locus copilot-instructions.md

locus copilot-instructions.md is an instructions file for GitHub Copilot from Nano-Nimbus/locus. It costs 840 tokens per session, scanned A, original, MIT.

Repository-specific instructions for Locus, a hierarchical Markdown memory system for AI agents. They define security rules, tool contracts, coding requirements, tests, command-line behavior, and public API expectations.

In plain words
What is it for?
Use them when reviewing or changing Locus code, especially filesystem access, signing, MCP tools, Python code, tests, or command-line interfaces.
Why use it?
They help an agent make changes without breaking security protections or the repository’s existing behavior.

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/nano-nimbus/locus/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/Nano-Nimbus/locus

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 locus copilot-instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/nano-nimbus/locus/copilot-instructions.svg)](https://agentmods.dev/instructions/nano-nimbus/locus/copilot-instructions)
Your own site
<a href="https://agentmods.dev/instructions/nano-nimbus/locus/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/nano-nimbus/locus/copilot-instructions.svg" alt="Measured on agentmods" height="20"></a>
Per session 840 This file is loaded in full into every session.
When invoked 840 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 $0.00840 $0.00840
Opus 5 $0.00420 $0.00420
Sonnet 5 $0.00168 $0.00168
Haiku 4.5 $0.00084 $0.00084

Measured 4d ago against content hash 4c9a68dde86a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

locus 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 4d 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 · 50 lines

How it starts

The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Locus is a hierarchical markdown memory system for AI agents. Core invariant: load only what you need. All changes must preserve minimal-context semantics and agent-agnostic compatibility.

Security invariants — flag any violation

  • TaintTracker.session_tainted is a one-way latch. Flag any code that clears, resets, or conditionally bypasses it within a session. There is no safe in-session reset.
  • auto_sign_writes must default to False in SigningConfig. A True default enables taint laundering.
  • safe_resolve() and assert_writable() in palace.py must be called before every filesystem read/write. Flag any path that bypasses them, including new helper functions.
  • Write-blocked dirs (.sig/, .security/, sessions/, _metrics/, archived/) must be checked at every depth in the path, not just parts[0].
  • locus/security/ must not import from locus/mcp/. Shared utilities belong in locus/utils.py to avoid circular dependencies.
  • Signing protocol payload (locus-sig-v1\n<slug>\n<path>\n<signed_at>\n<sha256>) is versioned. Flag any modification to this format without a protocol version bump.

MCP tool contracts

The five tool signatures (memory_list, memory_read, memory_write, memory_search, memory_batch) are stable — changes to parameter names, types, or return shapes are breaking. FastMCP guard errors return isError=True tool results, not Python exceptions. Flag try/except around tool calls that expect exceptions from guard violations.

Python correctness

  • Flag ((var++)) in bash scripts running under set -e — post-increment returns the old value, which exits on zero. Use var=$((var + 1)) instead.
  • Flag broad except Exception without re-raise or meaningful log context.
  • Flag raw string path manipulation — all paths must use pathlib.Path.
  • Flag # type: ignore without an explanatory comment.
  • Flag manual @pytest.mark.asyncio — the project uses asyncio_mode = "auto" globally.
  • Flag any write to sys.stdout in server code — stdout is the MCP wire protocol in stdio transport. All logging must use sys.stderr.

Read the full file on GitHub · 50 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.

  1. 4d ago First seen · 50 lines · 840 tokens per session scan A 4c9a68dde86a

Subscribe to this mod's changes

locus copilot-instructions.md is an instructions file published in the GitHub repository Nano-Nimbus/locus (0 stars, last pushed 5mo ago), licensed MIT. It adds 840 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 2026-08-31.

Related

Other instructions, from other repositories

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

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

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.

openai/codex · 5,182 tokens

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,733 tokens