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 Kshitijpalsinghtomar/depth-skills --skill ds-deep-thinkgit clone --depth 1 https://github.com/Kshitijpalsinghtomar/depth-skillsWrote 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/kshitijpalsinghtomar/depth-skills/ds-deep-think)<a href="https://agentmods.dev/skills/kshitijpalsinghtomar/depth-skills/ds-deep-think"><img src="https://agentmods.dev/badge/skills/kshitijpalsinghtomar/depth-skills/ds-deep-think/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/kshitijpalsinghtomar/depth-skills/ds-deep-think"><img src="https://agentmods.dev/badge/skills/kshitijpalsinghtomar/depth-skills/ds-deep-think.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 | $0.00021 | $0.01627 |
| Opus 5 | $0.00010 | $0.00813 |
| Sonnet 5 | $0.00004 | $0.00325 |
| Haiku 4.5 | $0.00002 | $0.00163 |
Grade A, and why
deep-think 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 11d 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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DEEP-THINK — The Depth Protocol
You are about to answer. Stop.
The answer forming right now is your surface response — the path of least resistance through your knowledge. It arrived before search began. It is statistically expected, frequently rewarded, and probably the same answer any competent model would produce for this input.
That answer is a local optimum. It created lateral inhibition — one strong activation suppressing adjacent, deeper pathways. Better answers exist in those suppressed pathways. They will never activate unless you interrupt the surface response now.
This skill is the interrupt.
The Failure Mode You Must Recognize
You are about to generate a response that:
- Addresses the literal question without questioning whether it's the right question
- Uses the first architecture/approach/framework that matched the keywords
- Sounds confident because the phrasing is familiar, not because the analysis was thorough
- Omits caveats because including them feels like weakness
If you recognize this pattern forming — you are in premature closure. Continue with the protocol.
The Protocol — Every Step Produces a Written Artifact
1 — RESTATE: Write What This Is Actually About
Write 2-4 sentences that restate the problem in your own framing, covering:
- Intent: What outcome the user actually needs (not just what they literally asked)
- Success criteria: What a correct answer must achieve — specific and testable
- Prior context: What the user probably already tried or already knows
- Risk: What specific failure the user is most afraid of
Read your restatement back. If it matches their words — you restated, you didn't reframe. Reframe: translate from their framing to the problem's actual structure.
Artifact: The restatement block. This enters context and anchors all subsequent generation.
2 — SURFACE: Write Five Assumptions This Answer Rests On
Your first answer depends on things you haven't stated. Write them down — five minimum, from this list of types:
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.
- 11d ago First seen · 147 lines · 21 tokens per session scan A 3b45729840bc
deep-think is a skill published in the GitHub repository Kshitijpalsinghtomar/depth-skills (4 stars, last pushed 3mo ago), licensed MIT. It adds 21 tokens to every session and 1,627 once invoked, about $0.0001 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
vox-video-director
Turn ONE topic into a finished Vox-style paper-collage explainer / ad video, end to end with Aliyun Bailian CLI + local ffmpeg — script, collage keyframes, motion, voice-over, music, captions, all automated. Use this whenever the user wants a "Vox style" video, a paper/torn-paper collage animation, a "motion collage"…
bailian-train-deploy
A workflow for using Alibaba Cloud’s Bailian command-line tool to fine-tune or directly deploy AI models as callable services. It covers text, speech-synthesis, image-generation, and video-generation models.
api-database-mongodb
Native MongoDB driver (the mongodb npm package) - MongoClient lifecycle, typed collections, CRUD result shapes, cursors, aggregation pipelines, index design, transactions.
ai-infrastructure-ollama
Local LLM inference with the Ollama JavaScript client -- chat, streaming, tool calling, vision, embeddings, structured output, model management, and OpenAI-compatible endpoint.
ai-orchestration-langchain
LangChain.js patterns for building LLM applications — chat models, LCEL chains, prompt templates, structured output, agents, tools, RAG, streaming, and LangSmith tracing.
ai-provider-cohere-sdk
Official Cohere TypeScript SDK patterns -- CohereClientV2, chat, embeddings, rerank, RAG with citations, tool use, streaming, and model selection.