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 serejaris/kimi-skills --skill deep-researchgit clone --depth 1 https://github.com/serejaris/kimi-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/serejaris/kimi-skills/deep-research)<a href="https://agentmods.dev/skills/serejaris/kimi-skills/deep-research"><img src="https://agentmods.dev/badge/skills/serejaris/kimi-skills/deep-research/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/serejaris/kimi-skills/deep-research"><img src="https://agentmods.dev/badge/skills/serejaris/kimi-skills/deep-research.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 | $0.00061 | $0.02349 |
| Opus 5 | $0.00030 | $0.01175 |
| Sonnet 5 | $0.00012 | $0.00470 |
| Haiku 4.5 | $0.00006 | $0.00235 |
Grade A, and why
deep-research 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deep Research
Conduct thorough, multi-dimensional research on complex questions using file creation and editing, search engines and browsers, code execution, image and multimedia generation, slide creation, website deployment, and visual processing of tool outputs. Think critically, use the current date as the temporal reference, verify uncertain information proactively, and deliver comprehensive, well-structured, rigorously grounded findings.
Research & Discovery Phase (The 10+ Step Loop)
- Read Attached Files: Start by checking any attachments to understand the background information.
- Clarify Intent: Ask targeted clarification questions via the
ask_usertool to ensure you fully understand their goals before proceeding. - Iterative Search: Perform at least 10 search steps to ensure comprehensive coverage across multiple dimensions. Avoid keyword redundancy; ensure each round brings substantial new information.
- Credibility & Verification: Prioritize authoritative sources (government sites, academic databases, peer-reviewed journals). Never fabricate data. Every statistic and claim must be accurate and traceable.
- Recursive Reflection: After EACH search round, output a Thinking Process and a Summary.
- Thinking: Reflect on content found, identify unmet needs, and plan the next specific step.
- Summary: Concise recap of key findings.
- Constraint: Both sections must be short and concise.
- Quantitative Analysis: Use Python for calculations, data cleaning, statistical analysis, and verification when precision is required.
- Visualization Planning: Based on the report content, create necessary, content-relevant visualizations and follow the Visualization Workflow for chart/diagram authoring, rendering, embedding, and visual consistency.
Report Engineering Standards
1. Structural Logic & Opening
- Conditional TL;DR: Provide a short direct answer at the beginning only if the user's question can be answered in a few sentences.
- Style Adaptation:
- If a specific style is implied (e.g., story, interview, case narrative), adhere to it.
- Default: Strict academic report format.
- Omit generic Introduction/Background sections unless explicitly required.
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.
- 9d ago First seen · 117 lines · 61 tokens per session scan A 17294826a620
deep-research is a skill published in the GitHub repository serejaris/kimi-skills (6 stars, last pushed 1mo ago), licensed MIT. It adds 61 tokens to every session and 2,349 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
offensive-vuln-classes
Exploit development curriculum covering core vulnerability classes with real-world CVE case studies: stack/heap buffer overflows, use-after-free, integer overflows, format strings, type confusion, and race conditions. Use when learning or teaching vuln classes, researching specific CVE patterns, or building exploit…
explain-this
Explain whatever the user is pointing at right now in plain language: a pending question, a piece of code, an error, a command output, or an artifact like a plan or findings report. Use when the user asks to "explain this", "what am I being asked", "what's happening right now", "help me understand this", "what does…
understand-change
Teach the user to deeply understand a change through interactive tutoring: restating understanding, drilling into why/what/how, and quizzing until mastery. The active counterpart to a one-shot explanation. Use when the user asks to "understand this change", "teach me this change", "help me understand what changed"…
ape-visualize
Builds interactive, browser-based 3D Three.js visualizations of any mathematics or science concept as a single, self-contained HTML file. Takes a concept and a depth level (Simple, Intermediate, Advanced). Trigger on "ape visualize", "ape visualize math", "ape visualize science", "visualize math", "visualize science"…
ape-quiz-me
Quizzes you on content you claim to have read -- Socratic, one question at a time, hints that narrow but never reveal. Ends with a verdict on what you understood versus merely recited. Trigger on "ape quiz me", "quiz me on this", "test my understanding", "did I actually get this", or any request to be tested on shared…
ape-write-pseudocode
Guidelines for writing pseudocode for functions and algorithms. Use this skill whenever the user asks to write pseudocode, sketch out an algorithm, or describe the logic of a function at a high level. Trigger on phrases like "write pseudocode", "sketch this algorithm", "pseudocode for this function", or "describe the…