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 shennawardana23/skillme --skill deep-researchgit clone --depth 1 https://github.com/shennawardana23/skillmeWrote 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/shennawardana23/skillme/deep-research)<a href="https://agentmods.dev/skills/shennawardana23/skillme/deep-research"><img src="https://agentmods.dev/badge/skills/shennawardana23/skillme/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/shennawardana23/skillme/deep-research"><img src="https://agentmods.dev/badge/skills/shennawardana23/skillme/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 | $0.00077 | $0.01265 |
| Opus 5 | $0.00039 | $0.00633 |
| Sonnet 5 | $0.00015 | $0.00253 |
| Haiku 4.5 | $0.00008 | $0.00127 |
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 11d 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deep Research
Produce a thorough, cited report from multiple web sources on an open-ended topic. This is the broadest of the research-family skills — research answers one narrow, verifiable technical question against this codebase, and market-research produces a business decision memo; this skill produces a long-form, themed report on any topic, technical or not, sourced from the open web.
When to Activate
- The user wants to research any topic in depth: "research X", "deep dive into Y", "investigate Z", "what's the current state of W"
- Competitive, technology, or trend analysis that isn't narrowly scoped to a business decision
- Any question requiring synthesis across many independent sources
Tooling
Use whatever web search and page-fetch tools are available in the current environment (e.g. WebSearch and WebFetch). If MCP servers such as firecrawl or exa are configured and available, prefer them for broader crawl/search coverage — they are not required.
Workflow
Step 1: Understand the Goal
Ask 1-2 quick clarifying questions: "What's your goal — learning, making a decision, or writing something?" and "Any specific angle or depth you want?" If the user says "just research it," skip ahead with reasonable defaults rather than blocking on clarification.
Step 2: Plan the Research
Break the topic into 3-5 research sub-questions before searching. Example — topic "impact of AI on healthcare": what are the main applications today; what clinical outcomes have been measured; what are the regulatory challenges; who are the leading companies; what's the market trajectory. Decomposing first prevents the search from wandering.
Step 3: Execute Multi-Source Search
For each sub-question, search with 2-3 different keyword variations, mixing general and recency-focused queries. Aim for 15-30 unique sources total across all sub-questions. Prioritize academic, official, and reputable-outlet sources over blogs, and blogs over forums.
Step 4: Deep-Read Key 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.
- 11d ago First seen · 101 lines · 77 tokens per session scan A 399b29280b02
deep-research is a skill published in the GitHub repository shennawardana23/skillme (2 stars, last pushed 14d ago), licensed Apache-2.0. It adds 77 tokens to every session and 1,265 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
writing-skills
Use when creating new skills, editing existing skills, or verifying skills work before deployment.
receiving-code-review
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation.
writing-plans
Use when you have a spec or requirements for a multi-step task, before touching code.
skill-creator
Create, improve, evaluate, benchmark skills. Use when authoring a new skill, updating an existing one, running evals, or optimizing a skill's description for triggering. Don't use for invoking skills, writing prose, or scaffolding Python projects.
skill-index-updater
Add GitHub skill repos to the ASM index: clone, audit, eval, regenerate index, rebuild catalog, open PR. Use when given GitHub URLs to onboard. Don't use for authoring (skill-creator), improving (skill-auto-improver), or install (asm install).
hello-world
A minimal test skill that greets the user and demonstrates the ASM publish workflow.