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-troubleshootgit 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-troubleshoot)<a href="https://agentmods.dev/skills/jessymariau/booboo/booboo-troubleshoot"><img src="https://agentmods.dev/badge/skills/jessymariau/booboo/booboo-troubleshoot/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-troubleshoot"><img src="https://agentmods.dev/badge/skills/jessymariau/booboo/booboo-troubleshoot.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 | $0.00079 | $0.01242 |
| Opus 5 | $0.00039 | $0.00621 |
| Sonnet 5 | $0.00016 | $0.00248 |
| Haiku 4.5 | $0.00008 | $0.00124 |
Grade A, and why
booboo-troubleshoot scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl localhost:8787/stats # what the server thinks it has How it starts
The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Troubleshooting
Read RULES.md first — rule 4 is the method: verify against the running thing,
because most of these failures exit 0.
Full reference: docs/TROUBLESHOOTING.md in the repo. This skill is the ordered
diagnostic path.
Start by finding out what is actually true
Before theorising, get three facts:
booboo build --config booboo.config.yaml # read the quality line AND the node count
curl localhost:8787/stats # what the server thinks it has
Plus: does org.booboo.json say "seed": true? That single flag explains a
surprising share of "my agents behave strangely" reports — the fleet is booting
from the scaffold's sample pair.
The build exits 0 but the graph is empty or tiny
The most common failure, because nothing errors.
- A
whereclause matching nothing. Run the same predicate asSELECT count(*)against the source. A filter that excludes everything is silent. - A wrong table or column name in a
nodes:entry. The adapter reads what you named; iflabel: namepoints at a column that does not exist, you get nodes with no labels or no nodes at all depending on the source. - The wall is wider than you think. A
walls:entry matching a cluster name you also use for real data filters it out entirely — correctly, silently, in the builder. ${VAR}did not resolve. An unresolved connection string usually fails loudly, but an unresolved path can silently read nothing.
Compare the built node count to a count(*) on the source. That one comparison
finds most of these.
The 3D view is a flat starburst
Everything is parented to the root, so there is no spine. Set parent: on your
node entries deliberately — see booboo-adapter. This renders perfectly and tells
you nothing, so it is easy to miss unless you look at the picture.
Spines converge somewhere that is not the root
A parent-mapping bug: some node is acting as a hub because a parent: column
contains a constant, a null coerced to a shared value, or a foreign key pointing
at the wrong table. Search for the hub node and read its neighbors.
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 · 113 lines · 79 tokens per session scan A 1558c85c2960
booboo-troubleshoot is a skill published in the GitHub repository jessymariau/booboo (1 stars, last pushed 29d ago), licensed MIT. It adds 79 tokens to every session and 1,242 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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-cli
Use when the task is centered on running, explaining, configuring, or troubleshooting the potpie command: doctor, login, pot management, source registration, search, graph workbench reads/writes, and pot scope behavior.
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.
edge-case-review
Use when stress-testing failure paths, race conditions, reconnects, duplicate or out-of-order events, stale state, permission bypasses, crash recovery, or breaking the system under hostile chaos conditions.
graph-explorer
Navigate the graphos knowledge graph before editing load-bearing code. Use when tracing dependencies, planning a rename, auditing API surface, or answering "what breaks if I change this?". Pairs with codebase-explorer — graph-explorer wins for symbol-precise queries, codebase-explorer wins for conceptual code-reading.
performance
Application performance for backend (Go+Fiber, Python+FastAPI), web frontends, and React Native mobile clients. Use when measuring or improving Web Vitals (LCP / INP / CLS), mobile FPS / TTI / memory, image/font/code-split optimization, profiling, or interpreting Lighthouse / Reanimated / Hermes / Flipper traces.…
codebase-explorer
Conceptual code-reading for unfamiliar areas — trace a feature, follow a data flow, understand a domain. Use when the question is conceptual ("how does auth work?", "what happens when a user buys X?"); for symbol-precise queries (callers, blast radius, rename) use graph-explorer instead. The two are complementary …