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 Evanciel/stellavault --skill vault-decisiongit clone --depth 1 https://github.com/Evanciel/stellavaultWrote 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/evanciel/stellavault/vault-decision)<a href="https://agentmods.dev/skills/evanciel/stellavault/vault-decision"><img src="https://agentmods.dev/badge/skills/evanciel/stellavault/vault-decision/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/evanciel/stellavault/vault-decision"><img src="https://agentmods.dev/badge/skills/evanciel/stellavault/vault-decision.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 | $0.00056 | $0.00342 |
| Opus 5 | $0.00028 | $0.00171 |
| Sonnet 5 | $0.00011 | $0.00068 |
| Haiku 4.5 | $0.00006 | $0.00034 |
Grade A, and why
vault-decision 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.
What it actually says
Decision journal (ADR)
Record decisions with their why, so future sessions can answer "why is it like this?" from the vault instead of guessing.
Look up a past decision
Call find-decisions with the topic. Present matches as: decision — rationale — date — [[source note]]. If nothing matches, fall back to search before concluding it was never recorded.
Log a new decision
- Extract the three parts from the conversation. If any is missing, ask one short question — do not invent:
- Decision — what was chosen ("Use X instead of Y")
- Rationale — why (the non-obvious reason; failures/constraints count)
- Alternatives — what was rejected and why
- Check
find-decisionsfirst so you extend rather than duplicate an existing ADR on the same topic. - Show the draft to the user and get a yes before writing — one compact block: title / decision / rationale / alternatives.
- On approval, call
log-decisionwith the finalized text. Confirm with the created note reference.
Rules
- Never log without explicit user approval of the exact text.
- One decision per entry — split compound decisions.
- Write in the user's language; keep technical identifiers (library names, versions) verbatim.
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 · 29 lines · 56 tokens per session scan A 1c4a10987d65
vault-decision is a skill published in the GitHub repository Evanciel/stellavault (4 stars, last pushed 15d ago), licensed MIT. It adds 56 tokens to every session and 342 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 2026-08-31.
Other skills, from other repositories
cortex-memory
Persistent cognitive memory for AI agents — query, record, review, and consolidate knowledge across sessions with spreading activation, FSRS scheduling, and NLI contradiction detection.
sibyl
Persistent memory and task coordination for this project. Invoke for any prompt about past work, project state, in-progress tasks, prior decisions, gotchas, or capturing a non-obvious learning. Also covers semantic search across project knowledge and external docs.
brainctl
Unified agent memory CLI — read, write, search, and maintain the shared memory spine (brain.db). Use for persistent cross-session memory, knowledge graph, event logging, decisions, affect tracking, and consolidation.
codemem
Quick reference for all 32 codemem MCP tools. Use when working with the codemem knowledge graph — finding code, traversing relationships, storing memories, or running analysis.
brain-dream
Brain maintenance -- replay conversations, fix graph quality, surface signals.
mnemon
Persistent memory CLI for LLM agents. Store facts, recall past knowledge, link related memories, manage lifecycle.