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 brodewa369/roowet-semantic-vault-search --skill scanthissessiongit clone --depth 1 https://github.com/brodewa369/roowet-semantic-vault-searchWrote 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/brodewa369/roowet-semantic-vault-search/scanthissession)<a href="https://agentmods.dev/skills/brodewa369/roowet-semantic-vault-search/scanthissession"><img src="https://agentmods.dev/badge/skills/brodewa369/roowet-semantic-vault-search/scanthissession/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/brodewa369/roowet-semantic-vault-search/scanthissession"><img src="https://agentmods.dev/badge/skills/brodewa369/roowet-semantic-vault-search/scanthissession.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 | $0.00113 | $0.02000 |
| Opus 5 | $0.00056 | $0.01000 |
| Sonnet 5 | $0.00023 | $0.00400 |
| Haiku 4.5 | $0.00011 | $0.00200 |
Grade A, and why
scanthissession 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 11d 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/scanthissession — Session Scanner & Vault Writer
PURPOSE
LLMs do not automatically log errors/facts when encountered (passive instructions fail). This skill FORCES scan + write via an explicit procedure. When the agent runs this skill, it MUST read the session, classify, and write files.
WHEN TO RUN
- User: scan session, scan this session, log session ini, /scanthissession
- Or after a complex task (>10 tool calls) → run as cleanup
- Do NOT run mid-task (unless the user asks)
PROCEDURE (run step by step)
Step 1 — Get session transcript
- Default profile:
hermes sessions list→ find active session → read viasession_search(session_id=...). - Other profile:
hermes -p <profile> sessions listthensession_search. - Or read
agent.loginprofiles/<profile>/logs/if session DB is unavailable. - Read FULL transcript (user messages + tool results + agent responses).
Step 2 — Scan & classify (check ONE BY ONE)
For each item below, ask: PRESENT IN TRANSCRIPT? → if YES, add to list.
| # | Item | Folder (default profile) | Folder (profile X) | Format file |
|---|---|---|---|---|
| 1 | error/bug/mistake/traceback (real) | 01-AGENT-MEMORY/error-log/ | 01-AGENT-MEMORY//error-log/ | YYYY-MM-DD-[topic].md (Error/Root Cause/Fix/Prevention) |
| 2 | user correction of agent | 01-AGENT-MEMORY/corrections/ | 01-AGENT-MEMORY//corrections/ | YYYY-MM-DD-[topic].md |
| 3 | blocker agent cannot resolve alone | 01-AGENT-MEMORY/blockers/ | 01-AGENT-MEMORY//blockers/ | YYYY-MM-DD-[topic].md |
| 4 | design/architecture/config decision | 01-AGENT-MEMORY/decisions/ | 01-AGENT-MEMORY//decisions/ | YYYY-MM-DD-[topic].md |
| 5 | lesson learned | 01-AGENT-MEMORY/lessons-learned/ | 01-AGENT-MEMORY//lessons-learned/ | YYYY-MM-DD-[topic].md |
| 6 | recurring pattern / insight | 01-AGENT-MEMORY/patterns/ | 01-AGENT-MEMORY//patterns/ | YYYY-MM-DD-[topic].md |
| 7 | topic/tech not yet understood | 01-AGENT-MEMORY/knowledge-gaps/ | 01-AGENT-MEMORY//knowledge-gaps/ | YYYY-MM-DD-[topic].md |
| 8 | used a specific skill | 01-AGENT-MEMORY/skill-usage/ | 01-AGENT-MEMORY//skill-usage/ | YYYY-MM-DD-[topic].md (Skill/Task/Result) |
| 9 | entity/org/protocol (not person) | 02-KNOWLEDGE/entities/ | 02-KNOWLEDGE/entities/ (shared) | YYYY-MM-DD-[name].md |
| 10 | specific person | 02-KNOWLEDGE/people/ | 02-KNOWLEDGE/people/ (shared) | YYYY-MM-DD-[name].md |
| 11 | domain topic (ai/crypto/learning/new) | 02-KNOWLEDGE/topics// | 02-KNOWLEDGE/topics// (shared) | YYYY-MM-DD-[topic].md (link to concepts/entities, NOT duplicate) |
| 12 | project-related task | 05-PROJECT/active//LOG.md | same (shared) | append ## YYYY-MM-DD |
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.
- 11d ago First seen · 108 lines · 0 tokens per session scan A 77779a74237b
scanthissession is a skill published in the GitHub repository brodewa369/roowet-semantic-vault-search (5 stars, last pushed 15d ago), licensed MIT. It adds 113 tokens to every session and 2,000 once invoked, about $0.0006 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
swarmvault
Use SwarmVault when the user needs a local-first knowledge vault that writes durable markdown, graph, search, dashboard, review, chat-session, context-pack, task-ledger, static AI export, retrieval, and MCP artifacts to disk from books, notes, transcripts, exports, datasets, slide decks, files, URLs, code, and…
recallnest
Recover cross-session context with RecallNest, search durable memory before repeat exploration, store durable decisions and lessons, and checkpoint unfinished work.
recallnest
Recover cross-session context with RecallNest, search durable memory before repeat exploration, store durable decisions and lessons, and checkpoint unfinished work.
knowledge-ingestion
A skill for saving links, social posts, videos, podcasts, screenshots, PDFs, local files, or text into an Obsidian knowledge base, a personal collection of searchable notes. The ingestion tools analyse and format the material for storage.
personal-knowledge-ingestion
A skill for saving links, videos, social posts, local files, screenshots, PDFs, or text into an Obsidian vault, a folder used for personal notes and knowledge. It uses connected knowledge tools to process and format the saved item.
time-library
Use when the user refers to previous decisions, corrections, forgotten context, already-built work, install/test/release status, source-backed evidence, or next steps in ongoing work. Treat Time Library as a standing active memory routing rule: call timelibraryrecall before answering memory-dependent prompts. Also…