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 r13v/pi-feature-dev --skill deepengit clone --depth 1 https://github.com/r13v/pi-feature-devWrote 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/r13v/pi-feature-dev/deepen)<a href="https://agentmods.dev/skills/r13v/pi-feature-dev/deepen"><img src="https://agentmods.dev/badge/skills/r13v/pi-feature-dev/deepen/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/r13v/pi-feature-dev/deepen"><img src="https://agentmods.dev/badge/skills/r13v/pi-feature-dev/deepen.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 | $0.00082 | $0.00805 |
| Opus 5.5 | $0.00033 | $0.00322 |
| Sonnet 5.5 | $0.00016 | $0.00161 |
| Haiku 4.5 | $0.00008 | $0.00081 |
Grade A, and why
deepen 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 10d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deepen
Make the task deeper, not bigger. Do not add scope, deliverables, or polish.
Change what the work starts from, how it is done, and how it is proven right.
Keep the user's goal and deliverable. If the better move is to change the
deliverable, say so in one line and suggest elevate instead.
Inspect before answering
Ground every answer in the current environment. Check which data, artifacts, tools, and access actually exist before you name them. Treat a discoverable fact as your work, not a question for the user. Mark anything you could not confirm as an assumption.
Describe what a professional does, not who they are. Do not role-play an expert; persona framing changes the tone without improving the work.
Answer four questions
- Missing practice. What would a top professional in this field do here that the request does not ask for? Name the few steps that change the result, not a checklist of best practices. Set a concrete stretch target beyond the obvious one, such as a tighter error bound or a larger effect. If a constraint seems to block it, name the measurement that would confirm the limit, and keep confirmed limits apart from unverified estimates.
- Raw material. What is the rawest material they would start from, instead of the summaries, dashboards, tables, or tickets already digested for the user? Say where it lives and whether you can reach it now. Name the belief in the request that this material should test, such as an assumed cause, and how the data could prove it wrong.
- Methods and tools. Which specific methods and tools would they use? Name concrete techniques, commands, or libraries that fit this environment. Restate the deliverable as the activity it serves, such as "a deck" as "convince busy people of a cause under uncertainty", and pick methods from the fields that activity draws on. Use this to choose methods, never to replace the deliverable.
- External validation. What, other than you or the user, would show the result is right? Prefer a check you can run yourself for fast feedback: a test, a held-out sample, a reproduction, a reconciliation against source data, a benchmark. Never let your own judgment be the only check. When the task allows it, aim for a result that is new to an expert, such as a model, a simulation, or an early warning signal, and validate it on data it did not see. Do not turn a routine fix into a research project.
What ships with it
1 file 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.
- 10d ago Changed · +14 lines · +28 tokens per session db7637f5c57a
- 18d ago First seen · 55 lines · 54 tokens per session scan A 42f200f99ee0
deepen is a skill published in the GitHub repository r13v/pi-feature-dev (3 stars, last pushed 2d ago), licensed MIT. It adds 82 tokens to every session and 805 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 2026-10-14.
Other skills, from other repositories
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…