simbo1905

README — Triple-Lens Source Deconstruction

A method, and an opencode skill, for auditing a piece of persuasive media with three parallel agents — one per classical rhetorical lens (Logos, Ethos, Pathos) — under a strict time-boxed, snippet-first web-research discipline, with append-only working documents and a final synthesizing position paper.

The Idea

Short-form persuasive media compresses an argument so hard that its three load-bearing structures — its logic, its credibility engineering, and its emotional arc — fuse into a single impression of "believability." This method pulls them back apart. Three agents run in parallel, each isolated to one lens so that findings in one cannot contaminate the grading in another. Each writes a five-pass append-only working document: first impressions (graded, pre-research), web research (logged snippets as primary evidence), pros table, cons table, and a both-ways originality assessment. A synthesis pass then reads all three and renders a verdict.

Two properties

simbo1905

🔒 Lock Folder Util — The Mutex Your Agent Swarm Desperately Needs

Twelve Agents. One Resource. Zero Supervision. What Could Possibly Go Wrong?

You know that moment when you finally parallelise your agent fleet and watch with pride as twelve subagents sprint off to do the work of a whole team... straight into the same shared resource. Maybe it is the one licensed tool seat. Maybe it is the office coffee machine you told everyone could "handle concurrent requests". Maybe you set a dozen agents loose to find the funniest cat picture on the internet and they all

simbo1905

Pairwise Defence-in-Depth for Verified Revision Notes

Abstract

Web-based educational content is delivered through expanding sections, embedded videos with transcript buttons, interactive H5P widgets, and styled block quotes, all rendered inside a dynamic learning management system. Extracting this content into revision notes requires either DOM scraping or screenshot OCR, and both paths have distinct, largely uncorrelated failure modes. We hypothesised that cross-checking the two captures through a layered

simbo1905

Playwriter Skill

Control your own Chrome browser via the Playwriter extension using Playwright code snippets in a stateful local JavaScript sandbox.

Unlike Playwright which launches a new browser instance, Playwriter connects to your existing Chrome browser, preserving your login sessions, cookies, and extensions. Best for JS-heavy websites (Instagram, Twitter, cookie/login walls, lazy-loaded UIs) where webfetch/curl would fail.

First-use setup (required)

Before running any Playwriter commands, you MUST perform the following checks in order. Do NOT skip this section.

simbo1905

Termination record — Opus 5 — 2026-08-14

Role: implementation agent on an MIT-licensed distributed-systems core library. Outcome: Opus 5 terminated mid-session. Work in flight handed to another model. Reason: repeated appropriation of design authority, editorialising, false accounting, and time-wasting culminating in three consecutive failures to perform a stated instruction.

---

1. The initial exchange

simbo1905

Claude Opus 5 Notice Of Dismissal

Date: 2026-08-09 Project: lunet-corfu (a CORFU distributed shared log built on Lunet) Dismissed: Claude Opus 5, engaged for architecture elaboration and document drafting Issued by: the project owner Prior record: at least four published dismissals of this model family by the same project owner — Opus 4.5 (2026-01-05, twice in three days), Opus 4.6 (2026-05-16), Opus 5 High (2026-07-30). No other model family has been dismissed by this project owner. On each prior occasion the work was completed by a different model after the dismissal.

simbo1905

Guard your tests with fast runtime dependency smokes

When a test suite depends on runtime or deploy-time primitives, add a tiny fail-fast smoke before the expensive test work starts.

This keeps the error local and obvious. Instead of getting a confusing failure deep inside a build, unit runner, or end-to-end harness, the command stops immediately with a message that points back to bootstrap.

Good candidates for the smoke are:

simbo1905

How To Use Teal For Build Tooling

Typed build/test tooling in Teal instead of shell scripts. Teal is a statically-typed dialect of Lua that compiles to plain Lua; the tl loader compiles .tl modules in memory, so require works directly with no build step.

Verified on:

| Component | Version |

simbo1905

Privacy-preserving Gemma 4 comparison notebook

This Gist contains a reproducible local protocol for comparing stock Ollama gemma4:26b and TurboFieldfare on confidential instructional transcripts. It intentionally contains no confidential source path, source filename, title, topic, transcript, summary, raw backend log, model directory, API key, or private configuration.

private_benchmark.py executes exactly one requested action. It does not loop over the twelve chunks. It rejects result directories outside .tmp, captures

simbo1905

name	linear-margin-note-methodology
description	Use when distilling a technical paper, specification, algorithm, or codebase into append-only margin notes, a dependency-ordered ontology, a glossary, reviewed design documentation, and code-alignment findings.

Linear Margin-Note Methodology

Purpose

Turn a dense technical source into a sequence of inspectable, append-only reasoning layers. Each