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 deciqAI/knowledge-skills --skill deep-workgit clone --depth 1 https://github.com/deciqAI/knowledge-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/deciqai/knowledge-skills/deep-work)<a href="https://agentmods.dev/skills/deciqai/knowledge-skills/deep-work"><img src="https://agentmods.dev/badge/skills/deciqai/knowledge-skills/deep-work/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/deciqai/knowledge-skills/deep-work"><img src="https://agentmods.dev/badge/skills/deciqai/knowledge-skills/deep-work.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 | $0.00123 | $0.01874 |
| Opus 5.5 | $0.00049 | $0.00750 |
| Sonnet 5.5 | $0.00025 | $0.00375 |
| Haiku 4.5 | $0.00012 | $0.00187 |
Grade A, and why
deep-work 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 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.
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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deep Work
Overview
Cal Newport's framework (2016): deep work = undistracted, cognitively demanding activity that creates hard-to-replicate value; shallow work = logistical, responsive, easy-to-replicate work that fills modern calendars. The most valuable knowledge work is disproportionately the product of deep work; shallow work is increasingly automatable. Three foundations: attention research shows 15-25 min recovery cost per interruption; expert performance requires deliberate practice (structurally a form of deep work); the opportunity cost of shallow work is invisible — no one tracks which deep work didn't happen this week.
Composes with wu-wei (flow as the felt experience), metacognition (monitoring drift out of deep mode), okr-goal-setting (OKRs give deep work direction), pareto-principle (the 20% producing 80% of value is almost always deep work).
When to Use
- Output depends on hard-to-replicate cognitive work (research, engineering, writing, design, strategy)
- Calendar fragmentation prevents the work that actually matters; weeks feel busy but produce nothing
- High-stakes project requires extended concentration; career advancement depends on skill development
- AI copilots / assistants have become another interruption stream ("is AI helping my focus or fragmenting it?", "AI adoption vs deep work", "AI hype and staying focused")
Not when: genuinely high-coordination roles where deep work is structurally impossible; already done with deep work and shallow follow-through is now required; short-term emergency where availability dominates.
Coaching Novices (Adaptive Front Door)
- Engine mode: user has a concrete case → run The Process directly.
- Coach mode: user unfamiliar or has no concrete case → guide step by step.
In Coach mode, respond one step at a time. Each [WAIT] is a hard stop — output only that step's question, then stop.
What ships with it
4 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 · 119 lines · 123 tokens per session scan A 9a5dcb1c9db5
deep-work is a skill published in the GitHub repository deciqAI/knowledge-skills (13 stars, last pushed 1mo ago), licensed MIT. It adds 123 tokens to every session and 1,874 once invoked, about $0.0005 per session on Opus 5.5. 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
mcp-lark
Based on FeiShu(飞书) / Lark's OpenAPI MCP server, manage user information, chats, emails, cloud documents, multidimensional tables, tasks, calendars, etc.
giasip-dispatch
A skill for sending a task to other AI models and collecting their results. It supports direct API calls, command-line tools and built-in internal agents, depending on the model.
chief-of-staff
The CEO's right hand — maintains validated project context, prepares task contracts, logs cross-department decisions, and runs the weekly review. Use when the user says "what's in flight", "resume the project", "log this decision", "weekly review", "turn this idea into a brief", or when multi-department work needs…
agent-evaluation
Measures a skill's practical value with fixed business tasks, paired with-skill and without-skill trials, explicit scoring, and honest uncertainty and cost reporting. Use when the user says "does this skill help", "benchmark our agent workflow", "compare this skill to the baseline", or "prove the new workflow works".
appsec-review
Produces a bounded defensive application security review: threat model, security-sensitive diff, dependencies, and secrets hygiene with source-grounded findings. Use when the user says "security-review this release", "check this integration before shipping", "review the auth change", or "audit our agent's data access".
skill-vetting
Reviews a candidate skill before activation with quarantined source inspection, version and license provenance, file hashes, static risk triage, and separate signature evidence. Use when the user says "check this skill before installing", "verify this NVIDIA skill", "review a skill update", or "is this plugin safe…