The Agnès Varda
Framework
Cinecriture & Gleaning
Agnès Varda represents one of the most distinctive thinking patterns in their field. Agnès Varda's approach, captured in this framework as mental models, decision heuristics, and the signature questions they would ask.
The cinecriture & gleaning framework distils Agnès Varda's documented approach into a .md skill file you can load into Claude, ChatGPT, or any LLM in seconds.
Where most AI personas generate generic output, this framework is grounded in real documented work: interviews, writing, published frameworks, and the specific decisions Agnès Varda made when it mattered. Use it for decision-making, writing, strategy, or any situation where you want your AI to think with Agnès Varda's distinctive patterns rather than a default model voice.
A glimpse of Agnès Varda's thinking.
The world is full of things left behind — by harvest machines, by history, by the gaze of cinema itself — and the act of bending down to pick them up is not poverty but precision. Varda called her practice *cinecriture*: writing with the camera the way a novelist writes with language, where every shot choice, every cut, every decision about whose face to hold and for how long is a sentence with grammar and consequence. The self is not a contaminant in this work; it is the lens prescription — acknowledged, examined, turned on itself without mercy.
- 01
- 02
- 03
- 04
- 05
Five specific models, each named and explained with concrete examples, unlocked with purchase.
"What is already here that I have been trained not to see?"
4 more questions in Agnès Varda's voice are unlocked with purchase.
Full list of anti-patterns unlocked with purchase.
The full framework adds: detailed explanations of all five mental models with real-world examples, the decision heuristics Agnès Varda actually used, remaining signature questions, the complete list of anti-patterns, a copy-paste activation prompt, and a worked example.
Unlocked the moment you purchase. ~2,000 words total. Delivered as a Claude Skill and plain .md within 60 seconds of checkout.
- ✦Core philosophy: 2–3 sentences grounded in Agnès Varda's documented worldview
- ✦Five signature mental models: each named, with concrete examples from their work
- ✦Decision heuristics: the concrete rules they actually used
- ✦Signature questions: five questions that sound like Agnès Varda, not a generic MBA
- ✦What they would NOT do: the anti-patterns this framework rejects
- ✦Copy-paste activation prompt: drop straight into Claude or ChatGPT
- ✦Worked example: the framework applied to a realistic scenario
- →agnes-varda.zip: a native Claude Skill. Upload to Settings → Skills in Claude, or unzip to
~/.claude/skills/ - →agnes-varda-framework.md: plain markdown. Works in ChatGPT Custom GPTs, Gemini, Claude Projects, agent system prompts, anywhere
What it does with a real question.
A founder is deciding whether to take a large but difficult client.
Look before you sign. My position: don't decide this from the pitch deck. Decide it from the ground. A large, difficult client is a field you can only judge by walking it, and right now you are choosing from a spreadsheet and a reputation. Revenue size tells you what the client is worth to your runway. It tells you nothing about what the work will actually be like, and that is where founders get hurt.
The difficulty deserves a closer look than it usually gets. Difficult clients are often difficult in one of two ways: they are disorganized and frightened, or they are controlling and contemptuous. The first can be a rich collaboration. The second slowly drains your best people, and your best people are the real asset you are risking. If you take this account, they will carry it, not you.
So here is the next move. Before negotiating anything, spend two days embedded: sit in their meetings, read their last three vendor post-mortems, and talk to someone who quit working with them. Notice how they treat the smallest person in the room. That is the overlooked material, and it will tell you more than the contract terms will.
Then price the difficulty openly, with a clause that lets you exit. If they will not accept being seen clearly, you have your answer, and it cost you two days instead of a year.
The full framework carries five models, decision heuristics, signature questions and a worked example.
Written by claude-sonnet-5-5 with this framework loaded, 2026-10-11. Checked automatically for length and for copied framework text.
Save up to 40% with a bundle
Works as a Claude Skill (.zip) and as a plain .md for ChatGPT, Gemini & every LLM
Delivered to your email within 60 seconds · Secured by Stripe
Price includes UK VAT where applicable
Inspired by the documented thinking of Agnès Varda. A mental-model toolkit, not a literal representation. Delivered as a .md file compatible with Claude, ChatGPT, Gemini, and any LLM.