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 MSApps-Mobile/claude-plugins --skill sosa-orchestratorgit clone --depth 1 https://github.com/MSApps-Mobile/claude-pluginsWrote 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/msapps-mobile/claude-plugins/sosa-orchestrator)<a href="https://agentmods.dev/skills/msapps-mobile/claude-plugins/sosa-orchestrator"><img src="https://agentmods.dev/badge/skills/msapps-mobile/claude-plugins/sosa-orchestrator/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/msapps-mobile/claude-plugins/sosa-orchestrator"><img src="https://agentmods.dev/badge/skills/msapps-mobile/claude-plugins/sosa-orchestrator.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00192 | $0.03011 |
| Opus 5.5 | $0.00077 | $0.01204 |
| Sonnet 5.5 | $0.00038 | $0.00602 |
| Haiku 4.5 | $0.00019 | $0.00301 |
Grade A, and why
sosa-orchestrator 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 1mo 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 — 306 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SOSA Orchestrator
The resource-aware brain that decides what runs, what waits, and what stops.
Why This Exists
Every Claude session — Cowork, Claude Code, scheduled tasks — burns through a finite token budget. Without active orchestration, a low-priority health check can eat the tokens you needed for a revenue-critical invoice run. The Orchestrator solves this by maintaining a live priority×cost matrix and making smart allocation decisions throughout the session.
It integrates tightly with the SOSA Governor (which gates individual tool calls) and the Token Efficiency Audit (which optimizes long-term patterns). The Orchestrator operates at the task level — deciding which tasks deserve tokens right now.
Core Concepts
Token Budget Hierarchy
Budgets cascade from broad to narrow. The orchestrator reads these from config/budgets.json (shared with SOSA Governor):
Monthly budget (25M tokens)
→ Weekly allocation (rolling average)
→ Daily budget (minus 15% reserve)
→ Agent category budgets (revenue, communication, operations, development, monitoring)
→ Individual task estimates
Task Priority Score
Every task gets a Priority Score computed as:
Priority = (Business Impact × Urgency × Dependency Weight) / Estimated Token Cost
Where:
- Business Impact (1-10): Revenue tasks score 8-10, monitoring scores 1-3
- Urgency (1-5): Deadline-driven tasks score higher
- Dependency Weight (1-3): Tasks that unblock other tasks score higher
- Estimated Token Cost: Based on historical averages or skill complexity heuristics
Higher score = should run first. The orchestrator maintains a sorted queue.
Budget Categories (from SOSA Governor config)
| Category | Daily Budget | Priority | Overage Policy |
|---|---|---|---|
| Revenue | 150K tokens | Critical | Borrow from reserve |
| Communication | 120K tokens | High | Borrow from reserve |
| Development | 100K tokens | Medium | Notify and continue |
| Operations | 80K tokens | Medium | Queue until tomorrow |
| Monitoring | 30K tokens | Low | Throttle |
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.
- 1mo ago First seen · 306 lines · 192 tokens per session scan A 92ec2bc42a31
sosa-orchestrator is a skill published in the GitHub repository MSApps-Mobile/claude-plugins (9 stars, last pushed today), licensed MIT. It adds 192 tokens to every session and 3,011 once invoked, about $0.0008 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 2026-09-13.
Other skills, from other repositories
houseclean
Cross-drive storage audit and cleanup. Surveys all drives, finds orphaned git worktrees, large AI tool caches (.ollama, .gemini, .cursor, npm, pip), and buildable artifacts (nodemodules, .venv). Produces a prioritized action plan with specific migration commands. Use when disk space is low or worktrees need cleanup…
schedule
Manages recurring and one-off scheduled tasks. Session-scoped scheduling via CronCreate/CronDelete/CronList. Documents the cloud path for tasks that need to survive machine sleep or network drops.
career-portfolio
A portfolio-building skill for Korean job seekers that organizes projects and explains their work for development, design, marketing, and planning roles.
hr-operations
A skill for designing remote-work and team-operation policies. It covers flexible work, asynchronous communication, collaboration tools, productivity tracking, and employee experience.
collab-conflict
A guide for handling difficult workplace colleagues and recurring communication conflicts.
collab-feedback-loop
A guide for giving and receiving workplace feedback about specific actions and their effects.