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 jessymariau/booboo --skill booboo-vaultgit clone --depth 1 https://github.com/jessymariau/boobooWrote 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/jessymariau/booboo/booboo-vault)<a href="https://agentmods.dev/skills/jessymariau/booboo/booboo-vault"><img src="https://agentmods.dev/badge/skills/jessymariau/booboo/booboo-vault/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/jessymariau/booboo/booboo-vault"><img src="https://agentmods.dev/badge/skills/jessymariau/booboo/booboo-vault.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 | $0.00076 | $0.00997 |
| Opus 5 | $0.00038 | $0.00498 |
| Sonnet 5 | $0.00015 | $0.00199 |
| Haiku 4.5 | $0.00008 | $0.00100 |
Grade A, and why
booboo-vault 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 12d 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The vault — the brain as plain markdown
Read RULES.md first. Rule 1 (derived files are never hand-edited) and rule 5
(one atomic fact, author your links) both apply directly.
booboo vault --snapshot my.booboo.json --org org.booboo.json --out vault
Emits one page per node with frontmatter and its links, index pages per layer and per cluster, and an agent dossier per org member — chain of command, inherited rules, buckets, machines, contract. Open the folder in Obsidian and the graph view works, because the wikilinks are real.
Why bother when the 3D view exists
Three reasons, in order of how often they matter:
- Portability. Plain files outlive every tool in the chain. Any human can read them, any agent from any provider can too — no MCP client, no server, no Node.
- Insurance. Emit it nightly and the vault is a complete, readable copy of the brain that survives the database going away.
- The second-brain pattern, without hand-feeding. The usual Obsidian knowledge vault is manually curated notes. This one is generated from the real system, so it cannot drift from what is actually deployed.
The vault is DERIVED
Regenerate it; never hand-edit it. Edits to vault/ are erased by the next
booboo vault run without warning.
If you want text in the vault, put it in the source — the note, the row, the table the adapter reads. That is the only edit that survives, and it is the edit that also reaches the API, the MCP server and the 3D view.
Authoring links — the part that actually improves the brain
Put refs inside a note's text:
The dispatcher writes to [[content-ledger-live]] after [[zernio-api]] confirms.
With wikilinks: true in the config, the builder turns those into first-class
authored edges that outrank harvested relations everywhere — the graph, the
API, the 3D view and the vault.
Both forms work: [[node-id]] and [[exact label]]. Prefer the id when you know
it — labels change, ids should not.
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.
- 12d ago First seen · 96 lines · 76 tokens per session scan A a63f80c86521
booboo-vault is a skill published in the GitHub repository jessymariau/booboo (1 stars, last pushed 29d ago), licensed MIT. It adds 76 tokens to every session and 997 once invoked, about $0.0004 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
potpie-graph
Use when the task can read or write the project-memory graph through the potpie CLI: discover the contract with graph catalog, read named views with graph read, resolve entity identity with graph search-entities, create validated plans with graph propose, commit plans with graph commit --verify, inspect quality with…
potpie-source-ingestion
Use when the user explicitly asks to ingest, refresh, or deeply understand a repository, PR, issue, ticket, runbook, incident report, document, or web link into Potpie. The harness performs todo-driven discovery, uses local/GitHub/integration tools and read-only subagents when available, builds evidence-backed…
potpie-repo-baseline
Use when establishing, refreshing, or deeply understanding a repository's baseline memory in Potpie: purpose, application type, features, services/modules, environments, deploy shape, dependencies, API contracts, datastores, integrations, ownership, and explicit preferences. The harness reads authored and…
potpie-debug-memory
Use while debugging or troubleshooting failures, flaky tests, incidents, production alerts, CI failures, local dev setup issues, repeated bugs, prior fixes, failed attempts, and verification history.
okf
Author, maintain, and consume Open Knowledge Format (OKF) knowledge bundles — portable markdown + YAML frontmatter that both humans and agents read. Use when capturing project knowledge (services, APIs, schemas, metrics, runbooks, decisions) into an OKF bundle, when updating one after code or docs change, or when a…
engraphis-memory
Give the agent durable, scoped, explainable memory across sessions and repositories through the Engraphis MCP tools. Use when you learn a convention, decision, bug cause/fix, or user preference worth keeping; when prior context would help before you answer or act (to avoid re-asking or re-deriving); when asked "why is…