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/linuxfoundation/lfx-self-serve/copilot-instructionsgit clone --depth 1 https://github.com/linuxfoundation/lfx-self-serveWhat 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 | $0.00830 | $0.00830 |
| Opus 5 | $0.00415 | $0.00415 |
| Sonnet 5 | $0.00166 | $0.00166 |
| Haiku 4.5 | $0.00083 | $0.00083 |
Grade A, and why
lfx-self-serve 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
lfx-self-serve — Copilot code review
This repo guides Copilot code review on its pull requests.
Code review
When the task is to review a change for correctness, design, and security,
the review method for this repo lives in .github/skills/:
copilot-code-reviewer— the entry point: reviewer scope, signal bar, and how to decide what is worth a comment. Governing when reviewing this repo.self-serve-code-review— the line-level implementation lens. Applies to every PR that changes code, however small.self-serve-security-review— the security lens. Applies whenever the diff touches auth, sessions or tokens, a server controller or service, an upstream proxy call, the public surface, identity or persona authorization, PII or logging, URLs or redirects,[innerHTML], or the SSR-to-client boundary.
Each of these stands on its own and says in its own description when it applies; read the ones that apply to the diff in front of you and follow them: together they are this repo's review method.
Shared context
This repo is LFX One, the user-facing tier of LFX V2: an Angular 20 SSR
application (apps/lfx-one/src/app/) and the Express.js BFF that serves it
(apps/lfx-one/src/server/), with shared types, constants, enums, and
validators in packages/shared/ (@lfx-one/shared). The BFF is a thin proxy:
it holds the user's OIDC session, resolves persona and impersonation context
server-side, and forwards most business requests to the V2 microservice mesh
with the user's bearer token, mirroring upstream request/response shapes rather
than defining its own contracts (some flows instead use direct NATS
request/reply or Snowflake analytics). Authentication is selective — a small public surface
(the /meetings/ pages, /public/api, /docs, health, and a few utility
routes like /invite/error, /auth-error, /sitemap.xml, /robots.txt) is
reachable without a session; everything else that reaches the auth middleware
requires one. The route table in
apps/lfx-one/src/server/middleware/auth.middleware.ts is authoritative for
those routes, while the OIDC login/logout/callback routes mount in server.ts
ahead of it. The app renders under SSR and then
hydrates, so browser-only code must be guarded and no server-only secret may
cross into the client bundle.
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 · 62 lines · 830 tokens per session scan A 45a38fb0318b
lfx-self-serve copilot-instructions.md is an instructions file published in the GitHub repository linuxfoundation/lfx-self-serve (11 stars, last pushed 2d ago), licensed MIT. It adds 830 tokens to every session, about $0.0042 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.