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 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/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/21pounder/terminalagent/deep-research"><img src="https://agentmods.dev/badge/skills/21pounder/terminalagent/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 | $0.00037 | $0.00879 |
| Opus 5.5 | $0.00015 | $0.00352 |
| Sonnet 5.5 | $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 2mo 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.
- 2mo ago First seen · 123 lines · 37 tokens per session scan A 62cb78989ab6
deep-research is a skill published in the GitHub repository 21pounder/terminalAgent (116 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 37 tokens to every session and 879 once invoked, about $0.0001 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 2026-08-30.
deep-research compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| deep-research21pounder/terminalAgent | Skill | 116 | 5mo ago | Apache-2.0 | A | 37 | Claude Code |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |