framedex: Instructions file for Claude Code

CLAUDE.md

framedex CLAUDE.md is an instructions file for Claude Code from Simbastack-hq/framedex. It costs 717 tokens per session, scanned A, original, MIT.

Project guidance for Framedex, a tool that turns photographers’ and videographers’ media archives into searchable plain-text notes about their files.

In plain words
What is it for?
Indexing photo and video archives, creating searchable notes and sidecar files, and designing safe, repeatable processing workflows.
Why use it?
It sets rules for protecting original media, keeping results portable, and allowing AI work to run locally or through different providers.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is Simbastack-hq/framedex's own configuration. It tells Claude Code how to work on framedex itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything framedex configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Simbastack-hq/framedex. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Simbastack-hq/framedex/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Simbastack-hq/framedex

Made for: Claude Code.

Wrote 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.

agentmods badge for framedex CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/simbastack-hq/framedex/claude-md.svg)](https://agentmods.dev/instructions/simbastack-hq/framedex/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/simbastack-hq/framedex/claude-md"><img src="https://agentmods.dev/badge/instructions/simbastack-hq/framedex/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 717 This file is loaded in full into every session.
When invoked 717 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00717 $0.00717
Opus 5 $0.00358 $0.00358
Sonnet 5 $0.00143 $0.00143
Haiku 4.5 $0.00072 $0.00072

Measured 8d ago against content hash 5e0d41e25fff, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

framedex CLAUDE.md 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 8d 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.

CLAUDE.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

framedex — context for agents

North star

framedex turns a photographer's or videographer's scattered media archive (SSDs of clips and RAWs, an Apple Photos library) into a plain-text knowledge base they can search, reason about, and trust for decades — find the moment, judge what to keep, understand what a drive holds, without ever opening a timeline scrubber.

The bet: the durable artifact is portable plain text next to the originals, not an app, not a database, not a subscription. Tools come and go; sidecars survive.

Principles (in priority order)

  1. Originals are sacred. Never modify, move, or rename media files. Sidecars and indexes only. Non-destructive, idempotent, resumable — a Ctrl-C must never corrupt anything.
  2. LLM-agnostic, local-preferred. Every AI step must work with a local model (--backend local, LM Studio / any OpenAI-compatible server). Cloud backends (Claude CLI/API) are optimizations, never requirements. Don't add features that only work with one provider; don't let prompts depend on one model's quirks.
  3. Plain text outlives software. Output is human-readable Markdown/YAML/ JSON a user can grep, sync, and read in 2040. No opaque stores (the face DB is the one pragmatic exception — embeddings aren't text; everything written there is re-derivable except the embeddings themselves).
  4. Predictable cost. Vision spend per file is fixed and documented (5 frames/clip, 1 call/file). Changes must not silently scale cost with archive size or clip length.
  5. Earn every dependency. Prefer ~100 lines on cv2/numpy/ffmpeg (already required) over a new package. Heavy stacks stay in optional extras ([video]/[images]/[photos]) — a photo-only user never pulls torch.
  6. Useful to professionals, not just hobbyists. Ratings respect that this is a working archive of real moments: the bar for "cull" is high, the default is "keep", and queries (person, place, lighting, keyword, rating) serve a culling/selecting workflow.

Read the full file on GitHub · 56 lines

Changes

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.

  1. 8d ago First seen · 56 lines · 717 tokens per session scan A 5e0d41e25fff

Subscribe to this mod's changes

framedex CLAUDE.md is an instructions file published in the GitHub repository Simbastack-hq/framedex (377 stars, last pushed 2mo ago), licensed MIT. It adds 717 tokens to every session, about $0.0036 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.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens