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/tmc/nlm/copilot-instructionsgit clone --depth 1 https://github.com/tmc/nlmWhat 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 | $0.02689 | $0.02689 |
| Opus 5 | $0.01345 | $0.01345 |
| Sonnet 5 | $0.00538 | $0.00538 |
| Haiku 4.5 | $0.00269 | $0.00269 |
Grade A, and why
nlm 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 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 — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
nlm — repository instructions for coding agents
Trust these instructions. Every command below was executed against this commit, including
in a fresh git clone, and the observed output is what is reported. Search the tree only when
something here is incomplete or demonstrably wrong.
What this repo is
nlm is a Go command-line client and MCP server for Google NotebookLM. It speaks two
undocumented Google wire protocols — batchexecute (URL-encoded, positionally-indexed nested
JSON arrays keyed by short rpc IDs like o4cbdc) and a gRPC-Web streaming endpoint for chat —
and maps them onto protobuf messages through a custom positional-JSON codec
(internal/beprotojson). Much of the repo's mass is the ongoing migration from hand-written
positional parsers to generated proto bindings; docs/nlm-proto-migration-ledger.md tracks
that per RPC family and is the source of truth for what is switched vs. still legacy.
- Single Go module
github.com/tmc/nlm,go 1.25.0. Verified with go1.26.3 darwin/arm64. - ~471 tracked files, 336
.gofiles, ~108k lines (about half is generated protobuf code). - Real runtime deps: chromedp (browser cookie extraction), protobuf,
modelcontextprotocol/go-sdk,rsc.io/script(CLI tests),golang.org/x/*. Not gRPC — NotebookLM speaks batchexecute and gRPC-Web over plainnet/http. - CI checks command reachability with
deadcodeafter compiling integration-tagged tests. The full local gate remainsgo build ./... && go vet ./... && go test ./....
Build and test — the exact sequence
Run from the repo root. No bootstrap, no codegen, no credentials, and no network beyond the
initial module download. Tests are hermetic: they use an isolated HOME under t.TempDir()
and never reach the network.
go build ./... # ~2s warm, ~4s cold — clean
go test ./... # ~17-19s — all packages pass
Optional extra confidence (verified green):
go test -race ./internal/... # ~16s
go test ./cmd/nlm -run TestCLICommands -v # the txtar script-test suite alone
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 · 188 lines · 2,689 tokens per session scan A e3a58e0e7a9c
nlm copilot-instructions.md is an instructions file published in the GitHub repository tmc/nlm (389 stars, last pushed 28d ago), licensed MIT. It adds 2,689 tokens to every session, about $0.0134 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
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.