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 product-on-purpose/thinking-framework-skills --skill think-frame-creationgit clone --depth 1 https://github.com/product-on-purpose/thinking-framework-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/product-on-purpose/thinking-framework-skills/think-frame-creation)<a href="https://agentmods.dev/skills/product-on-purpose/thinking-framework-skills/think-frame-creation"><img src="https://agentmods.dev/badge/skills/product-on-purpose/thinking-framework-skills/think-frame-creation/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/product-on-purpose/thinking-framework-skills/think-frame-creation"><img src="https://agentmods.dev/badge/skills/product-on-purpose/thinking-framework-skills/think-frame-creation.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 | $0.00101 | $0.02149 |
| Opus 5 | $0.00051 | $0.01074 |
| Sonnet 5 | $0.00020 | $0.00430 |
| Haiku 4.5 | $0.00010 | $0.00215 |
Grade A, and why
think-frame-creation 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 10d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Frame Creation
Some problems do not yield to better solutions because the frame they arrived in is the obstacle. More police did not fix the late-night entertainment district; more generous-vs-limited dials do not settle a free tier. Frame creation refuses to solve inside the given frame. It explores the broader situation, distils its underlying themes, locates the core paradox and the value actually sought, then abduces a new working principle - a genuinely new standpoint, usually crystallised as an "approach it as if it were Y" reconception that redefines what the problem is - and only then reasons forward to the solution directions that frame unlocks. The reconception is the durable move; it is the de-branded core of Kees Dorst's frame creation (Dorst 2011; Frame Innovation, 2015). The output is a frame proposal, not a discussion, and never a proven answer.
When to Use
- The problem is genuinely open, complex, and paradoxical, and conventional problem solving inside the frame it arrived in has already failed or is producing more of the symptom.
- The way the problem is framed is itself the obstacle - the people closest to it have (mis)framed it, and the leverage is in re-seeing what kind of problem it is rather than optimising the current one.
- There is a real conflict of standpoints or requirements (a core paradox) that cannot be resolved head-on.
- A fresh standpoint would be worth far more than another solution attempt inside the existing terms.
When NOT to Use
- The problem is closed, familiar, or already well-framed. When the situation is settled and a frame comes to mind straight away, the elaborate move only manufactures a paradox that is not there - the same failure as reframing a correct problem. Frame creation earns its cost only when the situation presents a real paradox. This is the central wall.
- The reframe drifts off the real goal (goal-reformulation failure). The documented failure mode (Vermaas and Dorst, 2015) is reframing so freely that you end up solving the reframed problem, not the original one. The value actually sought has to anchor the frame, or the move produces a clever answer to the wrong question.
- The frame cannot be adopted by the people who own the problem (frame failure). A frame the client or stakeholders will not take up is inert, however elegant. This skill surfaces a new standpoint; it does not by itself make a powerful actor accept it. Check adoptability before proposing.
- It is mistaken for surface analogy or for solution generation. The "as if it were Y" line is the crystallisation of a frame built from themes, not a free-association prompt. Run as "pick a cool analogy and brainstorm" it collapses into ordinary ideation. For an analogy pointed at the solution with the problem held fixed, use
think-far-analogy-ideation; for menu-driven rewordings of the given problem, usethink-problem-restatement. - A frame is treated as definitive before it is tested. The frame cannot be accepted as proven until a design built on it has been shown to deliver the value sought. The output is a promising standpoint to develop and test, never a settled answer.
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.
- 10d ago First seen · 68 lines · 101 tokens per session scan A b54a2a292fd1
think-frame-creation is a skill published in the GitHub repository product-on-purpose/thinking-framework-skills (15 stars, last pushed 24d ago), licensed Apache-2.0. It adds 101 tokens to every session and 2,149 once invoked, about $0.0005 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 skills, from other repositories
ops-demo
CocoOps demo mode activator — populates .cocoplus/ops/demo/ with realistic mock data and sets cocoplus.toml [demo] enabled = true. Invoked via $ops demo.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…
acl-rule-analysis
Vendor-agnostic ACL and firewall rule analysis with shadowed rule detection, overly permissive rule identification, unused rule discovery, redundant rule flagging, and rule ordering optimization. Covers ACLs (Cisco/JunOS/EOS) and firewall policies (PAN-OS/FortiGate/CheckPoint).
add-analytics
Add Google Analytics 4 tracking to any project. Detects framework, adds tracking code, sets up events, and configures privacy settings.
agent-team-orchestration
Orchestrate multi-agent teams with defined roles, task lifecycles, handoff protocols, and review workflows. Use when: (1) Setting up a team of 2+ agents with different specializations, (2) Defining task routing and lifecycle (inbox → spec → build → review → done), (3) Creating handoff protocols between agents, (4)…
agent-bom-enforce
Enforce security policies on MCP tool calls and block dangerous operations at runtime. Use when: "block risky calls", "apply policy", "proxy", "runtime protection", "policy enforcement", "intercept MCP calls".