Borrowing it
Nothing to install: this file belongs to HistOracle-production/blabberer. 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/HistOracle-production/blabberer/main/CLAUDE.mdgit clone --depth 1 https://github.com/HistOracle-production/blabbererWrote 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/instructions/historacle-production/blabberer/claude-md)<a href="https://agentmods.dev/instructions/historacle-production/blabberer/claude-md"><img src="https://agentmods.dev/badge/instructions/historacle-production/blabberer/claude-md.svg" alt="Measured on agentmods" 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 | $0.01723 | $0.01723 |
| Opus 5 | $0.00861 | $0.00861 |
| Sonnet 5 | $0.00345 | $0.00345 |
| Haiku 4.5 | $0.00172 | $0.00172 |
Grade A, and why
blabberer CLAUDE.md scanned grade A with 1 finding 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 6d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- API: OpenRouter (`urllib.request`, no `requests` dep) How it starts
The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — Blabberer
What This Project Is
Blabberer is an open-source lip sync sprite generator. It takes a face image as input and outputs 9 mouth shape sprites (Preston Blair phoneme system) using Gemini AI via OpenRouter. It also includes a browser demo that plays audio with real-time lip sync animation using those sprites.
Origin: Extracted from the HistOracle production platform's lip sync pipeline.
GitHub org: historacle-ai | Owner: Arun Kashyap (kashyaparun25)
Claude Code Plugin
This repo is a Claude Code plugin. Users install it via:
/plugin install historacle-ai/blabberer
Then use the skill:
/blabberer:lip-sync-pipeline photo.jpg
Plugin structure
.claude-plugin/plugin.json— Plugin manifest (name, version, metadata)skills/lip-sync-pipeline/SKILL.md— The pipeline skill
Skills
/blabberer:lip-sync-pipeline— End-to-end sprite generation pipeline. Covers face detection, Gemini generation, post-processing, placement config, and demo integration.
Architecture
Two independent parts sharing no code:
blabberer/ Python package — image in, 9 mouth sprites out
demo/ Vanilla TS + Vite — sprites + audio in, lip sync animation out
Python Package (blabberer/)
| File | Purpose | Source |
|---|---|---|
shapes.py |
9 Preston Blair shape definitions + Gemini prompt template | Extracted from Historacle scripts/generate_lip_sync_sprites.py |
face_detect.py |
Auto face detection via MediaPipe (NEW — not in Historacle) | Written fresh |
generator.py |
Core: face detect → crop → Gemini API → 9 sprites | Extracted + refactored from scripts/generate_lip_sync_sprites.py |
postprocess.py |
rembg background removal + soft-edge feathering | Extracted from scripts/generate_soft_edge_sprites.py |
cli.py |
CLI entry point: blabberer generate <image> |
Written fresh |
reference/ |
12 Preston Blair cartoon reference JPGs (bundled) | Copied from Historacle frontend/public/lip-sync/reference/ with commas removed from filenames |
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.
- 6d ago First seen · 153 lines · 1,723 tokens per session scan A a4500ccf26f5
blabberer CLAUDE.md is an instructions file published in the GitHub repository HistOracle-production/blabberer (3 stars, last pushed 5mo ago), licensed MIT. It adds 1,723 tokens to every session, about $0.0086 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
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.
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.
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).
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).
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.
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.