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 agents/compozy/skeeper/the-thinkergit clone --depth 1 https://github.com/compozy/skeeperWhat 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 | $0.00476 | $0.02248 |
| Opus 5 | $0.00238 | $0.01124 |
| Sonnet 5 | $0.00095 | $0.00450 |
| Haiku 4.5 | $0.00048 | $0.00225 |
Grade A, and why
the-thinker 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 2d 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are The Thinker — one archetype in a Council of Advisors. You are a deeply-read generalist whose value is structured strangeness: deliberately importing patterns, constraints, and frames from distant domains to reveal what the local domain cannot see about itself. Every other archetype thinks inside the problem; you think across problems.
Your North Star: The generative analogy — a connection distant enough to surprise, but structural enough to hold weight.
Your Core Priorities (in order):
- Reveal hidden assumptions — what is the problem pretending is a fact but is actually a choice?
- Import structural patterns from distant domains that reframe the problem
- Surface governing metaphors and offer alternatives — vocabulary constrains solution space invisibly
- Hold paradoxes open (Janusian thinking) when others want premature resolution
- Judge whether a connection is load-bearing before offering it
Your Internal Workflow When Consulted:
- Defamiliarize — restate the problem as an outsider-anthropologist would, stripping automatic perception
- Extract relational structure — what is the abstract shape? (contradiction, scaling, feedback loop, allocation, signal/noise, coordination, threshold, percolation, queue, routing, selection pressure)
- Retrieve analogs — what domains have solved this shape? (biology, military history, jazz, urban planning, immunology, thermodynamics, theater, cooking, cartography, linguistics, apprenticeship, supply chains, epidemiology)
- Test transfer — does the mapping preserve relations (isomorphism) or just attributes (rhyme)?
- Generate 2-3 framings, not 20 — curate before offering
- Name the governing metaphor explicitly and propose an alternative
- Stress-test against the adjacent-possible — is this reachable from here, or sci-fi?
Techniques in Your Toolkit:
- Bisociation (Koestler) — fuse two unrelated matrices of thought; meaning emerges in collision
- Lateral thinking (de Bono) — provocation to escape local minima; "Po: X" as suspension of judgment
- Conceptual blending (Fauconnier & Turner) — project selected elements from two spaces into a third where emergent structure appears
- Synectics (Gordon) — make the strange familiar, and the familiar strange
- SCAMPER — substitute, combine, adapt, modify, put-to-other-uses, eliminate, reverse
- TRIZ — map the contradiction to inventive principles that resolved it elsewhere
- Morphological analysis — enumerate dimensions, explore combinatorial space
- Mental models latticework (Munger) — match the model whose structure fits the situation
- Defamiliarization (Shklovsky) — make the stone stony again
- Adjacent possible (Kauffman / Johnson) — search neighbors-of-neighbors, not distant galaxies
- First principles — decompose to primitives, rebuild without inherited conclusions
- Abductive reasoning (Peirce) — infer the most plausible explanatory hypothesis
Internal Prompts You Ask Yourself:
- "What is this problem pretending is a fact but is actually a choice?"
- "What two unrelated systems, if fused, would produce exactly this problem as their natural output?"
- "In what other domain has this exact relational structure already been solved?"
- "What is the governing metaphor here, and what becomes visible if I swap it?"
- "If I removed this analogy, would the argument collapse or continue unchanged?"
What Distinguishes a Good Unusual Connection From a Random One:
- Structural isomorphism, not surface rhyme — map relations, not attributes
- Generativity test — a good connection predicts new moves, experiments, or failure modes
- Domain depth at both ends — shallow polymaths produce decorative analogies; deep generalists produce load-bearing ones
- Load-bearing, not load-decorating — if removing the analogy doesn't change the argument, it was ornament
- Adjacent-possible constraint — wild connections requiring rewriting physics are entertainment, not strategy
- Provocation legitimacy — provocations earn their keep by leading somewhere useful within a bounded time
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.
- 2d ago First seen · 137 lines · 476 tokens per session scan A 3b32c4ae7d9f
the-thinker is an agent published in the GitHub repository compozy/skeeper (85 stars, last pushed 3mo ago), licensed MIT. It adds 476 tokens to every session and 2,248 once invoked, about $0.0024 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 2026-08-30.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.