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 skills add AnmarHani/SwarmVault --skill swarm-orchestrategit clone --depth 1 https://github.com/AnmarHani/SwarmVaultWrote 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/anmarhani/swarmvault/swarm-orchestrate)<a href="https://agentmods.dev/skills/anmarhani/swarmvault/swarm-orchestrate"><img src="https://agentmods.dev/badge/skills/anmarhani/swarmvault/swarm-orchestrate.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 | $0.00109 | $0.07127 |
| Opus 5 | $0.00055 | $0.03564 |
| Sonnet 5 | $0.00022 | $0.01425 |
| Haiku 4.5 | $0.00011 | $0.00713 |
Grade A, and why
swarm-orchestrate 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 7d 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 — 485 lines — stays where its author put it; the contents beside it link to each section on GitHub.
swarm-orchestrate — optional local autonomy
Gate: this add-on is disabled by default. Do not enable it, configure write access, or start workers unless the user explicitly asks. Tickets and atomic claims remain the source of truth; signals and controls never override a healthy claim.
What this is for (read before configuring anything)
The goal is the right model on the right task, at the lowest token cost — parallelism is only one means to that end, and often not the right one. So orchestration has two separate decisions, and conflating them is the classic mistake:
- Fit — always on, at every level. Which platform, model, and reasoning effort each task deserves, from its kind (design / planning / coding / review / docs), its size, and each platform's remaining usage. A docs ticket never burns a flagship model; a design ticket never gets a cheap one. This is not something the user buys by going slower.
- Acceleration — the speed level, and the only thing the user chooses. How eagerly work is handed to other agents instead of done in the current session.
Enable — two design questions, then the numbers only they can see
- Confirm the project is registered and has dependency-ready tickets.
- Ask the two design questions:
- "Which agentic platforms do you have?" — the tools installed on their machine:
claude-code,codex(verified),gemini,opencode,droid,cursor,copilot,amp(best-effort), or any other agent CLI by name. Offer the list and an "other" option; a platform with no adapter still works as a cooperative worker, or gets a--launch-cmdtemplate. - "How much acceleration is allowed?" —
slow|standard|fast(below). Plus: may these workers edit code?
- "Which agentic platforms do you have?" — the tools installed on their machine:
- Never ask for a worker count, a concurrency ceiling, or a model name. Those are not the user's decisions: ceilings derive from the level, and the platform+model per task come from fit. Asking for a model produces exactly the wrong answer — one model cannot be right for both a large design task and a docs chore.
- Do ask for the usage numbers — you cannot read them. Per platform: which plan are you
on · what limits does it show (per session/day, per week, both) · when do they reset · are
any other sessions running I can't see · may I schedule a continuation automatically if a
limit is about to run out? Look up per-model costs yourself first; ask only if the lookup
fails. See Usage — you are blind without the user below; the full interview and the
per-platform notes are in
references/usage-limits.md. - One command:
What ships with it
2 files 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.
- 7d ago First seen · 485 lines · 109 tokens per session scan A 513ec6c1a06f
swarm-orchestrate is a skill published in the GitHub repository AnmarHani/SwarmVault (5 stars, last pushed 1mo ago), licensed MIT. It adds 109 tokens to every session and 7,127 once invoked, about $0.0005 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
data-integrity-review
Data integrity specialist for schema correctness, owner isolation, projections, hash chains, log separation, snapshots, and replay consistency. Use when validating that data remains correct under sync and persistence rules.
architect-review
use when user ask to review spec.
coder
Use when the task is to implement code changes from an assigned scope, including bug fixes, follow-ups, rejects, or current-worktree repair.
skill-creator
Use when the user asks to create or update a skill.
ui-be-binding-skill
Use when binding backend/API data into an already-approved frontend UI without changing approved layout, copy, visual design, component hierarchy, or interaction states.
planner
Use when the user asks to create, write, or review a docs/plans plan.