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 agentmods add skills/n-n-code/n-n-code-skills/playwright-testingnpx skills add n-n-code/n-n-code-skills --skill playwright-testinggit clone --depth 1 https://github.com/n-n-code/n-n-code-skillsWhat 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 | $0.00098 | $0.02105 |
| Opus 5 | $0.00049 | $0.01052 |
| Sonnet 5 | $0.00020 | $0.00421 |
| Haiku 4.5 | $0.00010 | $0.00211 |
Grade A, and why
playwright-testing 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 2d 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 — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Playwright Testing
Turn a focused browser question or named product claim into the smallest durable evidence. Preserve the repository's runner and language; do not translate every Playwright task into Node Playwright Test.
Choose The Lane
Route by the artifact and state model, not by the word “Playwright.”
Live investigation
Use playwright-cli to inspect a running app, reproduce a browser behavior, or
collect evidence. This lane does not require a repo-owned test harness and
does not authorize adding one. Keep the CLI agent-side unless the user asks for
repo changes.
Load references/playwright-cli-investigation.md.
If Playwright's upstream playwright-cli skill is also installed, use it as a
current command reference. This skill still owns claim framing, environment and
mutation safety, repo routing, and translation of observations into durable
tests. The executable's runtime help wins when the bundled reference drifts.
Existing-harness test work
Use this lane when a working Playwright harness exists and the main artifact is a spec, test review, locator change, flake diagnosis, mock decision, or visual check. Inspect the active ecosystem before choosing syntax or commands.
Load references/ecosystem-testing.md for Python, .NET, or Java, or whenever runner semantics are uncertain.
Setup or repair
Use setup-playwright when the requested artifact is package installation,
browser installation, runner config, webServer, project wiring, reusable-auth
plumbing, or CI shape. If the user wants both a new harness and tests, apply
setup-playwright first, then return here for the specs.
Persisted @playwright/cli tooling and Playwright Test Agent definitions also
belong to setup-playwright; Test Agents require a compatible Node Playwright
Test harness rather than a generic sidecar.
Adjacent Skills
- Add
tester-mindsetwhen the claim, risk model, oracle, or edge cases are still the main unknown. It is optional for routine authored checks. - Add
ui-guidanceorui-design-guidancewhen visual quality, accessibility, interaction, or responsive behavior is itself under review. - Use
securityfirst when the job is explicitly a security review. Addsecurity-identity-accessonly when the scope centers on authentication, sessions, recovery, federation or account linking, invitations, or tenant authorization.
What ships with it
7 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.
- 2d ago First seen · 182 lines · 98 tokens per session scan A de5dd4e1be0f
playwright-testing is a skill published in the GitHub repository n-n-code/n-n-code-skills (4 stars, last pushed 4d ago), licensed MIT. It adds 98 tokens to every session and 2,105 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
cocoscout
Relevance-ranked context loading — Tier 2 async subagent (Haiku, <5s) that fires after Tier 1 deterministic checks in UserPromptSubmit. Injects ranked context from CocoGrove, CocoContext, Environment Inspector, Prompt Studio, and CocoDream.
cocowatch
Developer engagement observer — non-blocking, always-on observational layer that tracks Delegation Intensity, Review Depth, and Engagement Zone throughout a session. Summary surfaced at $ship and FULL checkpoints.
the-grilling
Use when adversarial brainstorming is needed after reconnaissance — the Proposer, Devils-Advocate, and Synthesizer each run ONE pass (no rounds); the Don is grilled on the IDEA first, one question at a time, then the proposal is attacked.
using-gangsta
Use when starting any conversation — establishes how to find and use Gangsta skills, enforces the 1% invocation rule, maps platform tools, and routes the Don's intent through the Gangsta Agents Family hierarchy.
interrogation-debugging
Use when encountering any bug, test failure, or unexpected behavior — finds the rat in the code through systematic root-cause interrogation before any fix attempts.
the-hit
Use when the execution plan is approved and it is time for parallel execution — dispatches workers through crew leads to implement work packages with TDD enforcement, report collection, and escalation protocols.