Lians copilot-instructions.md

Lians copilot-instructions.md is an instructions file for GitHub Copilot from Lians-ai/Lians. It costs 285 tokens per session, scanned A, original, Apache-2.0.

Repository instructions for Lians Guard, a tool that checks whether a coding task is recovered, stale, blocked, or ready for human review. They define which kinds of evidence can be trusted.

In plain words
What is it for?
Use them when changing Lians Guard or evaluating repository state, completion evidence, trust levels, and human-review status.
Why use it?
They prevent agent statements or old test results from being mistaken for current, independently verified proof.

Instructions file for GitHub Copilot

Install

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.

agentmods
npx agentmods add instructions/lians-ai/lians/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/Lians-ai/Lians

Made for: GitHub Copilot.

Wrote 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.

agentmods badge for Lians copilot-instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/lians-ai/lians/copilot-instructions.svg)](https://agentmods.dev/instructions/lians-ai/lians/copilot-instructions)
Your own site
<a href="https://agentmods.dev/instructions/lians-ai/lians/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/lians-ai/lians/copilot-instructions.svg" alt="Measured on agentmods" height="20"></a>
Per session 285 This file is loaded in full into every session.
When invoked 285 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00285 $0.00285
Opus 5 $0.00143 $0.00143
Sonnet 5 $0.00057 $0.00057
Haiku 4.5 $0.00028 $0.00028

Measured 5d ago against content hash 8fcabf46962a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

Lians 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 5d 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.

.github/copilot-instructions.md · 24 lines

What it actually says

Lians Guard repository instructions

Lians Guard is the current-state and completion guard for AI coding agents. Keep the primary product loop focused on four results: RECOVERED, STALE, BLOCKED, and READY FOR HUMAN REVIEW.

  • Preserve the local-first recovery path and existing compatibility.
  • Treat agent prose, touched files, and caller-supplied test results as agent_attested or inferred_activity, never as measured proof.
  • Agent-facing tools cannot grant measured_local, measured_ci, or human_confirmed trust. Trusted evidence requires a Lians-owned verifier, an exact attested CI import, or interactive human confirmation.
  • Bind positive evidence to current repository and task state. A mismatch must become stale instead of silently updating old evidence.
  • READY FOR HUMAN REVIEW does not mean correct, approved, merged, or safe to deploy.
  • Do not introduce claims about time saved, token savings, revenue, retention, or product-market fit without matching external evidence.
  • Keep advanced memory, graph, compliance, and research capabilities available through progressive disclosure, but do not make them the initial Guard story.

For Guard changes, run the task-contract, CI-evidence, session-capture, Bridge, MCP, installer, and verification tests in packages/lians-easy/tests.

Changes

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.

  1. 5d ago First seen · 24 lines · 285 tokens per session scan A 8fcabf46962a

Subscribe to this mod's changes

Lians copilot-instructions.md is an instructions file published in the GitHub repository Lians-ai/Lians (10 stars, last pushed 5d ago), licensed Apache-2.0. It adds 285 tokens to every session, about $0.0014 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.