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/cdeistopened/skill-stack/deep-researchnpx skills add cdeistopened/skill-stack --skill deep-researchgit clone --depth 1 https://github.com/cdeistopened/skill-stackWhat 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 | $0.00060 | $0.01513 |
| Opus 5 | $0.00030 | $0.00757 |
| Sonnet 5 | $0.00012 | $0.00303 |
| Haiku 4.5 | $0.00006 | $0.00151 |
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 2d 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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gemini Deep Research
Delegate deep, multi-source research to Gemini's Deep Research agent. This skill optimizes the user's research question into a structured prompt, fires it off via the Interactions API, and returns the full report.
When to Use
- Market research, competitive analysis, due diligence
- Literature reviews, state-of-the-art surveys
- Historical deep dives on people, movements, or ideas
- "What does the current landscape look like for X?"
- Any question that benefits from searching 50-100+ web sources
- When the user explicitly asks for "deep research" or wants comprehensive analysis
When NOT to Use
- Quick factual lookups (use WebSearch instead)
- Code questions or debugging
- Tasks requiring real-time interaction or low latency
- Questions about the user's local codebase
Workflow
Phase 1: Optimize the Research Prompt
Before sending to Gemini, transform the user's raw request into a well-structured research prompt. This is critical — Deep Research quality scales with prompt quality.
Prompt optimization checklist:
- Scope the question clearly — What specifically should be researched? Add boundaries (time period, geography, industry, etc.)
- Define the output structure — Tell Gemini exactly what sections/format you want
- Specify depth expectations — "Include specific examples," "cite primary sources," "compare at least 5 competitors"
- Add anti-hallucination guardrails — "Only include claims with verifiable sources," "distinguish between confirmed facts and speculation"
- Request citations — "Include source URLs for all major claims"
Template for optimized prompts:
Research [TOPIC] with the following scope and structure:
## Scope
[Boundaries: time period, geography, domain, exclusions]
## Required Sections
1. [Section with specific instructions]
2. [Section with specific instructions]
3. [Section with specific instructions]
## Output Requirements
- Include source URLs for all major claims
- Distinguish between confirmed facts and projections/speculation
- Include a summary table comparing [key dimensions]
- Target depth: [comprehensive / focused overview / executive summary]
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.
- 2d ago First seen · 156 lines · 60 tokens per session scan A d132b8c86e3c
deep-research is a skill published in the GitHub repository cdeistopened/skill-stack (27 stars, last pushed 1mo ago), licensed MIT. It adds 60 tokens to every session and 1,513 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 2026-08-30.
Other skills, from other repositories
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
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…