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-querygit 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-query)<a href="https://agentmods.dev/skills/jessymariau/booboo/booboo-query"><img src="https://agentmods.dev/badge/skills/jessymariau/booboo/booboo-query/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-query"><img src="https://agentmods.dev/badge/skills/jessymariau/booboo/booboo-query.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 | $0.00074 | $0.01006 |
| Opus 5.5 | $0.00030 | $0.00402 |
| Sonnet 5.5 | $0.00015 | $0.00201 |
| Haiku 4.5 | $0.00007 | $0.00101 |
Grade A, and why
booboo-query 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 2mo 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.
Query a brain
Read RULES.md first — rules 5 and 6 govern every write you make here.
Boot first. Every session.
booboo_boot('<agent-id>')
Returns identity, authority chain, inherited rules, bucket reach, skills and children. Call it before deciding anything, not after — the rules it returns are binding on the work you are about to do, and reading them afterwards is how an agent discovers it just violated one.
Needs the server started with --org. If booboo_boot is missing from the tool
list, the org file was not passed.
The read path
Search before you fetch. booboo_node needs an exact id, and ids are rarely
what a human said. booboo_search ranks exact > prefix > substring; take the id
from the result and fetch with it.
booboo_search("payment webhook") → pick the id from the ranked hits
booboo_node("<that exact id>") → all fields + data
Neighbors versus path. They answer different questions:
booboo_neighbors(id, depth)— what is around this? Use to understand a thing's context, find what feeds it, spot orphans. Depth 1 first; depth 3 on a dense graph returns more than you can reason about.booboo_path(a, b)— how do these two connect? Returns the shortest chain, or null if unreachable. Use to answer "does X actually depend on Y" — and treat a null as a real answer, not a failed call.
Counts before payloads. booboo_stats gives node and link counts by layer;
booboo_count gives counts without pulling the data. Reach for these when sizing
a query — pulling a whole layer to count it is how a session runs out of context.
booboo_org returns the full organigram when you need the whole fleet rather
than one agent's slice.
The REST surface
Same graph, when MCP is not available:
/graph /stats /search /nodes/:id /neighbors/:id /path/:a/:b
Default port 8787. booboo serve --snapshot my.booboo.json --port 8787.
Writing back
Two write tools, both live — they append to the journal beside the snapshot, are queryable the same session, and survive every rebuild. No rebuild needed.
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.
- 2mo ago First seen · 96 lines · 74 tokens per session scan A 97a6d0c5cccf
booboo-query is a skill published in the GitHub repository jessymariau/booboo (1 stars, last pushed 2mo ago), licensed MIT. It adds 74 tokens to every session and 1,006 once invoked, about $0.0003 per session on Opus 5.5. 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
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.
linglu-discipline
A set of 16 operating rules for an AI coding agent, including when to read or write long-term memory and how to report completed actions. It is designed to work with the Lingshu memory service through an MCP connection.
ori-memory
Persistent agent memory with learning retrieval. Knowledge graph on markdown files — capture insights, decisions, research, and learnings during work, then retrieve them weeks or months later. Use when knowledge is too valuable to lose but too much to inject into every prompt.
lemmalog
Externalize working memory and logical state into the lemmalog Datalog engine (MCP). Use for ANY multi-step task where state should outlive one context window or span agents: long investigations, debugging sessions, audits, multi-agent searches, systematic explorations, planning with many interdependent constraints…
forgetful-entities
Model the things knowledge attaches to — people, organisations, devices, products, system components. Use when a new thing surfaces that memories will reference, when relationships between things need recording (owns, depends on, part of), or when another skill routes a pointable thing here. Litmus: an entity is a…
wenlan-handoff
End a work session. Stores durable captures, writes a narrative session log, and automatically applies typed item-level deltas to the current Space Brief. Invoked as /wenlan-handoff.