prompt-fidelity vs Amicus
prompt-fidelity is no longer listed on any marketplace we read: these are its last known data, as of 2026‑10‑15.
prompt-fidelity is a plugin bundle for AI coding tools published by James Barney. No marketplace we read lists it any more. Amicus is an MCP server published by BourbonDog. Marketplaces we read that list it: 1 (Official MCP Registry). As of our marketplace pass on 2026-10-26. A plugin in this pair is no longer listed on any marketplace we read, so search engines are asked not to index the page.
Where each is published
| Marketplace |  Amicus | |
|---|---|---|
| Community marketplace barneyjm/prompt-fidelity | Removed on 2026-10-15 Version: 0.1.0 Forks (GitHub): 0 Stars (GitHub): 1 Not marked · First seen |
Not listed |
| Official MCP Registry | Not listed | Listed Version: 4.14.3 Downloads/month (npm): 3 297 Downloads/week (npm): 523 Forks (GitHub): 0 Stars (GitHub): 2 Not marked · First seen |
Each figure is the marketplace's own and is never added up across marketplaces. A marketplace that publishes no figure shows none: no number is not zero.
The facts side by side
| Fact | prompt-fidelityno longer listed · | Amicus |
|---|---|---|
| Marketplaces that list it (differs) | 0 | 1 |
| Stars (GitHub) (differs) | 1 | 2 |
| Forks (GitHub) | 0 | 0 |
| Last release (differs) | Not published | 2026-10-14 |
| Where it runs (differs) | Installs as a plugin bundle | On your machine (amicus) |
| Transport (differs) | Not stated | stdio |
| Tools it declares | Not published | Not published |
| Environment variables it asks for (differs) | Not published | 2, secrets among them: 1 |
| Parts of the bundle (differs) | 1 | Not a bundle |
| Licence | MIT | MIT |
| Repository (differs) | github.com/barneyjm/prompt-fidelity | github.com/bourbondog/amicus |
| Changes in the last 7 days | 0 | 0 |
| First seen (differs) | 2026-10-14 | 2026-10-11 |
Lines where the two differ have a tinted background and bold values. No value is marked better or worse: a plugin no marketplace lists any more is shown with its last known data, which we do not rank against current figures.
What to use instead of prompt-fidelity
Plugins still listed whose own names, descriptions, tools and skills are closest in meaning to it. Comparable, not endorsed.
-
Three-layer verification pipeline for AI output. Extracts claims, finds sources, and flags hallucination risks so humans can verify before acting.
-
HallucC — Hallucination & Safety Guardian
Fact-check LLM outputs with cited sources. API key: aihcc.cloud/keys.
-
Three-layer verification pipeline for AI output. Extracts claims, finds sources, and flags hallucination risks so humans can verify before acting.
-
Hallucination validator and factual grounding checker for LLM outputs.
-
Spectral — verified-knowledge oracle
Cross-check a factual claim against a verified knowledge graph before you assert it. Never guesses.
-
Independent fact-checking for AI answers: a verdict and sources for every claim.
What each says it does
prompt-fidelity
Self-check skill: decompose a request into verified vs inferred constraints, compute a fidelity score, and report which parts of an answer are auditable vs judgment calls.
Amicus
Multi-model LLM Council and parallel AI window for Claude Code. Fork any model, fold results back.
How to run each
prompt-fidelity
No data for an automatic command: what its marketplaces declare does not say unambiguously how to connect it.
Amicus As a local MCP server: npm package
claude mcp add --env "OPENROUTER_API_KEY=<YOUR_OPENROUTER_API_KEY>" --transport stdio amicus -- npx -y amicus mcpRequires: OPENROUTER_API_KEY (secret)
Commands built only from what the marketplaces declare; the full set for every client is on each card.
Tools each declares
Neither one's marketplaces publish a list of tools, so there is nothing to compare.
Settings each asks for
The marketplaces of prompt-fidelity publish no settings it asks for, so we do not compare settings.
What it can do: prompt-fidelity · What it can do: Amicus · Compare two other plugins
Data comes from public marketplace files in GitHub repositories of their authors. Data comes from the Official MCP Registry (registry.modelcontextprotocol.io), CC0 1.0. Figures come from our own regular passes over the marketplaces, last read on . We publish no contact details for plugin publishers.