What is lex copilot-instructions.md?

A set of instructions for GitHub Copilot agents working on the Lex repository. It describes commands for recalling and storing memory, checking policy compliance, and following repository rules.

Use it when working on Guffawaffle/lex to retrieve prior context, follow canonical terms and architecture decisions, validate policy compliance, and handle approved merges.

It gives the agent repository-specific context and boundaries before it explores files or changes code.

lex copilot-instructions.md — Instructions file by Guffawaffle

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/guffawaffle/lex/copilot-instructions

Clone the repo

git clone --depth 1 https://github.com/Guffawaffle/lex

Made for: GitHub Copilot.

Per session 661 This file is loaded in full into every session.

When invoked 661 The same file — it is already loaded in full.

Security scan C 1 finding. 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.

Model	Per session	Once invoked
Fable 5	$0.00661	$0.00661
Opus 5	$0.00331	$0.00331
Sonnet 5	$0.00132	$0.00132
Haiku 4.5	$0.00066	$0.00066

Measured yesterday against content hash 97f835e85479, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

lex copilot-instructions.md scanned grade C with 1 finding 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.

Hidden instructionshighPrompt injection

Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.

.github/copilot-instructions.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GitHub Copilot Instructions for Lex

Lex Instructions

Use Lex Memory. Before starting work, run lex recall "topic" to retrieve prior context.

Core Commands

lex recall "topic"     # Retrieve relevant context before work
lex remember           # Store context after completing work
lex timeline           # View recent work history
lex check              # Validate policy compliance

Key Principle

Lex is the constitution, not the government. Schemas, contracts, and memory are stable surfaces. Don't leak implementation details into them.

Quick Links

docs/FOUNDERS_NOTE.md — Philosophy
docs/CONTRACT_SURFACE.md — Contract surface (v1)
canon/policy/lexmap.policy.json — Module boundaries

Run lex recall for detailed guidance on any topic.

🔐 Admin Authority

Copilot agents have delegated --admin merge authority when local CI passes. Run lex recall "admin authority" for conditions.

🎭 Behavioral Layer (LexSona)

Persona execution is handled by LexSona (separate package). Lex provides the behavioral memory socket (recordCorrection, getRules).

For persona-based workflows, see LexSona documentation.

⚠️ Critical Rules

Run lex recall for detailed guidance on:

lex recall "git tests" — NO git commits in tests (GPG signing hangs)
lex recall "sql safety" — Curated query modules only (see TROUBLESHOOTING.md "SQL Safety Violations")
lex recall "ip boundary" — Lex never imports from lexrunner

SQL Safety Quick Reference:

All db.prepare() calls must be in curated query modules (see test/sql-safety.test.ts)
If you get a SQL safety test failure, see TROUBLESHOOTING.md for refactor examples
Never use string interpolation for SQL queries - always use parameterized queries

🏗️ TypeScript Composite Projects

This repo uses TypeScript project references (composite projects). When adding new .ts files:

Read the full file on GitHub · 96 lines

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.

yesterday First seen · 96 lines · 661 tokens per session scan C 97f835e85479

Subscribe to this mod's changes

lex copilot-instructions.md is an instructions file published in the GitHub repository Guffawaffle/lex (0 stars, last pushed 3d ago), licensed MIT. It adds 661 tokens to every session, about $0.0033 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Memory and context Planning

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.

github/spec-kit · 7,104 tokens

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).

microsoft/vscode · 6,785 tokens

lex copilot-instructions.md