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 softspark/ai-toolkit --skill orchestrategit clone --depth 1 https://github.com/softspark/ai-toolkitWrote 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/softspark/ai-toolkit/orchestrate)<a href="https://agentmods.dev/skills/softspark/ai-toolkit/orchestrate"><img src="https://agentmods.dev/badge/skills/softspark/ai-toolkit/orchestrate/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/softspark/ai-toolkit/orchestrate"><img src="https://agentmods.dev/badge/skills/softspark/ai-toolkit/orchestrate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 9 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
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 | $0.00026 | $0.00853 |
| Opus 5.5 | $0.00010 | $0.00341 |
| Sonnet 5.5 | $0.00005 | $0.00171 |
| Haiku 4.5 | $0.00003 | $0.00085 |
Grade A, and why
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 13d 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/orchestrate - Multi-Agent Coordination
$ARGUMENTS
Only in Claude Code, apply the model-routing-patterns skill when choosing
executors or creating agent definitions. Delegate to codex:codex-rescue only
when its plugin is installed, enabled and callable in this session. Otherwise
use the installed native agents and their configured models. A context without
the Agent tool returns the dispatch decision to its supervisor; it does not
invent a tool or bypass the client. Preserve explicit user choices and verify
actual completion before accepting a delegated result.
Choose the available execution mode
When the Agent tool is available, decompose the task and delegate owned work to real agents. The supervisor integrates and verifies their results. If the runtime has no delegation support, do the authorized work in the current session and report that limitation. Never invent agent calls or present role-play as delegation.
Step 1 — Decompose
Analyze the task and identify 3–6 sub-domains (e.g. backend, frontend, security, testing, docs). Define clear file ownership per domain so agents don't conflict.
Present the decomposition and obtain any approval not already covered by the user's instructions. Preserve approval already given for the task.
Step 2 — Spawn agents in parallel (REQUIRED)
When available, call the Agent tool for independent sub-domains in parallel,
within the runtime's concurrency and nesting limits. Execute dependent tasks in
order and use the current-session fallback when delegation is unavailable.
Example for a feature implementation task:
Agent(subagent_type="backend-specialist", prompt="...", ...)
Agent(subagent_type="frontend-specialist", prompt="...", ...)
Agent(subagent_type="test-engineer", prompt="...", ...)
Agent(subagent_type="security-auditor", prompt="...", ...)
Each agent prompt MUST include:
- The original user task
- The specific sub-task this agent owns
- File paths this agent is allowed to modify
- Success criteria for this agent's work
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.
- 13d ago Changed · +16 lines f7b70bd8e789
- 1mo ago First seen · 87 lines · 26 tokens per session scan A f2a440e9734e
orchestrate is a skill published in the GitHub repository softspark/ai-toolkit (180 stars, last pushed yesterday), licensed Apache-2.0. It adds 26 tokens to every session and 853 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
orchestrator
Providerneutrales Protokoll zum Zerlegen komplexer Aufgaben, zum Beauftragen unabhängiger Worker und zur evidenzbasierten Abnahme ihrer Ergebnisse.
workflow-extract
Baut aus einem Chatverlauf oder aus bestehenden Automatisierungs-Prompts (z. B. eines anderen Agenten-Systems) eine selbstlaufende, user-neutrale Workflow-Automatisierung: einen wiederkehrenden Prompt bzw. Automations-Skill für Cron/Schedule/Loop. Alias: automations-extractor. Nutze diesen Skill bei „mach daraus eine…
project-onboarding
Standard procedure for onboarding new software projects: Feature analysis, code quality review, onboarding checklist, and task creation.
skill-register-care
Pflege-Skill, der das dreiteilige Skill-Register konsistent hält (code-skill-index-Kataloge, Skill-Index, SKILL-MAP Family-/Routing-Map). Nutze diesen Skill für einen Drift-Check zwischen dem realen Skill-Inventar und dem dokumentierten Register: fehlende oder zu viele Einträge melden, Counts korrigieren, Stand-Datum…
data-governance-guide
Gouvernance des données incluant catalogues, lineage, qualité, ownership, politiques et metadata management. Se déclenche avec "data governance", "gouvernance données", "data catalog", "data lineage", "metadata", "data ownership".
it-commercial-proposal
Génération d'offres commerciales pour des projets IT — lots techniques, chiffrage jour-homme, hypothèses, SLA, TMA et annexes techniques. Se déclenche avec "offre commerciale IT", "proposition commerciale IT", "devis IT", "appel d'offres", "offre technique et financière", "chiffrage jour-homme", "SOW", "réponse à AO".…