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 HinkoK/agent-skills --skill deepgit clone --depth 1 https://github.com/HinkoK/agent-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/hinkok/agent-skills/deep)<a href="https://agentmods.dev/skills/hinkok/agent-skills/deep"><img src="https://agentmods.dev/badge/skills/hinkok/agent-skills/deep/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/hinkok/agent-skills/deep"><img src="https://agentmods.dev/badge/skills/hinkok/agent-skills/deep.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 | $0.00061 | $0.00852 |
| Opus 5.5 | $0.00024 | $0.00341 |
| Sonnet 5.5 | $0.00012 | $0.00170 |
| Haiku 4.5 | $0.00006 | $0.00085 |
Grade B, and why
deep scanned grade B with 1 finding 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 1mo 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
chmod 600 ~/.openclaw/workspace/.secrets/deep-ws.env How it starts
The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/deep — Parallel Task Deep Research
Запускает асинхронный глубокий ресёрч через Task API и ждёт завершения.
Hermes usage rules
- Use for complex research where a quick answer would be unreliable or too shallow.
- Prefer
scripts/deep.sh "question" pro 1800as the default runtime path. - For urgent or lightweight fact checks, use normal web/perplex instead of this skill.
- Tell the user when the run may take a long time, especially for
proorultraprocessors. - Return a concise synthesis first, then evidence, caveats, and follow-up questions.
Usage
/deep твой исследовательский вопрос
Локально:
scripts/deep.sh "твой исследовательский вопрос" pro 1800
Параметры:
processor(опционально):pro(по умолчанию),ultra, и т.д.timeout_seconds(опционально): по умолчанию1800
Когда использовать
- Нужен глубокий отчёт, а не обычный поиск
- Многошаговый ресёрч с синтезом
- Аналитические задачи, где важна полнота
Требования и API-ключ
Для работы нужен PARALLEL_API_KEY от Parallel.
Где взять ключ:
- Открой https://platform.parallel.ai
- Войди или создай аккаунт.
- Перейди в раздел API keys / Developer settings.
- Создай новый API key.
- Сохрани его локально как переменную окружения:
export PARALLEL_API_KEY="PASTE_YOUR_KEY_HERE"
Для постоянного хранения можно добавить ключ в shell profile (~/.zshrc, ~/.bashrc) или в env-файл, который читает scripts/deep.sh:
mkdir -p ~/.openclaw/workspace/.secrets
printf 'PARALLEL_API_KEY=%s
' 'PASTE_YOUR_KEY_HERE' > ~/.openclaw/workspace/.secrets/deep-ws.env
chmod 600 ~/.openclaw/workspace/.secrets/deep-ws.env
Не коммить API key в GitHub и не вставляй его в промпт агенту.
Дополнительно:
- Для Deep Research лучше использовать
pro/ultra(доступны и fast-версии, если включены у аккаунта). - Входной запрос держать короче
15000символов. - Задача может выполняться долго (до ~45 минут на сложных ресёрчах).
- Docs: https://docs.parallel.ai/getting-started/overview
What ships with it
3 files 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.
- 1mo ago First seen · 93 lines · 61 tokens per session scan B 2b99f01cee1d
deep is a skill published in the GitHub repository HinkoK/agent-skills (6 stars, last pushed 4mo ago), licensed MIT. It adds 61 tokens to every session and 852 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
research-ops
Use when someone hands you an open question whose answer must survive scrutiny — a tech choice, a regulation, a what-is-actually-true-about-X — with every non-obvious claim dated and sourced, source disagreements surfaced rather than averaged away, and a cited memo as the deliverable. Also for refreshing a stale…
deep-research
Multi-lens research engine — one question, 9 angles, synthesized analysis. Uses /research-skill-graph/ as the knowledge base. Load this skill when given a research question and use it to produce deep, structured analysis. Invoke by saying "do deep research on [question]".
gemini-prompting
Internal guidance for composing effective grounded search queries.
search-result-handling
Internal guidance for presenting the search results to the user.
swarm-advanced
Advanced swarm orchestration patterns for research, development, testing, and complex distributed workflows.
analyze-constraints-readiness
Characterize what blocks a research target: readiness dimensions, obstacles, bottlenecks, resource gaps, causal constraints, dependencies, conflicts, removability, and mitigation pathways. Depth selects lightweight triage, readiness assessment, or causal/TOC-style constraint analysis.