
Routing Rules
Assessment mode:
Load agents/assessment-mode.md and execute its workflow.
Conversion mode:
Load agents/conversion-mode.md and execute its workflow.
Core Anti-Patterns
-
NEVER spawn both mode workflows simultaneously — executing both duplicates work and wastes tokens.
-
NEVER modify output directories — use exact paths the user provides. Do not append subdirectories.
What ships with it
60 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.
- agents/assessment-mode.md 19 KB
- agents/conversion-mode.md 15 KB
- agents/diagnose-schema-errors.md 7.0 KB
- agents/diagnose-translation-errors.md 3.7 KB
- agents/generate-names.md 6.6 KB
- agents/validate-actions.md 6.6 KB
- agents/validate-assertions.md 5.5 KB
- agents/validate-bullet-format.md 2.9 KB
- agents/validate-gherkin-structure.md 6.7 KB
- agents/validate-preconditions.md 3.7 KB
- agents/validate-targets.md 3.6 KB
- assets/evals/BAD-AC.feature 436 B
- assets/evals/expected/BAD-AC.assessment.yaml 1.8 KB
- assets/evals/expected/MIXED-AC.assessment.yaml 1.5 KB
- assets/evals/expected/PERFECT-AC.assertions.yaml 663 B
- assets/evals/expected/PERFECT-AC.plan.json 6.2 KB
- assets/evals/MIXED-AC-1.feature 2.0 KB
- assets/evals/PERFECT-AC.feature 2.9 KB
- assets/fixtures/console-tracking.ts 991 B runs code
- assets/fixtures/error-handling.ts 1016 B runs code
- assets/templates/playwright.config.ts 2.0 KB runs code
- CHANGELOG.md 9.9 KB
- evals/_noise_filter.py 2.6 KB runs code
- evals/_reporter.py 16 KB runs code
- evals/.env.example 647 B
- evals/.gitignore 214 B
- evals/conftest.py 7.2 KB runs code
- evals/DESIGN.md 25 KB
- evals/litellm_judge.py 2.9 KB runs code
- evals/metrics/_json_extraction.py 3.7 KB runs code
- evals/metrics/assessment_quality.py 4.0 KB runs code
- evals/metrics/assumptions.py 4.7 KB runs code
- evals/metrics/blatant_errors.py 3.5 KB runs code
- evals/metrics/clarification_needed.py 4.4 KB runs code
- evals/metrics/goal_accuracy.py 5.3 KB runs code
- evals/metrics/hallucinated_assertions.py 7.2 KB runs code
- evals/metrics/json_completeness.py 6.6 KB runs code
- evals/metrics/permission_compliance.py 2.8 KB runs code
- evals/metrics/plan_adherence.py 5.3 KB runs code
- evals/metrics/plan_semantic.py 4.7 KB runs code
- evals/metrics/plan_structural.py 3.5 KB runs code
- evals/metrics/step_efficiency.py 4.6 KB runs code
- evals/metrics/target_coverage.py 3.8 KB runs code
- evals/metrics/task_completion.py 3.6 KB runs code
- evals/pyproject.toml 1.5 KB
- evals/README.md 13 KB
- evals/runner.py 8.3 KB runs code
- evals/tests/test_assessment_mode.py 5.9 KB runs code
- evals/tests/test_compare_outputs.py 1.1 KB runs code
- evals/tests/test_conversion_mode.py 6.9 KB runs code
- evals/tests/test_correctness_metrics_regressions.py 2.7 KB runs code
- evals/tests/test_efficiency_metrics_regressions.py 2.8 KB runs code
- evals/tests/test_engineer_not_ready_conversion.py 5.4 KB runs code
- evals/tests/test_metrics_catch_regressions.py 9.1 KB runs code
- evals/tests/test_pitfalls_metrics_regressions.py 3.6 KB runs code
- evals/tests/test_pm_perfect_assessment.py 5.8 KB runs code
- evals/tests/test_rubric_hashes.py 1.4 KB runs code
- evals/uv.lock 440 KB
- package-lock.json 60 KB
- package.json 810 B
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.
- 29d ago Changed · -234 lines afda2e850e4d
- 1mo ago First seen · 279 lines · 123 tokens per session scan A 4ee2fadaa619
accelint-ac-to-playwright is a skill published in the GitHub repository gohypergiant/agent-skills (25 stars, last pushed 9d ago), licensed Apache-2.0. It adds 123 tokens to every session and 365 once invoked, about $0.0005 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
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
test-master
Generates test files, creates mocking strategies, analyzes code coverage, designs test architectures, and produces test plans and defect reports across functional, performance, and security testing disciplines. Use when writing unit tests, integration tests, or E2E tests; creating test strategies or automation…
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
critique
Adversarial design critique of the current work. Render it, look at it, and argue for rejection. Run after the gates are green, never instead of them.