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 instructions/idavidov13/agentic-playwright/api-testinggit clone --depth 1 https://github.com/idavidov13/agentic-playwrightWhat 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 | $0.04618 | $0.04618 |
| Opus 5 | $0.02309 | $0.02309 |
| Sonnet 5 | $0.00924 | $0.00924 |
| Haiku 4.5 | $0.00462 | $0.00462 |
Grade A, and why
agentic-playwright api-testing.instructions.md scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **Do NOT** curl the endpoint first to "see what it returns" and then write schemas that match reality. How it starts
The opening of the file, as written. The whole thing — 366 lines — stays where its author put it; the contents beside it link to each section on GitHub.
API Testing
Critical
These rules are non-negotiable. Violating any of them breaks the scaffold's contract.
- NEVER hardcode API URLs, access tokens, emails, passwords, or endpoint paths. The only allowed sources of truth are
process.env.*(for URLs and credentials) and theenums/{area}/*enums (for endpoint paths, e.g.ApiEndpoints.LOGIN). - ALWAYS validate API response bodies with Zod using the exact assertion pattern
expect(SchemaName.parse(body)).toBeTruthy();. Type generics alone are not enough, andschema.parse(body)without theexpect(...).toBeTruthy()wrapper is not enough. - ALWAYS wrap each API call in
test.step()when a test contains more than one API call. - NEVER silently drop a test because the API misbehaves. Write the test as the spec says, wrap it in
test.skip, and add a// FIXME: <ticket-url>comment. - NEVER stop at
{}empty-body validation. Every request-body endpoint requires per-field omission and per-field invalid-type tests. - ALWAYS fuzz path parameters with the invalid-format data-driven loop — regardless of whether OpenAPI mentions it.
- ALWAYS use the
apiRequestfixture directly in tests. Only promote to a helper fixture when the same setup/teardown is reused across 3+ test files.
Instructions
Phase 1: Source the contract (documentation first, exploration only as fallback)
The API contract — not observed behavior — is the source of truth for schemas and tests.
- If OpenAPI / Swagger / equivalent documentation exists (the normal case):
- Build schemas and tests strictly from the documented contract: field names, types, required vs optional, nullability, status codes, error shapes.
- Do NOT curl the endpoint first to "see what it returns" and then write schemas that match reality.
- If, during test execution, the actual response disagrees with the documentation (missing field, wrong type, wrong status code, extra field), that is a bug to report, not a reason to loosen the schema. Handle it via Phase 7 (
test.skip+// FIXME: <ticket-url>).
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 · 366 lines · 4,618 tokens per session scan A 9f7561523366
agentic-playwright api-testing.instructions.md is an instructions file published in the GitHub repository idavidov13/agentic-playwright (134 stars, last pushed 5d ago), licensed MIT. It adds 4,618 tokens to every session, about $0.0231 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
COG-second-brain AGENTS.md
Instructions for huytieu/COG-second-brain, covering cog: agentic second brain - universal agent commands, available commands, /onboarding, /braindump and /daily-brief.
COG-second-brain CLAUDE.md
Instructions for huytieu/COG-second-brain, covering cog second brain — framework instructions, verification harness (opt-in, off by default), visual verification (always apply, ui/ux tasks), delegation cap (always apply) and model routing — always apply.
COG-second-brain GEMINI.md
Instructions for huytieu/COG-second-brain, covering cog: agentic second brain, your role, vault structure, user profile and available skills.
agentic-config AGENTS.md
Instructions for WaterplanAI/agentic-config, covering project guidelines, environment & tooling, core rules, skill triggering and content & pii.
compare-mcp CLAUDE.md
Instructions for Cristophereasygoing927/compare-mcp, covering compare-mcp, architecture, running and key decisions.
multiagent-template CLAUDE.md
Instructions for Neftedollar/multiagent-template, covering how to start (required for every session), 1. determine mode, 2. load context (depends on mode), 3. act and workspace structure.