sos
Skill10 starsChanged 6 months agoMITView on GitHub
Use when helping a user inspect, organize, plan, apply, activate, back up, or restore SOS-managed agent skill packs on Codex or Claude Code without assuming global installation.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- parkkarl/claude-skill-sostheir own version, first seen May 13, 2026
- MetalLegBob/solana-vibes-kittheir own version, first seen Feb 25, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- MetalLegBob/solana-vibes-kit★ 19same name
- parkkarl/claude-skill-sos★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repositoryOne other file it gives its agents.
- AGENTS.mdAGENTS.md
The file
Show its rules and text
We split this skill into the rules it gives an agent
13 rules. About 0 are common, 5 are distinctive, and 8 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
8
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 7
Use this skill for workflows around Skill Orchestration System (SOS) on Codex or Claude Code: inspecting active skills, proposing packs, …
- Distinctive: line 10
Start in no-global-install mode.
- Very specific: line 11
Use scripts/sos_doctor.py to detect whether SOS can run and which hosts are visible.
- Distinctive: line 13
Prefer read-only or dry-run commands before any write.
- Distinctive: line 14
Keep deterministic writes in the SOS CLI.
- Very specific: line 15
Do not edit Codex config, Claude .sos-archive/, SOS vaults, manifests, registry files, backups, or generated pointer skills by hand.
- Very specific: line 18
Read references/execution-modes.md when local capability is uncertain.
- Very specific: line 19
Read references/workflows.md for the specific operation the user requested.
- Very specific: line 20
Read references/safety-model.md before any write, restore, cleanup, sync apply, or source deletion.
- Very specific: line 21
Read references/codex.md for Codex-specific config or skill-root behavior.
- Very specific: line 22
Read references/claude-code.md for Claude-specific archive and skill-root behavior.
- Distinctive: line 24
Do not load every reference up front.
- Very specific: line 26
Keep README.md and README_CN.md aligned when user-facing install, usage, or workflow entry points change.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
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.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

