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/asmyshlyaev177/test-proxy-recorder/agents-mdgit clone --depth 1 https://github.com/asmyshlyaev177/test-proxy-recorderWrote 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/instructions/asmyshlyaev177/test-proxy-recorder/agents-md)<a href="https://agentmods.dev/instructions/asmyshlyaev177/test-proxy-recorder/agents-md"><img src="https://agentmods.dev/badge/instructions/asmyshlyaev177/test-proxy-recorder/agents-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.03377 | $0.03377 |
| Opus 5 | $0.01688 | $0.01688 |
| Sonnet 5 | $0.00675 | $0.00675 |
| Haiku 4.5 | $0.00338 | $0.00338 |
Grade C, and why
test-proxy-recorder AGENTS.md scanned grade C 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 today.
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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rebuild reads as "the fix didn't work". `rm -rf .astro node_modules/.astro dist` How it starts
The opening of the file, as written. The whole thing — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS — structure cheatsheet
Record/replay HTTP+WebSocket proxy for deterministic e2e tests. pnpm monorepo.
Layout
packages/
test-proxy-recorder/ # the library + CLI (the product)
src/
ProxyServer.ts # core: record / replay / transparent modes
httpRecorder.ts # capture & persist HTTP exchanges
websocketHandlers.ts# WS record/replay
replaySessions.ts # per-test session keying (x-test-rcrd-id)
cli.ts proxy-cli.ts proxy.ts # `test-proxy-recorder` CLI entry
init.ts # `init` — auto-wire into a project
config*.ts # config load/merge
reset.ts # reset proxy mode
nextjs/ # SSR helpers: registerProxyFetch / registerProxyAxios
# / setNextProxyHeaders (middleware) / createHeadersWithRecordingId
tanstack-start/ # TanStack Start SSR helpers: registerProxyFetch /
# getRecordingId / createHeadersWithRecordingId
recorderEnabled.ts # shared isRecorderEnabled() gate for the adapters
playwright/ # playwrightProxy fixture (before()/teardown())
utils/ # redact, recordingId, cors, fileUtils, httpHelpers
skills/ # AI agent skills (intent-managed; 500-line SKILL.md cap,
# bulk in references/). Validate: npx intent validate <dir>
landing/ # Astro Starlight docs site (the documentation site)
src/content/docs/docs/ # English source of truth; other locales are translations
apps/ # runnable examples + e2e suites (the proof the lib works)
example-nextjs16, example-nextjs-edge, example-tanstack-start,
example-websocket, example-auth-*, example-extension, example-init
Package exports: . (Playwright/core), ./playwright, ./nextjs, ./tanstack-start. CLI bin: test-proxy-recorder.
Commands (run from repo root)
pnpm build # core library
pnpm lint
pnpm typecheck
pnpm test
pnpm example:test:e2e:ci # nextjs16 example — record then replay
pnpm example-edge:test:e2e:ci # edge example
pnpm example-tanstack:test:e2e:ci # TanStack Start example
pnpm landing:dev
pnpm landing:build # docs site
pnpm landing:audits # accessibility + Lighthouse on the built docs site
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.
- today Changed · +10 lines · +163 tokens per session 9df9ac3de260
- 5d ago First seen · 234 lines · 3,214 tokens per session scan C 19bc4b02314c
test-proxy-recorder AGENTS.md is an instructions file published in the GitHub repository asmyshlyaev177/test-proxy-recorder (111 stars, last pushed today), licensed MIT. It adds 3,377 tokens to every session, about $0.0169 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
playwright CLAUDE.md
Claude Code instructions for microsoft/playwright, covering monorepo packages, browser packages, tooling packages, key directories and build.
playwright-mcp CLAUDE.md
Claude Code instructions for microsoft/playwright-mcp, covering commit convention, ... make changes .., summary, rolling playwright and preparing a release.
playwright copilot-instructions.md
Copilot instructions for microsoft/playwright, a project described as: Playwright is a framework for Web Testing and Automation. It allows testing Chromium, Firefox and WebKit with a single API.
playwright-movies-app AGENTS.md
Instructions for debs-obrien/playwright-movies-app, covering agent guide (humans and ai), preferred tool path, style contract, healing and review checklist.
phoenix_test_playwright AGENTS.md
AGENTS.md instructions for ftes/phoenix_test_playwright, covering dev and phoenixtest upstream compatibility.
argus AGENTS.md
Instructions for chriswu727/argus, covering argus — agent guide, setup, web mode (works everywhere), wire it into the mcp host and using argus within the host task.