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 agentmods add skills/21pounder/terminalagent/deep-researchnpx skills add 21pounder/terminalAgent --skill deep-researchgit clone --depth 1 https://github.com/21pounder/terminalAgentWrote 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/21pounder/terminalagent/deep-research)<a href="https://agentmods.dev/skills/21pounder/terminalagent/deep-research"><img src="https://agentmods.dev/badge/skills/21pounder/terminalagent/deep-research.svg" alt="Measured on agentmods" 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 | $0.00037 | $0.00879 |
| Opus 5 | $0.00018 | $0.00439 |
| Sonnet 5 | $0.00007 | $0.00176 |
| Haiku 4.5 | $0.00004 | $0.00088 |
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 6d 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deep Research (Dify Powered)
This skill delegates research tasks to a specialized Dify Workflow that:
- Searches official documentation, tutorials, and academic resources
- Analyzes the topic with DeepSeek Reasoner for deep insights
- Iteratively searches for examples, solutions, and related research
- Generates a comprehensive research report with structured findings
Use this skill for:
- Code implementation research (APIs, libraries, best practices)
- Academic paper analysis and literature review
- Technology comparison and evaluation
- Any topic requiring comprehensive, structured research
Parameters
{
"type": "object",
"properties": {
"coding_task": {
"type": "string",
"description": "The coding task or question to research (required)"
},
"tech_stack": {
"type": "string",
"description": "Technology stack context (e.g., 'React 18, TypeScript, Next.js')"
},
"depth": {
"type": "integer",
"minimum": 1,
"maximum": 5,
"default": 3,
"description": "Research depth (1=quick, 3=standard, 5=comprehensive)"
}
},
"required": ["coding_task"]
}
Workflow
Step 1: Locate the Client Script
The client script is at: .claude/skills/deep-research/scripts/dify-client.ts
Use Glob to find the absolute path if needed.
Step 2: Execute Research
Use Bash to run the script with npx tsx:
npx tsx "<path_to_script>" "<coding_task>" "<tech_stack>" <depth>
Examples:
# Basic research
npx tsx ".claude/skills/deep-research/scripts/dify-client.ts" "How to implement OAuth2 in Next.js"
# With tech stack
npx tsx ".claude/skills/deep-research/scripts/dify-client.ts" "Add real-time notifications" "React 18, Socket.io"
# With depth
npx tsx ".claude/skills/deep-research/scripts/dify-client.ts" "Optimize database queries" "PostgreSQL, Prisma" 5
Step 3: Process Results
The script returns JSON with two main fields:
analysis: Task analysis with knowledge gaps and tech requirementsguide: Complete implementation guide with:- TASK_SUMMARY
- DEPENDENCIES (install commands)
- FILES_TO_CREATE (complete code)
- FILES_TO_MODIFY (change instructions)
- ENVIRONMENT_CONFIG
- VERIFICATION (test commands)
- GOTCHAS (common issues)
- SOURCES
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.
- 6d ago First seen · 123 lines · 37 tokens per session scan A 62cb78989ab6
deep-research is a skill published in the GitHub repository 21pounder/terminalAgent (120 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 37 tokens to every session and 879 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
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…
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…
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…
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…