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/jamillazarev/multica-ops/agents-mdgit clone --depth 1 https://github.com/jamillazarev/multica-opsWrote 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/jamillazarev/multica-ops/agents-md)<a href="https://agentmods.dev/instructions/jamillazarev/multica-ops/agents-md"><img src="https://agentmods.dev/badge/instructions/jamillazarev/multica-ops/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 | $0.06009 | $0.06009 |
| Opus 5 | $0.03004 | $0.03004 |
| Sonnet 5 | $0.01202 | $0.01202 |
| Haiku 4.5 | $0.00601 | $0.00601 |
Grade A, and why
multica-ops 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 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.
How it starts
The opening of the file, as written. The whole thing — 314 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent entry point
This repository ships one skill: multica-ops — a Mops (Executive Advisor) that builds and runs an autonomous company of AI agents on Multica.
Using the skill? Whatever harness you are (Claude Code, Codex, Cursor, Windsurf, Gemini CLI, …): read SKILL.md and follow it. Slash commands are a Claude Code plugin convenience; every flow works from natural language in any agent — "set up my team", "join this project", "status", "add a feature: …".
Requires the multica CLI on the machine, pointed at a workspace:
multica setup cloud, or multica setup self-host --server-url … for your own server.
Changing this repository? Read this part.
Two scripts guard it. Run them; they are fast and they have caught real defects:
bash scripts/preflight.sh # form: is the documentation well-made?
python3 scripts/verify.py --live # truth: do the commands and sources still exist?
What the automation cannot check — and what you must therefore read
The scripts verify shape and existence. They are blind to whether a paragraph is still correct, and every expensive defect this repo has shipped was of exactly that kind: a statement that parsed perfectly, linked correctly, and was false. So before you commit, read for these six things — as a human, or as an agent asked to review, but never assume a green hook covered them.
1 · Does this contradict another file? Rules live in several places on purpose (core, companion, guide template) and drift apart silently. The core once said squad leaders "never implement" while ROLES made working craft leads out of them; both files were internally consistent and the pair was wrong. If you change a rule, grep for it everywhere and fix every copy in the same commit.
2 · Is the framing still the current one? Text ages by being outrun, not by breaking. The docs-site introduction described version 1.x long after 2.1 shipped — every sentence true when written, the whole page misleading. When you add a capability, ask what page now describes an older product.
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.
- 4d ago First seen · 314 lines · 6,009 tokens per session scan A 3828d3341a9f
multica-ops AGENTS.md is an instructions file published in the GitHub repository jamillazarev/multica-ops (10 stars, last pushed 6d ago), licensed Apache-2.0. It adds 6,009 tokens to every session, about $0.0300 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.
Other instructions, from other repositories
build_a_product_agent CLAUDE.md
Instructions for ADW-19/build_a_product_agent, covering claude.md, 项目本质（readme 概览之外）, 目录与编号规范, 文章写作规范（新增/修改文章时必须遵循） and 常用操作.
BuildersGate CLAUDE.md
Claude Code instructions for Thepizzapie/BuildersGate, covering setting up builders gate for a user, ask two things first, install, point it at a game and keys.
growmos AGENTS.md
Instructions for codician-team/growmos: This repository keeps a knowledge graph in .growmos/ (entities, typed relations, provenance, profiles, a journal). It is the shared world model that survives context windows. Treat it as memory you read at the start of work and write to as you develop. Zero-config commands.
akidevrule GEMINI.md
Instructions for lacvietanh/akidevrule, covering gemini.md — ag rules bootstrap, 1. single source of truth and 2. separation of concerns.
akidevrule CLAUDE.md
Instructions for lacvietanh/akidevrule, covering akidevrule, project role, source of truth, file naming conventions and rule authoring principles.
awesome-agent-infrastructure CLAUDE.md
Instructions for backblaze-labs/awesome-agent-infrastructure, covering claude.md — awesome-agent-infrastructure, what this list is, scope and files, schema, workflow, rules.