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 BusyBee3333/sol-governed-codex --skill sol-governed-workersgit clone --depth 1 https://github.com/BusyBee3333/sol-governed-codexWrote 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/busybee3333/sol-governed-codex/sol-governed-workers)<a href="https://agentmods.dev/skills/busybee3333/sol-governed-codex/sol-governed-workers"><img src="https://agentmods.dev/badge/skills/busybee3333/sol-governed-codex/sol-governed-workers/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/busybee3333/sol-governed-codex/sol-governed-workers"><img src="https://agentmods.dev/badge/skills/busybee3333/sol-governed-codex/sol-governed-workers.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00498 |
| Opus 5 | $0.00019 | $0.00249 |
| Sonnet 5 | $0.00008 | $0.00100 |
| Haiku 4.5 | $0.00004 | $0.00050 |
Grade A, and why
sol-governed-workers 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 9d 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sol-Governed Workers
Keep the root responsible for requirements, integration, and user communication. Delegate only when bounded work, specialization, or parallelism repays the extra call. Keep max_depth = 1.
Set up
Let <skill-dir> be the directory containing this file, including when loaded from a plugin cache.
bash <skill-dir>/scripts/install_global_infra.sh
bash <skill-dir>/scripts/validate_setup.sh
Add the optional every-task project contract only after reconciling existing instructions:
bash <skill-dir>/scripts/install_project_contract.sh /absolute/project
Use --append for a compatible unmanaged AGENTS.md, --update for a reviewed stale managed block, and --live-probe during validation only when spending one model call is acceptable.
Route work
- Root: settle requirements, make cross-cutting decisions, integrate, verify, and report.
luna_worker: mechanical work with settled decisions.terra_worker: bounded implementation needing local judgment.sol_advisor: concise plan or evidence judgment; never implementation.
Ask the user directly for missing product intent. Before editing, request a Sol plan gate for architecture, authentication, security, billing, migrations, destructive operations, public interfaces, or a concrete unresolved technical risk.
Give each worker one ownership area, acceptance criteria, allowed scope, required verification, and an escalation condition. Inspect its diff and command results; a summary is not proof.
Gate completion
After root verification, request a Sol final gate for changes to runtime behavior, dependencies or configuration, persistent data, security, or public interfaces. It may be skipped for verified docs-only, comments-only, formatting-only, or generated-output-only changes. When uncertain, gate it.
Send only the task contract, targeted diff or file references, verification results, observed behavior, and known risks. Follow references/review-protocol.md.
What ships with it
11 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.
- agents/openai.yaml 232 B
- assets/AGENTS.sol-governed.md 1.1 KB
- assets/agents/luna-worker.toml 734 B
- assets/agents/sol-advisor.toml 958 B
- assets/agents/terra-worker.toml 815 B
- assets/sol-governed-high.config.toml 238 B
- assets/sol-governed.config.toml 240 B
- references/review-protocol.md 1.2 KB
- scripts/install_global_infra.sh 4.2 KB runs code
- scripts/install_project_contract.sh 3.4 KB runs code
- scripts/validate_setup.sh 8.5 KB runs code
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.
- 9d ago First seen · 45 lines · 39 tokens per session scan A 53ee3f16a382
sol-governed-workers is a skill published in the GitHub repository BusyBee3333/sol-governed-codex (41 stars, last pushed 1mo ago), licensed MIT. It adds 39 tokens to every session and 498 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 2026-08-30.
Other skills, from other repositories
sw-handoff
Use when the user runs /sw-handoff or wants to carry over context before /clear — prepares a structured handoff (keep/discard file decision + summary + next task) and returns a load token for the next segment.
sw-load
Restore a session handoff into context. Use when the user provides a handoff token, asks to resume or continue previous work, the session-start output announces a handoff, or you are about to call loadhandoff.
sw-explain
Use when the user asks what a Session Watcher metric means (br, mf, pp, u, wall, sweet, valley) or runs /sw-explain — explains the requested metric in plain language and contextualizes it for the current session.
mainline
Use for coding-agent work in Git repos that use or may need Mainline, or when users mention Mainline, intents, agent autonomy, agentauthority, maxautonomy, stop lines, allowedboundary, inspectorstop, beforecommit/proposedintent/openedpr, current-instruction overrides, commit/seal handoff, push/PR review boundaries…
breaking-down-the-work
Splits scope into a product-first work breakdown that follows the 100% rule, keeps pieces from overlapping, uses outline numbers, and gives every piece a dictionary entry. Use when an epic, feature, or new subsystem needs a clean split into deliverables, or one source of truth before folders or work begin. Do not use…
staying-on-mission
Tests the current work against a written, lasting mission anchor and forces one choice, re-anchor, escalate, or stop. Use when an agent keeps finishing tasks but the work drifts from the goal, scope creeps, the same action repeats in a loop, or standards slip one small step at a time. Do not use for a tiny edit with…