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/stone16/multica-agent-team/agents-mdgit clone --depth 1 https://github.com/stone16/multica-agent-teamWrote 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/stone16/multica-agent-team/agents-md)<a href="https://agentmods.dev/instructions/stone16/multica-agent-team/agents-md"><img src="https://agentmods.dev/badge/instructions/stone16/multica-agent-team/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 | $0.02247 | $0.02247 |
| Opus 5 | $0.01123 | $0.01123 |
| Sonnet 5 | $0.00449 | $0.00449 |
| Haiku 4.5 | $0.00225 | $0.00225 |
Grade A, and why
multica-agent-team 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- multica-agent-team CLAUDE.md — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Company Operating System
This repository is the source of truth for the reusable agent company deployed to Multica. These rules apply regardless of whether Claude, Codex, Grok, or another model edits or executes the repository.
AGENTS.md and CLAUDE.md are intentionally byte-identical mirrors. Edit both in the same change and verify with cmp -s AGENTS.md CLAUDE.md. Neither file is an adapter for one runtime.
Source of Truth
Use this precedence when facts conflict:
- The user's explicit instruction for the current task.
AGENTS.mdandCLAUDE.md, which must say the same thing.workspace-context.mdfor company-wide Multica behavior.squads/*/squad.jsonandsquads/*/instructions.mdfor a functional Squad.agents/<profession>/personality.mdandagents/<profession>/skill.mdfor stable professional capability.- The current Project ledger and Issue Definition of Done for domain and run context.
README.mdfor human onboarding.
Do not silently blend conflicting rules. Follow the higher source, state the conflict, and flag the lower source for correction.
Company Ontology
Keep these objects separate:
- Profession Profile: stable, domain-neutral responsibility, judgment, tools, evidence contract, and prohibited work. It lives under
agents/<profession>/. - Agent Instance: a deployed identity with one primary Profession Profile, runtime/model, permissions, and capacity. Multiple instances may share one profile.
- Squad Definition: a long-lived functional routing and operating contract. It has a leader, members, squad-local roles, activation rules, workflow, and entry/exit artifacts.
- Squad Run: one bounded Issue, project phase, incident, or objective. Run state is fresh by default.
- Project or Domain Ledger: durable facts, evidence, decisions, PRDs, designs, code, evaluations, and incident records for one business domain.
Long-lived Squad identity does not authorize long-lived unreviewed conversation memory. Promote reviewed facts and decisions to a ledger; do not treat logs, traces, metrics, or chat history as durable product state.
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 · 157 lines · 2,247 tokens per session scan A 088f50f00396
multica-agent-team AGENTS.md is an instructions file published in the GitHub repository stone16/multica-agent-team (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 2,247 tokens to every session, about $0.0112 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
playbooks CLAUDE.md
Instructions for playbooks-ai/playbooks, covering claude.md, project overview, core architecture, framework components and key architectural insights.
junjo AGENTS.md
Instructions for mdrideout/junjo, covering junjo platform agents.md, developer philosophy, scope and complexity, repository ownership and boundary rules.
Herdforge CLAUDE.md
Claude Code instructions for Kampe/Herdforge, covering claude.md - build bootstrap & routing protocol, 1. quick invariants (hard rules), 2. fast commands, build binary and run preflight, unit tests, and build.
co-evolution CLAUDE.md
Instructions for alanshurafa/co-evolution, covering co-evolution - cross-ai document refinement, default rule, components, co-evolution skill (skills/co-evolution/) and co-evolve bouncer (co-evolve-bouncer.sh).
orcho-mcp AGENTS.md
Instructions for symphos-ai/orcho-mcp, covering orcho-mcp instructions, scope, local instruction files, workspace development pipeline and stable install is read-only.
powernode-platform CLAUDE.md
Claude Code instructions for nodealchemy/powernode-platform, covering claude.md, project overview, core models, where guidance lives and memory & knowledge.