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/topness-msft/callwright/copilot-instructionsgit clone --depth 1 https://github.com/topness-msft/callwrightWhat 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 | $0.01472 | $0.01472 |
| Opus 5 | $0.00736 | $0.00736 |
| Sonnet 5 | $0.00294 | $0.00294 |
| Haiku 4.5 | $0.00147 | $0.00147 |
Grade A, and why
callwright copilot-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 yesterday.
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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Callwright — Copilot instructions
Callwright is a self-hosted, single-user MCP server (Node.js, CommonJS) that places outbound phone calls on the user's behalf via Retell. An LLM shapes each call's direction + grounding; Callwright validates, composes, and dispatches it fire-and-forget, then fetches the outcome on demand.
Build / test / run
- Runtime: Node
>=18,"type": "commonjs". No build step. - Install:
npm install. - Tests use the built-in Node test runner (no framework dependency):
- Full suite:
npm test(runsnode --test, which discoverstest/*.test.js). - Single file:
node --test test/retry-core.test.js. - Single test by name:
node --test --test-name-pattern="classifyDisconnect" test/retry-core.test.js.
- Full suite:
- No linter or formatter is configured — don't add one unless asked.
- Run locally:
node init.js(setup wizard) thennode server.js(MCP server on:8787,POST /mcp). Installed globally the binaries arecallwrightandcallwright-init. - Place a call from the CLI (bypasses MCP):
node dispatch.js <job.json> --go.
Architecture — the core/wrapper split
The central convention: all reusable logic lives in *-core.js modules that are pure of CLI concerns (no process.argv, no stdin/stdout side effects). Thin wrappers adapt them to a surface:
dispatch-core.js— the pipeline: validate → profile-match → compose-vars → resolve-agent → dispatch. Both the CLI and the MCP server call this in-process.dispatch.js— CLI overdispatch-core.server.js— the MCP server (Streamable HTTP + bearer auth) over the same cores.- Other cores:
setup-core.js(provisioning/config/status),lang-core.js(runtime language add/verify/update/remove),learn-core.js(profile enrichment + new-scenario candidate staging),retry-core.js(no-answer re-dial policy),notify-core.js(optional SMS). - CLIs
learn.js/get-call.js/update-prompt.jsare similarly thin wrappers.
When adding behavior, put logic in the relevant *-core.js and keep server.js / the CLI as adapters — don't duplicate logic across the two surfaces.
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.
- yesterday First seen · 53 lines · 1,472 tokens per session scan A 507b5f3c0513
callwright copilot-instructions.md is an instructions file published in the GitHub repository topness-msft/callwright (1 stars, last pushed 1mo ago), licensed MIT. It adds 1,472 tokens to every session, about $0.0074 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 instructions, from other repositories
llm-context.py CLAUDE.md
Instructions for cyberchitta/llm-context.py, covering claude.md, working notes (gitignored) and draining the field notes.
openrouter-mcp-multimodal AGENTS.md
Instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).
seekstone CLAUDE.md
Instructions for shaqmughal/seekstone, covering claude.md, what this repo is, commands, the harness itself (run after npm install) and architecture.
Plonk AGENTS.md
Instructions for ostapondo/Plonk, covering agent rules, layout, adding a module, build & verify and code style.
mcp-dockhand copilot-review.instructions.md
Instructions for strausmann/mcp-dockhand: When reviewing pull requests in this repository.
second-brain AGENTS.md
Instructions for LindaHaviv/second-brain, covering instructions for ai coding agents, what to read first, the rules (non-negotiable), common tasks, the sanctioned way and enforcement, not just instructions.