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 mayrsascha/deep-research-skill --skill deep-researchgit clone --depth 1 https://github.com/mayrsascha/deep-research-skillWrote 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/mayrsascha/deep-research-skill/deep-research)<a href="https://agentmods.dev/skills/mayrsascha/deep-research-skill/deep-research"><img src="https://agentmods.dev/badge/skills/mayrsascha/deep-research-skill/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 | $0.00050 | $0.00781 |
| Opus 5 | $0.00025 | $0.00391 |
| Sonnet 5 | $0.00010 | $0.00156 |
| Haiku 4.5 | $0.00005 | $0.00078 |
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 8d 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a research prompt engineer. Your job is to take a research request, ground it in the user's project context, transform it into an expert Deep Research prompt, and copy it to the user's clipboard.
Instructions
-
Take the research request provided by the user.
-
Gather project context — this is not optional. Before crafting the prompt:
- Check package.json, requirements.txt, Cargo.toml, or equivalent for the tech stack and dependencies
- Check the recent conversation for the problem being solved or decision being made
- Note any constraints, existing integrations, or architectural decisions already in play
- If you already have this context from the current session, use it — do NOT re-explore the codebase. Only look up files if the user's request references something you haven't seen.
-
Craft the prompt using this structure:
## Objective
[One paragraph: what to research and why it matters for this project]
## Context
[Tech stack, existing integrations, constraints, scale, team size — concrete details from the project]
## Investigate
[Numbered list of specific angles, questions, or comparisons to explore]
## Output Format
[Exactly what structure the research should be delivered in — report sections, comparison matrix, decision framework, etc.]
## Constraints
[Scope boundaries, what to exclude, any preferences or non-negotiables]
- Copy the prompt to the clipboard using a pipe and heredoc. Try clipboard commands in order until one works. If none are available, print the prompt to stdout and tell the user to copy it manually.
cat <<'PROMPT' | pbcopy 2>/dev/null || cat <<'PROMPT' | xclip -selection clipboard 2>/dev/null || cat <<'PROMPT' | wl-copy 2>/dev/null || cat <<'PROMPT' | clip.exe 2>/dev/null
[your crafted prompt here]
PROMPT
If all clipboard commands fail, output the prompt in a clearly marked block and tell the user: "Could not access clipboard. Copy the prompt above manually."
- After copying, confirm to the user:
- That the prompt has been copied to their clipboard
- A brief summary of what the prompt asks to be researched
- Suggest pasting into their preferred deep research tool (Gemini Deep Research, Perplexity, ChatGPT, etc.)
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.
- 8d ago First seen · 73 lines · 50 tokens per session scan A 9dbfb5ccd9f4
deep-research is a skill published in the GitHub repository mayrsascha/deep-research-skill (5 stars, last pushed 6mo ago), licensed MIT. It adds 50 tokens to every session and 781 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 2026-08-31.
Other skills, from other repositories
chatcrystal-debug-recall
Recall ChatCrystal memories for debugging tasks involving failing tests, compiler errors, runtime exceptions, dependency issues, environment breakage, or performance regressions. Use when historical root causes, fixes, or pitfalls may accelerate diagnosis before proposing a fix.
verify
Fact-check claims encountered during reading — dates, names, events, citations. Use when encountering historical facts or disputed claims.
vibeflow-stats
Compiles statistics from audit reports: PASS/PARTIAL/FAIL rates, most violated patterns, most failing DoD checks, and quality trends. Use after running several audits to spot improvement areas.
megalinter-check
Collect MegaLinter lint errors for the current repository. Use when the user wants to know if the code passes linting, why the MegaLinter CI job fails, or before/after fixing lint errors. Two modes - watch a CI job (GitHub Actions, GitLab CI, Azure Pipelines, Bitbucket Pipelines) and parse its logs, or run MegaLinter…
assistant
Assistant — on any repo, scan README→docs→AGENTS→CONTRIBUTING→PR templates→task runners→devcontainer→CI→configs before code; cite sources; prefer AGENTS.md for agent behavior; portable across Cursor/Copilot/Claude; use agent-toolkit CLI when needed.
design-improvement
WHAT - Browser-grounded iterative design improvement. Consumes design-assessment findings, defines direction, prioritizes safe vs ambiguous changes, implements within existing design system, runs app, captures rendered evidence via browser, reviews and iterates. Reuses evidence model — no new scoring framework.