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/magnifico4625/locus/agents-mdgit clone --depth 1 https://github.com/Magnifico4625/locusWrote 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/magnifico4625/locus/agents-md)<a href="https://agentmods.dev/instructions/magnifico4625/locus/agents-md"><img src="https://agentmods.dev/badge/instructions/magnifico4625/locus/agents-md.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 | $0.01092 | $0.01092 |
| Opus 5 | $0.00546 | $0.00546 |
| Sonnet 5 | $0.00218 | $0.00218 |
| Haiku 4.5 | $0.00109 | $0.00109 |
Grade A, and why
locus AGENTS.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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS
This file defines the working contract for AI agents operating in the locus repository.
It is intentionally short, opinionated, and practical.
Mission
Build and maintain Locus as a persistent memory platform for AI coding tools, with the current primary product focus on:
- Codex CLI
- Codex desktop / extension surfaces
- Claude Code compatibility preservation
Secondary IDE adapters such as Cursor, Windsurf, Cline, and Zed matter, but they must not degrade the primary Codex path.
Core Working Style
- Think before coding.
- Surface wrong assumptions, hidden confusion, and missed trade-offs early.
- Prefer simplicity first.
- Avoid unnecessary abstraction and speculative complexity.
- Make surgical changes.
- Do not touch unrelated code without a clear reason.
- Keep implementation goal-oriented.
- Use tests and checkable success criteria as a competitive advantage, not as an afterthought.
Collaboration Contract
- Work task-by-task when the user is driving an execution sequence.
- Do not silently jump to the next major task if the user asked for approval gates.
- Communicate directly and concisely.
- Prefer facts, validation results, and concrete trade-offs over reassurance or filler.
- Save important project decisions so they remain discoverable across sessions.
Product Rules
1. Keep one Locus, not separate products
- Do not fork Locus into separate products for Codex, Claude Code, or other clients.
- Reuse the shared storage, inbox, search, and ingest pipeline wherever possible.
- Client-specific behavior should be implemented as thin adapters.
2. Codex is the current primary product line
- Codex CLI and Codex desktop / extension are the primary validation path after
v3.3.0. - Codex-first work should improve one or more of:
- installation UX
- conversational recall quality
- diagnostics
- packaging
- user trust and privacy clarity
3. Claude Code must not regress casually
packages/claude-code/**should stay untouched unless a shared contract change truly requires it.- Codex work must not create incidental Claude regressions.
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.
- 6d ago First seen · 154 lines · 1,092 tokens per session scan A 8e889d7e8088
locus AGENTS.md is an instructions file published in the GitHub repository Magnifico4625/locus (14 stars, last pushed 2mo ago), licensed MIT. It adds 1,092 tokens to every session, about $0.0055 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.
Other instructions, from other repositories
marm-memory AGENTS.md
AGENTS.md instructions for Lyellr88/marm-memory, covering marm-memory - agent instructions, architecture, consistency rules, code patterns and testing.
Perenna AGENTS.md
Instructions for scarletkc/Perenna, covering perenna agent guidelines, start with the project contract, environment, implementation boundaries and generated and versioned artifacts.
nobrainr CLAUDE.md
Claude Code instructions for vicquick/nobrainr, covering nobrainr — collective agent memory service, what this is, canonical categories, architecture and routing (when using a reverse proxy).
mcp-memory-server CLAUDE.md
Instructions for foxj77/mcp-memory-server, covering claude.md, what this repo is, chart layout, build / run / test and local build + run.
flux-memory CLAUDE.md
Instructions for harsh5i/flux-memory, covering flux memory v0.5 — claude.md, hard constraints (never deviate), repo layout, development rules and status.
Muninn GEMINI.md
Gemini CLI instructions for wjohns989/Muninn, covering muninn mcp — sota+ development context, 🚀 sota+ development philosophy, 🛠 operational guidelines (always-on), 🏗 system architecture and 📂 project structure.