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/configgit 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 | $0.02424 | $0.02424 |
| Opus 5 | $0.01212 | $0.01212 |
| Sonnet 5 | $0.00485 | $0.00485 |
| Haiku 4.5 | $0.00242 | $0.00242 |
Grade A, and why
agentic-playwright config.instructions.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Configuration
Critical
- NEVER hardcode URLs, tokens, emails, or passwords anywhere in the scaffold. The only source of truth for env-driven values is
process.env.*, backed byenv/.env.${environment}. - NEVER hardcode endpoint paths or route strings in
config/. Paths belong inenums/{area}/*(see theenumsskill). - ALWAYS add every new env variable to
env/.env.examplewith a safe placeholder — no real secrets, no production URLs. - ALWAYS add a JSDoc comment on every config property describing the value and the backing env var.
- ALWAYS keep app-facing URLs/settings in
config/app.tsand utility/third-party services inconfig/util/util.ts. Do not create ad-hoc config files elsewhere. - NEVER commit
env/.env.dev,env/.env.staging, or any other real env file containing credentials. Onlyenv/.env.exampleis tracked.
File Locations
| Type | Directory | Purpose |
|---|---|---|
| App config | config/app.ts |
URLs and settings for the main application |
| Utility config | config/util/util.ts |
Utility / third-party service configuration |
| Env template | env/.env.example |
Tracked template — safe placeholders only |
| Env (active) | env/.env.${ENVIRONMENT} |
Real values, selected at runtime (.env.dev etc.) — untracked |
Instructions
Phase 1: Understand how env files are loaded
playwright.config.ts loads env values via dotenv at startup:
const environment = process.env.ENVIRONMENT ?? 'dev';
const environmentPath = `./env/.env.${environment}`;
dotenv.config({ path: environmentPath });
Consequences:
- Default environment is
dev(fileenv/.env.dev). - Override with a shell variable:
ENVIRONMENT=staging npx playwright test. - The selected file must exist — missing files silently load nothing and every
process.env.*becomesundefined. ENVIRONMENTitself is set at the shell level; it is not declared in any.envfile.
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 · 215 lines · 2,424 tokens per session scan A bcec01fce9c8
agentic-playwright config.instructions.md is an instructions file published in the GitHub repository idavidov13/agentic-playwright (139 stars, last pushed 6d ago), licensed MIT. It adds 2,424 tokens to every session, about $0.0121 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.
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.