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 arozumenko/sdlc-skills --skill deep-researchgit clone --depth 1 https://github.com/arozumenko/sdlc-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/arozumenko/sdlc-skills/deep-research)<a href="https://agentmods.dev/skills/arozumenko/sdlc-skills/deep-research"><img src="https://agentmods.dev/badge/skills/arozumenko/sdlc-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/arozumenko/sdlc-skills/deep-research"><img src="https://agentmods.dev/badge/skills/arozumenko/sdlc-skills/deep-research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00068 | $0.01378 |
| Opus 5 | $0.00034 | $0.00689 |
| Sonnet 5 | $0.00014 | $0.00276 |
| Haiku 4.5 | $0.00007 | $0.00138 |
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 10d 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deep Research
One workflow, three modes. Pick the mode from the user's intent:
| Mode | Use when |
|---|---|
| trends | "what's happening in X", "emerging patterns", "who are the players" |
| analyze | "go deep on X", "tradeoffs of X", "SWOT", "compare perspectives" |
| factcheck | document or list of claims handed in for verification |
All three share the same workspace + checkpoint discipline below. Read this section once, then jump to your mode.
Workspace & Checkpointing (all modes)
Workspace: .research/<YYYY-MM-DD>/<mode>_<session>/
00_plan.md # written before any research
notes.md # rolling findings, source URLs
checkpoint_NNN.md # batch results (factcheck) or section drafts (trends/analyze)
report.md # final output, assembled from disk — never from memory
Rules that apply to every mode:
- Plan first. Write
00_plan.mdbefore searching anything. Include the question, sub-questions, and the sources you intend to hit. - Disk is truth, memory is scratch. Append findings to
notes.mdas you go with source URLs. If the session dies, you resume from disk. - Checkpoint on a budget. Every ~10 research steps OR when context approaches ~150K tokens, write a checkpoint and drop detailed research from working memory — keep only 2–3 line summaries.
- Assemble the final report from disk. Use
cat/Readover checkpoints. Never reconstruct from memory. - Resume, don't restart. On error,
lsthe workspace, read the last checkpoint, continue from the next unprocessed item.
Mode: trends
Goal: identify the current state and trajectory of a space.
- Plan sub-questions: who are the players, what's new in the last 6–12 months, what are adoption signals, what are the contrarian takes.
tavily_searchfor each sub-question. For technical topics, alsoresolve-library-id+query-docs(Context7) to ground claims in current docs.- Note publication dates aggressively — anything older than 12 months gets flagged as "background, not signal."
- Final
report.md:- State of the space (2–3 paragraphs)
- Key players (table: name, focus, signal)
- Emerging patterns (bullets, each with a dated source)
- Contrarian / risk signals
- Where this is heading (1 paragraph, clearly labeled as opinion)
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.
- 10d ago First seen · 126 lines · 68 tokens per session scan A 25fe0242d7a0
deep-research is a skill published in the GitHub repository arozumenko/sdlc-skills (20 stars, last pushed 6d ago), licensed MIT. It adds 68 tokens to every session and 1,378 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.
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
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…