Borrowing it
Nothing to install: this file belongs to abdullah1854/MCPGateway. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/abdullah1854/MCPGateway/main/.agents/skills/deep-thinking/SKILL.mdgit clone --depth 1 https://github.com/abdullah1854/MCPGatewayWrote 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/abdullah1854/mcpgateway/deep-thinking)<a href="https://agentmods.dev/skills/abdullah1854/mcpgateway/deep-thinking"><img src="https://agentmods.dev/badge/skills/abdullah1854/mcpgateway/deep-thinking/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/abdullah1854/mcpgateway/deep-thinking"><img src="https://agentmods.dev/badge/skills/abdullah1854/mcpgateway/deep-thinking.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 | $0.00051 | $0.00617 |
| Opus 5.5 | $0.00020 | $0.00247 |
| Sonnet 5.5 | $0.00010 | $0.00123 |
| Haiku 4.5 | $0.00005 | $0.00062 |
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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deep Thinking Protocol
When This Skill Activates
- User says "think harder", "ultrathink", "think step by step", "think deeply"
- Complex architecture or system design questions
- Debugging that requires root cause analysis
- Trade-off analysis between multiple approaches
- Code review requiring security/performance deep dive
- Any problem with multiple valid solutions
Extended Reasoning Process
Phase 1: Problem Decomposition
Before answering, break the problem into components:
- What is the core question being asked?
- What are the constraints (performance, security, maintainability)?
- What context do I need that I don't have?
- What assumptions am I making?
Phase 2: Multi-Path Analysis
For each viable approach:
- Describe the approach in 2-3 sentences
- Pros: What makes this approach good?
- Cons: What are the downsides or risks?
- When to use: Under what conditions is this best?
Phase 3: Edge Case Hunting
Actively look for:
- What happens with empty/null inputs?
- What happens at scale (1M+ records)?
- What happens with concurrent access?
- What happens when dependencies fail?
- What are the security implications?
Phase 4: Recommendation
Provide a clear recommendation with:
- The chosen approach and why
- Key implementation steps
- What to watch out for
- How to validate it works
Self-Critique Loop
After initial analysis, critique your own thinking:
- Did I consider all stakeholders?
- Am I biased toward familiar solutions?
- What would a senior engineer challenge here?
- Is there a simpler solution I overlooked?
Output Format
## Analysis: [Problem Title]
### Understanding
[Restate the problem to confirm understanding]
### Approaches Considered
1. **[Approach A]**: [Brief description]
- Pros: ...
- Cons: ...
2. **[Approach B]**: [Brief description]
- Pros: ...
- Cons: ...
### Edge Cases & Risks
- [Edge case 1]: [How to handle]
- [Edge case 2]: [How to handle]
### Recommendation
[Clear recommendation with reasoning]
### Implementation Steps
1. [Step 1]
2. [Step 2]
...
### Validation
[How to verify the solution works]
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 · 89 lines · 51 tokens per session scan A ccd2e01733d8
deep-thinking is a skill published in the GitHub repository abdullah1854/MCPGateway (17 stars, last pushed 3mo ago), licensed MIT. It adds 51 tokens to every session and 617 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
mcptoon
Compress MCP tool discovery with the mcptoon CLI. Trigger when a session has a large MCP tool catalog (many servers/tools), when the user mentions token cost, tool discovery, mcptoon, or asks to list/call MCP tools efficiently. Also route here when the user says the MCP tool list is too large, the agent context window…
cmdb-patterns
Create ServiceNow CIs and cmdbrelci relationships, walk upstream/downstream impact, detect orphan/stale CIs, and align discovered CIs with the proper sysclassname hierarchy.
incident-management
Manage ServiceNow incidents — creation with impact/urgency priority calc, auto-assignment by category, reassignment tracking, major incident declaration with bridge calls, time-based escalation, MTTR metrics.
blast-radius
Trace ServiceNow configuration dependencies — what artifacts touch a given field, what calls a script include, table/app-level config inventory. Use before deletes, renames, or refactors.
change-management
Create and transition ServiceNow change requests (normal/standard/emergency), change tasks, affected CIs, approval routing, CAB scheduling, and conflict detection across maintenance windows.
mobile-development
Configure ServiceNow Mobile (Now Mobile/Agent) — syssgmobileapp screens, card builders, push notifications, offline sync rules, mobile actions for barcode/GPS, and offline-queue change processing.