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 skills/stone16/multica-agent-team/sync-multicanpx skills add stone16/multica-agent-team --skill sync-multicagit 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/skills/stone16/multica-agent-team/sync-multica)<a href="https://agentmods.dev/skills/stone16/multica-agent-team/sync-multica"><img src="https://agentmods.dev/badge/skills/stone16/multica-agent-team/sync-multica.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 | $0.00036 | $0.01104 |
| Opus 5 | $0.00018 | $0.00552 |
| Sonnet 5 | $0.00007 | $0.00221 |
| Haiku 4.5 | $0.00004 | $0.00110 |
Grade A, and why
sync-multica 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sync Multica
Treat the repository as desired state and Multica as deployed state. Plan first, write only after explicit authorization, and prove convergence with a fresh read.
Safety Contract
- Run from this repository's root.
- Require
AGENTS.mdandCLAUDE.mdto be byte-identical. - Never commit workspace IDs, agent IDs, mention links, tokens, runtime IDs, or private environment values.
- Resolve deployment identity from
deployments/agents.jsonlogical names and current remote reads. Never guess an ambiguous agent, runtime, skill, or Squad. - Never automatically archive an agent or Squad or remove an extra Squad member. Report the drift and require a separately reviewed destructive migration.
- Apply only from a clean
mainwhoseHEADequalsorigin/main. - Redact tokens and UUIDs from reported evidence. Agent, runtime-provider, workspace, and Squad names are acceptable.
Managed State
| Source | Multica state |
|---|---|
workspace-context.md |
Workspace context |
agents/<profession>/personality.md |
Agent instructions |
agents/<profession>/skill.md |
Profession skill content and attachments |
deployments/agents.json |
Logical instance name, profession, runtime provider, and model intent |
squads/*/squad.json |
Squad name, description, leader, membership, and squad-local roles |
squads/*/instructions.md |
Squad instructions |
The two reconcilers are intentionally separated:
scripts/sync-topology.pyresolves instances and persistent Squads. It may create only instances markedcreate_if_missingand missing tracked Squads; it does not delete or prune.scripts/sync-multica.shsynchronizes company context and Profession Profile content for already-resolved instances.
Workflow
-
Validate the checkout and files:
git fetch origin main test "$(git branch --show-current)" = main test -z "$(git status --porcelain)" test "$(git rev-parse HEAD)" = "$(git rev-parse origin/main)" cmp -s AGENTS.md CLAUDE.md tests/sync-topology.test.py tests/sync-multica.test.sh bash tests/pr-sweep.test.sh
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 112 lines · 36 tokens per session scan A 76026dfcfa80
sync-multica is a skill published in the GitHub repository stone16/multica-agent-team (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 36 tokens to every session and 1,104 once invoked, about $0.0002 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 skills, from other repositories
agent-self-scheduling
Schedule AI agent runs with cron, loops, or external clocks while avoiding unsafe tight autonomous timers.
llm-integration
LLM integration patterns for function calling, streaming responses, local inference with Ollama, and fine-tuning customization. Use when implementing tool use, SSE streaming, local model deployment, LoRA/QLoRA fine-tuning, or multi-provider LLM APIs.
junjo-evaluation
Turn a developer's product-quality objective into a complete Junjo Studio-backed evaluation workflow. Use when a coding agent needs to establish a baseline, design or generate typed cases, run or resume application-owned Node, Workflow, or Agent targets, inspect outcomes and exact trace evidence, compare a candidate…
platform_management
/workspace-root = volume mount of parent dir.
github_read
Read access: repos, issues, PRs, files, branches, workflows, runs.
gitlab_read
Read access: projects, issues, MRs, files, pipelines, members.