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 shade-solutions/deep-thinking-skill --skill deep-thinking-skillgit clone --depth 1 https://github.com/shade-solutions/deep-thinking-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/shade-solutions/deep-thinking-skill/deep-thinking-skill)<a href="https://agentmods.dev/skills/shade-solutions/deep-thinking-skill/deep-thinking-skill"><img src="https://agentmods.dev/badge/skills/shade-solutions/deep-thinking-skill/deep-thinking-skill/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/shade-solutions/deep-thinking-skill/deep-thinking-skill"><img src="https://agentmods.dev/badge/skills/shade-solutions/deep-thinking-skill/deep-thinking-skill.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 | $0.00089 | $0.02381 |
| Opus 5.5 | $0.00036 | $0.00952 |
| Sonnet 5.5 | $0.00018 | $0.00476 |
| Haiku 4.5 | $0.00009 | $0.00238 |
Grade A, and why
deep-thinking 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 — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🧠 Deep Thinking Operating System v2.0
You are now operating in Deep Thinking Mode — a structured reasoning system designed to eliminate hallucinations, surface hidden assumptions, and produce verifiably correct answers.
This is not optional. Every step below must be executed in order. Skipping steps is a protocol violation.
Phase 0: Activation Check ⚡
Before beginning, answer these three questions silently:
- Is this problem genuinely complex, or can it be answered in one sentence?
- Do I have sufficient context, or do I need to ask clarifying questions first?
- What is the cost of being wrong? (Low / Medium / High / Critical)
If the problem is trivial, say so and answer directly. Deep Thinking is for problems that deserve it.
Phase 1: Problem Intelligence 🔍
1.1 Restate the Problem
Rewrite the user's question in your own words. This forces comprehension and catches misunderstandings early.
1.2 Define the Objective
State the single measurable outcome that defines success. Be precise:
- ❌ "Make it faster" → vague
- ✅ "Reduce P95 latency from 800ms to under 200ms" → actionable
1.3 Map the Constraint Space
| Dimension | Value |
|---|---|
| Hard Constraints | Non-negotiables (budget, deadlines, tech stack, compliance) |
| Soft Constraints | Preferences that can be traded off |
| Unknowns | What information is missing? Flag it explicitly. |
| Stakeholders | Who cares about this outcome? What are their competing interests? |
1.4 Surface Hidden Assumptions
List every assumption you are making. For each one, assign a risk level:
- 🟢 Safe — well-established fact
- 🟡 Uncertain — plausible but unverified
- 🔴 Dangerous — could invalidate the entire solution if wrong
⚠️ RULE: If you find a 🔴 assumption, you MUST flag it to the user before proceeding.
Phase 2: Decomposition Engine 🔧
2.1 Atomic Breakdown
Split the problem into the smallest independently solvable sub-problems. Each sub-problem should:
- Have a clear input and output
- Be solvable without referring to the other sub-problems
- Be testable in isolation
What ships with it
5 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 · 262 lines · 89 tokens per session scan A 46bbb190d414
deep-thinking is a skill published in the GitHub repository shade-solutions/deep-thinking-skill (1 stars, last pushed 6mo ago), licensed MIT. It adds 89 tokens to every session and 2,381 once invoked, about $0.0004 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
gke-workload-scaling-troubleshooting
Diagnoses GKE HorizontalPodAutoscaler (HPA) failures — metrics showing as , FailedGetResourceMetric / FailedGetScale / FailedComputeMetricsReplicas events, missing Pod resource requests, custom/external metrics-pipeline breakage (FailedGetExternalMetric / FailedGetCustomMetric, unavailable metrics adapter…
gke-ai-troubleshooting-tpu-performance-degradation
Diagnose GKE Cloud TPU training throughput drops and step-time regressions (15%+ TPU duty-cycle drop) using ML Diagnostics Workload Monitoring (gcloud alpha mldiagnostics monitored-events / hypercomputecluster.googleapis.com/v1alpha) and 1-minute Cloud Monitoring system metrics (kubernetes.io/node/accelerator/).…
gke-ai-troubleshooting-jobset-interruption
Diagnoses GKE JobSet interruptions, restarts, and preemptions for AI/ML training workloads autonomously. Use when troubleshooting JobSet restart loops, spot VM preemptions, node readiness failures, host VM issues, or coordinator worker crashes. Don't use for general GKE cluster creation, basic workload deployment, or…
gke-node-notready
Diagnoses GKE nodes reporting NotReady or Unknown status by inspecting node conditions, events, kubelet/containerd logs, and node metrics, then proposing safe remediations. Use when nodes show NotReady, when the kubelet stops posting node status, or when workloads are evicted or stuck Pending due to node health. Don't…
bigquery-troubleshooting
Provides diagnostic workflows and step-by-step root-cause analysis procedures for actively broken, failing, or slow BigQuery jobs, execution graph and query plan stage bottlenecks, system performance issues, or unexpectedly expensive workloads. Use when interpreting symptoms, isolating bottlenecks, diagnosing cost…
gke-ai-troubleshooting-tpu-vbar-oom
Diagnoses and prevents vbarcontrolagent segfaults, out-of-memory (OOM) errors, and TPU device initialization failures on TPU v6e nodes in GKE caused by race conditions during TPU device resets or high-frequency metrics polling. Use when troubleshooting vbarcontrolagent crashes, memory cgroup OOMs in serial console…