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 Rainnystone/skill-orchestration-system --skill sosgit clone --depth 1 https://github.com/Rainnystone/skill-orchestration-systemWrote 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/rainnystone/skill-orchestration-system/sos)<a href="https://agentmods.dev/skills/rainnystone/skill-orchestration-system/sos"><img src="https://agentmods.dev/badge/skills/rainnystone/skill-orchestration-system/sos.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 | $0.00039 | $0.00367 |
| Opus 5 | $0.00019 | $0.00183 |
| Sonnet 5 | $0.00008 | $0.00073 |
| Haiku 4.5 | $0.00004 | $0.00037 |
Grade A, and why
sos 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 8d 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.
What it actually says
SOS Skill Orchestration
Use this skill for workflows around Skill Orchestration System (SOS) on Codex or Claude Code: inspecting active skills, proposing packs, creating reviewable plans, applying approved plans, activating packs, checking status, and restoring backups.
Default stance:
- Start in no-global-install mode.
- Use
scripts/sos_doctor.pyto detect whether SOS can run and which hosts are visible. - Resolve the host (
--host codexor--host claude) before any write command. - Prefer read-only or dry-run commands before any write.
- Keep deterministic writes in the SOS CLI.
- Do not edit Codex config, Claude
.sos-archive/, SOS vaults, manifests, registry files, backups, or generated pointer skills by hand.
Progressive disclosure:
- Read
references/execution-modes.mdwhen local capability is uncertain. - Read
references/workflows.mdfor the specific operation the user requested. - Read
references/safety-model.mdbefore any write, restore, cleanup, sync apply, or source deletion. - Read
references/codex.mdfor Codex-specific config or skill-root behavior. - Read
references/claude-code.mdfor Claude-specific archive and skill-root behavior.
Do not load every reference up front. Do not paste the full CLI reference unless the user asks for command details or the selected workflow needs exact commands.
Keep README.md and README_CN.md aligned when user-facing install, usage, or workflow entry points change.
What ships with it
6 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.
- 8d ago First seen · 27 lines · 39 tokens per session scan A 74535446f880
sos is a skill published in the GitHub repository Rainnystone/skill-orchestration-system (10 stars, last pushed 2mo ago), licensed MIT. It adds 39 tokens to every session and 367 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
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
interview
Ask one useful structured question at a time only when material product/implementation choices are genuinely missing; remember answers and produce a brief/spec. Discoverable facts should be investigated instead of asked.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
printing-press-import
Bring a published CLI from the public library into the internal library so it's identical to a freshly-generated copy — module path reverted, manuscripts placed alongside, ready for /printing-press-polish or /printing-press-emboss. Use when the public library has a CLI you don't have locally, or to recover from a…
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.