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 mrDesign-ww/vault-os --skill savegit clone --depth 1 https://github.com/mrDesign-ww/vault-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/mrdesign-ww/vault-os/save)<a href="https://agentmods.dev/skills/mrdesign-ww/vault-os/save"><img src="https://agentmods.dev/badge/skills/mrdesign-ww/vault-os/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/mrdesign-ww/vault-os/save"><img src="https://agentmods.dev/badge/skills/mrdesign-ww/vault-os/save.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 | $0.00029 | $0.00428 |
| Opus 5 | $0.00015 | $0.00214 |
| Sonnet 5 | $0.00006 | $0.00086 |
| Haiku 4.5 | $0.00003 | $0.00043 |
Grade A, and why
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 7d 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
Save this session
Use this vault-local workflow instead of the generic plugin save command.
- Determine the active zone from the conversation. Default to work. Never read or write another zone.
- Acquire
bash scripts/wiki-lock.sh acquire .vault-meta/write/ZONE --ttl 3600. Every batch writer for that zone uses this same lock path. Record the returned token. Use afinallypath that releases this exact token after success or failure. After every long phase and before later writes, build and checkpoint, runrenewthencheck. Never reacquire over an expired record and continue partial work. - Preserve raw session material only when useful. It is L0 and goes to the active inbox. Work inbox is
wiki/workspace/projects/inbox/. - Materialize explicit user decisions and verified reusable outcomes as separate project or resource pages. Use explicit L1 with
memory_provenance, or explicit L2 for canonical state and workflows. Automatically inferred or uncertain claims go throughmemory-candidates.pyand remain L0 until reviewed. Evidence paths remain L0. - Update the active zone index, project index, append-only log, then overwrite its hot cache. Do not call the plugin repository's
wiki-mode.py. - Run
memory-model.py scan, thenbuild --zone ZONE --lock-token TOKEN, thenvalidate --zone ZONE --lock-token TOKEN. The build is the final wiki write. - Check the token again, then create a local Git checkpoint containing only this save's durable files. Never push. Release in the
finallypath, then run one project-scoped retrieval acceptance query with the matching named role loadout and inspect its snippet and context budget.
If validation or checkpoint fails, release the token, report the exact state, then reacquire before repair. Do not claim that context was saved while retrieval is stale or the acceptance query fails.
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.
- 7d ago First seen · 19 lines · 29 tokens per session scan A ea5947ba6e67
save is a skill published in the GitHub repository mrDesign-ww/vault-os (2 stars, last pushed 5d ago), licensed MIT. It adds 29 tokens to every session and 428 once invoked, about $0.0001 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 2026-09-05.
Other skills, from other repositories
agent-carnet
Use this skill when the user asks to save, recall, find, or organize notes. Triggers on: 'remember this', 'save this', 'note this', 'what did we discuss about...', 'check the notebook', 'find in carnet'. Also use proactively when discovering findings worth preserving across sessions.
neat-freak
Knowledge and governance closeout: reconcile project docs, rule files (CLAUDE.md/AGENTS.md), authorized agent memory, and workspace residue with what the code and runtime actually do, so the next session or the next person starts from one current answer. Trigger when the user names "neat-freak", "洁癖", or "/neat" — and…
mnemos
Task-scoped memory lifecycle — typed MnemoGraph prevents lossy context compaction by treating facts/decisions/code-refs/handoffs as distinct node types with per-type eviction policies.
grimoire
Use when the user says 'update context', 'update claude', 'save library', or after significant project changes.
keep-the-why
Extract and preserve the reasoning code cannot explain - decisions, rejected alternatives, workarounds, incidents, constraints - plus project setup and maintainer interviews. Not for what changed (see Keep a Changelog) - only why. Also the place for complaints, feedback and settings changes about this skill itself.
ln-31-performance-optimizer
Profiles and improves a measured latency, throughput, CPU, memory, or I/O problem. Not for speculative tuning or cosmetic refactoring.