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/anthony-chaudhary/fak/copilot-instructionsgit clone --depth 1 https://github.com/anthony-chaudhary/fakWrote 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/anthony-chaudhary/fak/copilot-instructions)<a href="https://agentmods.dev/instructions/anthony-chaudhary/fak/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/anthony-chaudhary/fak/copilot-instructions.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 5.1 | $0.00503 | $0.00503 |
| Opus 5 | $0.00251 | $0.00251 |
| Sonnet 5 | $0.00101 | $0.00101 |
| Haiku 4.5 | $0.00050 | $0.00050 |
Grade A, and why
fak 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.
What it actually says
Copilot instructions
The canonical agent instructions for this repo are in AGENTS.md — read
it first for build/test/run, the repo map, and the rules. Curated doc map:
llms.txt. Contributor contract: CONTRIBUTING.md.
Must-know rules (enforced below the agent layer):
- Delegate substantive work and keep the coordinator context clean — use guarded
headless agents or equivalent isolated workers for investigation, implementation, tests,
and review. Keep only decisions and compact witnessed evidence in the primary context;
independently verify worker effects before landing or reporting them. Direct work is for
lightweight coordination and truly trivial tasks. See
AGENTS.md. - Default is to ship — when the tree is green (
make ci), commit AND push unprompted; decide from the work in front of you, you don't wait to be asked. The rules below gate that default (stay on trunk, commit by path, never force-push); if a guard refuses (OFF_TRUNK) or a peer's merge is mid-flight, reconcile in place or stop. - Work directly on the trunk (
main); never open a feature branch or worktree — the trunk guard refuses off-trunk commits (OFF_TRUNK). The one sanctioned exception: a detached per-worker worktree that lands onmainviafak worktree worker prepare|land|reap(build isolation, #1334) — detached and lane-serialized, it is not a branch and never tripsOFF_TRUNK. Feature branches and off-trunk commits stay forbidden. - Commit by explicit path (
git commit -- <paths>, nevergit add -A); sign off withgit commit -s(DCO). - Keep code comments succinct: omit comments that restate syntax or narrate each step. Preserve comments that explain non-obvious rationale, invariants, safety, concurrency, compatibility, or exported APIs; prefer clearer code and put durable tutorials in docs.
- The Go module is the repository root — run
gocommands from the clone root (go install github.com/anthony-chaudhary/fak/cmd/fak@latestresolves directly).
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 · 30 lines · 503 tokens per session scan A a8b40c4f82d5
fak copilot-instructions.md is an instructions file published in the GitHub repository anthony-chaudhary/fak (36 stars, last pushed today), licensed Apache-2.0. It adds 503 tokens to every session, about $0.0025 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 2026-09-03.
Other instructions, from other repositories
neuron-ai CLAUDE.md
Claude Code instructions for neuron-core/neuron-ai, covering project overview, code standards, think before coding, simplicity first and surgical changes.
memv CLAUDE.md
Claude Code instructions for vstorm-co/memv, covering claude.md, project overview, development setup, commands and quality.
quant.cpp CLAUDE.md
Claude Code instructions for quantumaikr/quant.cpp, covering quant.cpp — agent development guide, project vision, project overview, architecture and key documents.
goa-ai CLAUDE.md
Claude Code instructions for goadesign/goa-ai, covering claude guide for mcp plugin (goa), high-level goals, core strategy (from prompts.txt), file/dir conventions and path handling.
claude-my-network-engineer CLAUDE.md
Instructions for Claudedidthis/claude-my-network-engineer, covering claude.md — claudemynetworkengineer, working modes, build mode (laptop, fixture-based, no live writes), live mode (always-on runtime, real network) and identity.
StoryMind AGENTS.md
AGENTS.md instructions for LinHao-city/StoryMind: MANDATORY: Read AGENTGUIDE.md before responding to ANY user message.