framework-scout

framework-scout is a skill for Claude Code, Codex from Bumblebiber/its-over-9k. It costs 85 tokens per session (2,412 once invoked), scanned A, original, MIT.

A research tool for finding and evaluating agent frameworks, plugins, and MCP servers on GitHub. MCP servers are services that give an agent access to additional tools or data.

In plain words
What is it for?
Comparing frameworks, checking whether an unknown companion tool fits, updating compatibility records, and researching what is new or better than an existing option.
Why use it?
It reduces the work of searching the fast-changing agent ecosystem and turns broad research into a short compatibility recommendation.

Skill for Claude CodeCodex

Part of the o9k-recon plugin — 3 skills shipped together

Install

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.

agentmods
npx agentmods add skills/bumblebiber/its-over-9k/framework-scout
Any agent
npx skills add Bumblebiber/its-over-9k --skill framework-scout
Clone the repo
git clone --depth 1 https://github.com/Bumblebiber/its-over-9k

Made for: Claude Code, Codex.

Or install o9k-recon, the plugin that ships this one along with the rest of its 3 skills.

Wrote 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.

agentmods badge for framework-scout

README.md
[![agentmods](https://agentmods.dev/badge/skills/bumblebiber/its-over-9k/framework-scout.svg)](https://agentmods.dev/skills/bumblebiber/its-over-9k/framework-scout)
Your own site
<a href="https://agentmods.dev/skills/bumblebiber/its-over-9k/framework-scout"><img src="https://agentmods.dev/badge/skills/bumblebiber/its-over-9k/framework-scout.svg" alt="Measured on agentmods" height="20"></a>
Per session 85 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,412 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00085 $0.02412
Opus 5 $0.00043 $0.01206
Sonnet 5 $0.00017 $0.00482
Haiku 4.5 $0.00009 $0.00241

Measured 4d ago against content hash 3d261de5f4b2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

framework-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 4d 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.

plugins/o9k-recon/skills/framework-scout/SKILL.md · 170 lines

How it starts

The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.

framework-scout — the GitHub Scout

The agent ecosystem moves weekly. This skill is a repeatable recon loop: find what's new, score it, slot it into o9k's compatibility matrix — without dumping raw search results into context. Scout brings back a one-page verdict, not the whole map.

Scouting is expensive (many searches, many pages). Dispatch is mandatory for broad sweeps: fan searches to dispatch path A, keep only the shortlist. Write findings to memory (memory skill) so the next session diffs from the last scout, not from zero.

When to run

  • User asks "what's new / better than X?" or "find a framework for Y".
  • Refreshing docs/COMBINING.md or the README matrix.
  • Before proposing a new companion bundle or hand-installing an MCP server.
  • /o9k-init Step 2b — user gave Go to evaluate an unknown installed tool (not in compat/registry.json). Start at Step 2 (score); escalate to Step 4 trial / the bundle-bench companion only if the README verdict is inconclusive.
  • Not every session — scheduled recon (weekly-ish). Recon has a cost; amortize it.

Step 1 — Hunt (where to look)

Cast wide, in rough order of signal-to-noise:

  1. GitHub Topics — the highest-density source. Search repos by topic: claude-code, mcp, model-context-protocol, ai-agents, agentic-ai, token-optimization, claude-code-plugin. Use the GitHub MCP search_repositories with queries like:
    • topic:claude-code sort:stars
    • topic:mcp token OR context OR memory pushed:>2026-01-01
    • claude code skill OR plugin in:name,description,readme sort:stars
  2. GitHub Trending / OSSInsightWebFetch https://ossinsight.io/trending/ai for real-time star-growth (raw Trending has known ranking noise; growth rate beats absolute stars for spotting the new thing).
  3. Anthropic plugin directory — install counts are a strong quality prior (claude.com/plugins). A plugin with 100k+ installs is battle-tested.
  4. Awesome-listsawesome-claude-code, awesome-ai-agents-*, awesome-mcp-servers. Good for coverage, lagging on freshness.
  5. Changelogs & releases — for tools already in the matrix, check list_releases / get_latest_release to catch a pivot (e.g. a memory tool that just added a SessionStart hook → now a blocking conflict).

Read the full file on GitHub · 170 lines

Changes

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.

  1. 4d ago First seen · 170 lines · 85 tokens per session scan A 3d261de5f4b2

Subscribe to this mod's changes

framework-scout is a skill published in the GitHub repository Bumblebiber/its-over-9k (0 stars, last pushed 8d ago), licensed MIT. It adds 85 tokens to every session and 2,412 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens