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 notforyou23/home23 --skill shakedown-feature-forgegit clone --depth 1 https://github.com/notforyou23/home23Wrote 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/notforyou23/home23/shakedown-feature-forge)<a href="https://agentmods.dev/skills/notforyou23/home23/shakedown-feature-forge"><img src="https://agentmods.dev/badge/skills/notforyou23/home23/shakedown-feature-forge/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/notforyou23/home23/shakedown-feature-forge"><img src="https://agentmods.dev/badge/skills/notforyou23/home23/shakedown-feature-forge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00039 | $0.02856 |
| Opus 5 | $0.00019 | $0.01428 |
| Sonnet 5 | $0.00008 | $0.00571 |
| Haiku 4.5 | $0.00004 | $0.00286 |
Grade A, and why
Shakedown Feature Forge 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 9d 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 — 339 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Shakedown Feature Forge
This skill memorializes the successful pre-rewrite process used to make “The Mandolin Knows” from “Rubin and Cherise” on August 10, 2026.
Its product is a complete, sourced feature with a real governing idea. It is not a dossier, topic card, pipeline state transition, publishing operation, or jtr-voice rewrite.
The central rule
Find the sentence that makes the whole piece legible, then try to prove it wrong.
For “Rubin and Cherise,” that sentence was:
Reuben can lie, but his mandolin cannot.
That was not a decorative headline added after research. It selected the research, organized the evidence, and became the article’s spine. The second pressure point—this deeply Garcia song barely became a Grateful Dead song—supplied the historical counterweight.
Do not begin by filling a template. Do not begin with the pipeline. Begin by reading the thing closely enough to have a take.
When to use
Use this skill when jtr names a Garcia, Hunter, Grateful Dead, JGB, song, performance, object, collaborator, or episode and wants the actual Shakedown story found and written.
Especially use it when he says:
- “straight up”
- “just do the piece”
- “find the story”
- “give it the Rubin and Cherise treatment”
- the pipeline is unfinished or would distract from the editorial work
Do not use it for:
- publishing or distribution
- a routine factual lookup
- a voice-only rewrite
- backlog selection
- North Star gap-filling
- forcing a weak subject into an article
Actions
forge
Run forge as one editorial workflow:
- close-read the primary object
- state a provisional governing idea
- derive bounded research threads that could prove or break it
- gather and validate authoritative sources claim by claim
- follow meaningful discrepancies and variants
- build an argument-shaped narrative movement
- draft the complete sourced feature
- run the adversarial editorial pass
- freeze the pre-voice manuscript
The action ends at a verified manuscript. Publishing and voice rewriting are separate actions.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 339 lines · 39 tokens per session scan A bf0e47e47719
Shakedown Feature Forge is a skill published in the GitHub repository notforyou23/home23 (11 stars, last pushed yesterday), licensed MIT. It adds 39 tokens to every session and 2,856 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
source-driven-development
Reads official sources before implementing. Use when using a library, API, or framework that might have changed since training. Use when you're unsure about current API signatures, best practices, or when working with rapidly evolving tools.
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
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…