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 Bumblebiber/its-over-9k --skill scoutgit clone --depth 1 https://github.com/Bumblebiber/its-over-9kWrote 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/bumblebiber/its-over-9k/scout)<a href="https://agentmods.dev/skills/bumblebiber/its-over-9k/scout"><img src="https://agentmods.dev/badge/skills/bumblebiber/its-over-9k/scout.svg" alt="Measured on agentmods" 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 | $0.00080 | $0.00821 |
| Opus 5 | $0.00040 | $0.00411 |
| Sonnet 5 | $0.00016 | $0.00164 |
| Haiku 4.5 | $0.00008 | $0.00082 |
Grade A, and why
scout 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 6d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
scout — Context Discipline
The cheapest token is the one never loaded. Explore structure, not content.
The ladder — always start at the top
- Memory first. Project already known? Ask the memory MCP (
load_projector search) before touching the filesystem — a 300-token briefing beats a 20k-token re-exploration. - Map second. Need repo orientation? Build/read ONE overview: file tree
(
ls/glob), or a generated map (codesightCONTEXT.md, aider-style repo-map) if available. Cache it mentally — never regenerate mid-session. - Search third. Locate by symbol/pattern (grep, ast-grep, Serena
find_symbol) — getfile:line, not file contents. - Read last, read narrow. Open only the located range (offset/limit around the hit). Full-file reads only when the file is small or the task is a whole-file rewrite.
Hard rules
- Never read a file to find something — that's what search is for.
- Never re-read a file you just edited — you know what's in it.
- Never load generated artifacts (lockfiles, dist/, minified, fixtures) unless they ARE the subject of the task.
- Broad sweep needed? (many files, unknown naming, "where is X handled?")
→ don't do it inline; hand it to
dispatchpath A and receive the conclusion only. External CLI coding workers with ateam-uproster →dispatchpath B (mailbox + watcher), not inline exploration. - Docs/logs over ~200 lines: extract the relevant slice (grep the error ID, read the section) — never the whole thing.
Symbol work
If the Serena MCP (or an LSP-backed tool) is installed, symbol-level lookups and
edits go through it: find_symbol / find_references / targeted insert replace
an 8-step grep-and-read loop with one call. Scout owns the overview; Serena
owns the symbols. Never run both for the same question.
High-volume shell output
Never diagnose with bare npm test, vitest run, or eslint . when the runner
can dump tens of KB into the transcript. Redirect → extract → act on summary.
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.
- 6d ago First seen · 67 lines · 80 tokens per session scan A e06ac7ef4f60
scout is a skill published in the GitHub repository Bumblebiber/its-over-9k (0 stars, last pushed 9d ago), licensed MIT. It adds 80 tokens to every session and 821 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
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.