advanced-prompting-engine: Command for Claude Code

.claude/commands/research-semantic-improvement.md

research-semantic-improvement is a command for Claude Code from JoshuaRamirez/advanced-prompting-engine. It costs 0 tokens per session (928 once invoked), scanned A, original, MIT.

A research command for improving an instrument that measures philosophical intent in literary texts. It targets benchmark results across works such as Shakespeare, Genesis, Marx, and Aristotle.

In plain words
What is it for?
For planning experiments with word embeddings and sentence-composition methods to improve the instrument's text-analysis accuracy.
Why use it?
It structures investigation into problems such as words having multiple meanings, overly broad categories, and missing vocabulary.

Command for Claude Code

Written for Claude Code: installed under .claude/.

This is JoshuaRamirez/advanced-prompting-engine's own configuration. It tells Claude Code how to work on advanced-prompting-engine 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 advanced-prompting-engine configures →

Part of the advanced-prompting-engine plugin — 1 skill, 3 commands, 1 MCP server shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to JoshuaRamirez/advanced-prompting-engine. 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/JoshuaRamirez/advanced-prompting-engine/main/.claude/commands/research-semantic-improvement.md
Clone the repo
git clone --depth 1 https://github.com/JoshuaRamirez/advanced-prompting-engine

Made for: Claude Code.

Or install advanced-prompting-engine, the plugin that ships this one along with the rest of its 1 skill, 3 commands, 1 MCP server.

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 research-semantic-improvement

README.md
[![agentmods](https://agentmods.dev/badge/commands/joshuaramirez/advanced-prompting-engine/research-semantic-improvement/github.svg)](https://agentmods.dev/commands/joshuaramirez/advanced-prompting-engine/research-semantic-improvement)
Your own site
<a href="https://agentmods.dev/commands/joshuaramirez/advanced-prompting-engine/research-semantic-improvement"><img src="https://agentmods.dev/badge/commands/joshuaramirez/advanced-prompting-engine/research-semantic-improvement/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.

agentmods 80×15 button for research-semantic-improvement

Your own site · 80×15
<a href="https://agentmods.dev/commands/joshuaramirez/advanced-prompting-engine/research-semantic-improvement"><img src="https://agentmods.dev/badge/commands/joshuaramirez/advanced-prompting-engine/research-semantic-improvement.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 928 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00000 $0.00928
Opus 5 $0.00000 $0.00464
Sonnet 5 $0.00000 $0.00186
Haiku 4.5 $0.00000 $0.00093

Measured 12d ago against content hash 96a0ee595f31, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

research-semantic-improvement 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 12d 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/commands/research-semantic-improvement.md · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Research: Semantic Bridge Improvement

Design a research plan to advance a philosophical intent measurement instrument from its current literary text benchmark score to 20/20 across Shakespeare, Genesis, Marx, MLK, Newton, Aristotle, Tao Te Ching, and Descartes. The instrument embodies a twelve-face geometric manifold where each face is a 12x12 grid with constitutive character on the x-axis and dispositional orientation on the y-axis. Its parser inverts three inference layers — axis meta-meaning, polarity convention, and sub-dimensions — by projecting intent tokens onto pre-computed GloVe 100d direction vectors. Remaining failures stem from: word polysemy where context determines domain, centroid broadness where some faces attract generic vocabulary, and vocabulary gaps where literary terms fall outside the word bridge. The research plan must systematically evaluate: (1) multi-sense static embeddings that provide sense-specific vectors without runtime neural inference — assess LMMS, sensEmbed, DeConf, and AutoExtend for GloVe compatibility and numpy-only resolution; (2) smooth inverse frequency sentence composition (Arora et al. 2017) as a replacement for simple word averaging — assess whether the principal component removal step sharpens face discrimination; (3) counter-fitting with antonym-only constraints and no face-cohort attraction to avoid centroid destabilization; (4) product quantization or dimensionality-indexed vocabulary expansion to cover 50K words within 10MB artifact budget; (5) character n-gram approximation for out-of-vocabulary literary terms using pre-computed prefix/suffix tables. For each technique, provide: expected improvement rationale, mathematical formulation, numpy implementation sketch, artifact size estimate, and risk assessment. Rank by expected impact on the specific benchmark failures.

Constraints

  • Runtime: numpy only. No torch, tensorflow, onnxruntime, spacy, gensim, nltk.
  • Artifacts: Ship with pip package. Under 10MB total.
  • Build time: Any tool on developer machine. GloVe 6B already cached.
  • Architecture: GeometricBridge loads pre-computed numpy arrays, intent parser tokenizes + looks up + averages. Improvements produce better arrays, not change runtime flow.

Read the full file on GitHub · 55 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. 12d ago First seen · 55 lines · 0 tokens per session scan A 96a0ee595f31

Subscribe to this mod's changes

research-semantic-improvement is a command published in the GitHub repository JoshuaRamirez/advanced-prompting-engine (0 stars, last pushed 15d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 928 tokens. 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 2026-08-31.