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 romarayt/raytsystem-public-os --skill raytsystem-savegit clone --depth 1 https://github.com/romarayt/raytsystem-public-osWrote 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/romarayt/raytsystem-public-os/raytsystem-save)<a href="https://agentmods.dev/skills/romarayt/raytsystem-public-os/raytsystem-save"><img src="https://agentmods.dev/badge/skills/romarayt/raytsystem-public-os/raytsystem-save/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/romarayt/raytsystem-public-os/raytsystem-save"><img src="https://agentmods.dev/badge/skills/romarayt/raytsystem-public-os/raytsystem-save.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 | $0.00053 | $0.00435 |
| Opus 5 | $0.00026 | $0.00217 |
| Sonnet 5 | $0.00011 | $0.00087 |
| Haiku 4.5 | $0.00005 | $0.00044 |
Grade A, and why
raytsystem-save 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 10d 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
raytsystem SAVE
Inputs and outputs
- Accept bounded synthesis text, safe title, and one or more verified active evidence segment IDs.
- Return one idempotent
SaveResult, typed staging bundle, and escaped DRAFT preview.
Write scope
- Write only
ops/staging/<run_id>/,ops/runs/<run_id>/, coordination state, andartifacts/drafts/. - Never write
ledger/, events, generated knowledge, Git refs, outbox, or external systems.
Preflight
- Run
uv run raytsystem agent preflight --skill raytsystem-save --write --json. - Obtain evidence IDs from a verified generation-bound QUERY result.
- Reject secret text, unsafe title/path, stale generation, linked output/control paths, or uncited synthesis.
Workflow
- Run
uv run raytsystem save "SYNTHESIS" --title "TITLE" --evidence SEGMENT_ID --json. - Inspect
bundle.json, typed proposal artifacts, and preview hashes. - Leave the result in DRAFT/awaiting-review state.
Validation
- Bind the operation key to generation, text/title hashes, evidence, schemas, component, and config.
- Verify a repeated/concurrent identical SAVE returns the same artifact and no canonical mutation.
- Exercise evals
m3-save-goldenandm3-save-adversarial.
Recovery
- Re-run the exact SAVE; join the existing operation and verify its hash-closed bundle.
- Keep incomplete staging for diagnosis and fail closed on generation change.
Stop and approval conditions
- Stop before promotion, send, publish, upload, outbox dispatch, push, PR, or release.
- Require a later explicit reviewed promotion design; M2/M3 SAVE cannot promote by construction.
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.
- 10d ago First seen · 45 lines · 53 tokens per session scan A 01cc8b5a4be7
raytsystem-save is a skill published in the GitHub repository romarayt/raytsystem-public-os (143 stars, last pushed yesterday), licensed Apache-2.0. It adds 53 tokens to every session and 435 once invoked, about $0.0003 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
shodh-memory
Persistent memory system for AI agents. Use this skill to remember context across conversations, recall relevant information, and build long-term knowledge. Activate when you need to store decisions, learnings, errors, or context that should persist beyond the current session.
sandbox-environment
Sandbox API reference, proven patterns, and library recommendations for evaluateexpression.
vault-health-batch
Autonomous batch mode for Vault Health findings. Works through orphans, missing backlinks, and tags in batches without asking on every fix.
llm-wiki
Build and maintain an LLM-curated personal knowledge base — the "LLM Wiki" pattern from Andrej Karpathy's April 2026 gist. Use this skill whenever the user wants to ingest a source (paper, article, transcript, PDF, notes) into a persistent compounding knowledge base, ask a question against accumulated notes, lint or…
continuous-attention
Use when the user asks to keep watching an external state, notify them when something changes or a condition is met, remember fresh external state across turns, or manage an existing Context Binding or Event Subscription.
chatcrystal-task-writeback
Write reusable ChatCrystal task memories after substantive work completes. Use when implementation or debugging produced a durable fix, pitfall, pattern, or decision worth preserving, and when the environment can either persist it through writetaskmemory or emit a structured memory candidate for later save.