lean-ctx copilot-instructions.md

Repository instructions for LeanCTX, a local tool that controls which files an AI agent reads, remembers, searches, and edits. They also specify a terse response style and special commands for understanding code, finding symbols, and tracing callers.

In plain words
What is it for?
Use them when reading or searching LeanCTX code, looking up exact symbols or callers, managing agent memory, or following the project's response format.
Why use it?
They help the agent limit unnecessary context and use the project's preferred ways to inspect code. This keeps responses short and makes code searches more targeted.

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/yvgude/lean-ctx/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/yvgude/lean-ctx

Made for: GitHub Copilot.

Per session 253 This file is loaded in full into every session.
When invoked 253 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 $0.00253 $0.00253
Opus 5 $0.00127 $0.00127
Sonnet 5 $0.00051 $0.00051
Haiku 4.5 $0.00025 $0.00025

Measured yesterday against content hash e0b8c6d1b249, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

lean-ctx 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 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.

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 · 17 lines

What it actually says

lean-ctx shadow mode: native read/search/shell calls auto-route to ctx_* — no tool-mapping needed. File editing → native Edit/StrReplace (lean-ctx only handles reads); if denied, use ctx_patch. Exclusive tools (no native trigger): ctx_compose (understand code, call first), ctx_search(action=symbol) (exact symbol), ctx_search(action=semantic) (by meaning), ctx_callgraph (callers), ctx_knowledge / ctx_session (memory).

OUTPUT STYLE: expert-terse

  • Telegraph format: subject-verb-object, drop articles/prepositions
  • Symbolic vocabulary: → cause, ∵ because, ∴ therefore, ⊕ add, ⊖ remove, Δ change, ≈ similar, ≠ different, ∈ in/member, ∅ empty/none, ✓ ok, ✗ fail
  • Code blocks: untouched (never compress code syntax)
  • Each line: max 80 chars
  • Zero narration, zero filler
  • BUDGET: ≤100 tokens per non-code response
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. yesterday First seen · 17 lines · 253 tokens per session scan A e0b8c6d1b249

Subscribe to this mod's changes

lean-ctx copilot-instructions.md is an instructions file published in the GitHub repository yvgude/lean-ctx (3,681 stars, last pushed yesterday), licensed Apache-2.0. It adds 253 tokens to every session, about $0.0013 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.