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 agentmods add skills/deciqai/knowledge-skills/deep-worknpx 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.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 | $0.00123 | $0.01874 |
| Opus 5 | $0.00062 | $0.00937 |
| Sonnet 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 4d 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.
- 4d 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 (10 stars, last pushed 2d ago), licensed MIT. It adds 123 tokens to every session and 1,874 once invoked, about $0.0006 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
complete-partial-pr
Evaluate and complete an issue or PR where the submitted patch fixes only a narrow symptom of the reported pain point. Use when a contribution may miss adjacent integration surfaces, provider/spec semantics, roundtrip behavior, tests, docs, or historical maintainer decisions.
rulesync
Generates and syncs AI rule configuration files (.cursorrules, CLAUDE.md, copilot-instructions.md) across 20+ coding tools from a single source. Use when syncing AI rules, running rulesync commands, importing or generating rule files, or managing shared AI coding configurations.
taiyi-ui-design
TaiyiForge 第 4 阶段 — UI/UX 契约，产出 UI-DESIGN.md。四端通用。.
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
gh-bulk-issues
Orchestrate parallel Mastra Code headless instances to debug and fix multiple GitHub issues simultaneously.
aggregator
Daily fetch from a fixed public allowlist; score against the user's interests file; cluster into themes; push the digest to the configured channel.