privacyPolicyURL should be present for marketplace readiness.
Logic Probe
Design-document & plan claim verification — checks every verifiable claim against the codebase, escalates behavioral claims to executable-model verification, compares before/after models for regression detection, and mines concurrency risk claims
amethyst-luna/logicprobe · v0.9.0 · Development & Workflow
Trust Score
78
Security
76
Surfaces
2
What is Logic Probe?
Logic Probe is a published development & workflow plugin for AI coding agents in the codex ecosystem, developed by Amethyst Luna and distributed through the HOL AI plugin registry. Design-document & plan claim verification — checks every verifiable claim against the codebase, escalates behavioral claims to executable-model verification, compares before/after models for regression detection, and mines concurrency risk claims
- Canonical slug
- amethyst-luna/logicprobe
- Version
- v0.9.0 · updated Oct 6, 2026
- Open data
- entity.json (JSON-LD)
Trust & Reputation
Factor Analysis
Per-metric points (0–100 each) combined via a weighted average into the overall score.
Registry Snapshot
- Canonical profile
- https://hol.org/registry/plugins/amethyst-luna%2Flogicprobe
- Publisher verification
- No
- Marketplace source
- Unknown
- Scanner
- Broker fallback
- Safety label
- review
- Digest verified
- Yes
Trust & reputation
Trust & Reputation
Factor Analysis
Per-metric points (0–100 each) combined via a weighted average into the overall score.
Provenance
- Plugin root
- .
- Source repo
- https://github.com/AmethystLuna/logicprobe
- Source commit
- dc53ff32db58…
- Publisher verified
- No
- Owner verified
- @AmethystLuna
Continuous scanner CI detected
No action is required. This plugin receives the full trust score.
Verified badge not detected
Add the HOL verified badge to the repository README to score +2% trust. Plugin owners can open that pull request from Guard Plugins.
Security Posture
- Provider
- registry-broker-fallback
- Grade
- C · review
- Version
- Unknown
Findings
termsOfServiceURL should be present for marketplace readiness.
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Logic Probe — Frequently asked questions
- What is Logic Probe?
- Logic Probe is an AI plugin in the HOL registry. Design-document & plan claim verification — checks every verifiable claim against the codebase, escalates behavioral claims to executable-model verification, compares before/after models for regression detection, and mines concurrency risk claims
- How do I install Logic Probe?
- Install Logic Probe in your harness: Codex — codex plugin marketplace add AmethystLuna/logicprobe; Claude Code — /plugin marketplace add AmethystLuna/logicprobe; Cursor — npx skills add AmethystLuna/logicprobe. Full step-by-step guidance is on the HOL plugin page.
- How do I install Logic Probe in Codex?
- To install Logic Probe in Codex, start with codex plugin marketplace add AmethystLuna/logicprobe. The complete step-by-step install guide for Codex is on the HOL plugin page.
- How do I install Logic Probe in Claude Code?
- To install Logic Probe in Claude Code, start with /plugin marketplace add AmethystLuna/logicprobe. The complete step-by-step install guide for Claude Code is on the HOL plugin page.
- How do I install Logic Probe in Cursor?
- To install Logic Probe in Cursor, start with npx skills add AmethystLuna/logicprobe. The complete step-by-step install guide for Cursor is on the HOL plugin page.
- Is Logic Probe free?
- Pricing for Logic Probe is published on its HOL plugin page when the maker schedules a launch.
- Who publishes Logic Probe?
- Logic Probe is published by Amethyst Luna and listed on HOL.
- Is Logic Probe available now?
- Logic Probe availability is listed on its HOL plugin page.
Install Guidance
Install in Claude Code
Install through the Claude Code plugin marketplace.
- 1
Add the marketplace
Run this inside a Claude Code session.
claude code - 2
Install the plugin
Use the plugin name and the marketplace name shown by the previous command.
claude code - 3
Scripted alternative
Non-interactive equivalent for scripts and CI pipelines. Add --scope project to pin the install to one repository.
shell
Plugin Manifest
{
"name": "logicprobe",
"version": "0.9.0",
"description": "Design document & plan claim verification — logic primitives + adversarial probing for behavioral claims. State machines, data models, protocol logic, and refactoring plans get executable-model verification (state machine S1-S8/A1-A11, data model DS/DA/DD) with before/after regression detection.",
"author": {
"name": "Amethyst Luna",
"url": "https://github.com/AmethystLuna"
},
"homepage": "https://github.com/AmethystLuna/logicprobe",
"repository": "https://github.com/AmethystLuna/logicprobe",
"license": "MIT",
"keywords": [
"verification",
"fact-check",
"design-review",
"state-machine",
"logic-verification",
"adversarial",
"refactoring",
"model-checking"
],
"skills": "./",
"interface": {
"displayName": "Logic Probe",
"developerName": "Amethyst Luna",
"shortDescription": "Claim verification for design docs & plans — logic primitives + adversarial probing",
"longDescription": "Documents are not truth — code is. Verifies every verifiable claim in design documents, architecture specs, and refactoring plans against the actual codebase, then escalates to executable-model verification for behavioral claims: 8 structural checks (reachability, deadlock, liveness, determinism, guard/invariant completeness, monotonicity) and 11 adversarial probes (unexpected events, race interleaving, order permutation, pair symmetry, boundary blast, resource injection, minimal counter-example, idempotent replay, leads-to, sequence, atomicity). Data-model verification adds DS/DA/DD checks for schemas, migrations, copy consistency, and data invariants. Before/after model comparison catches regressions. Python harnesses included, with manual fallback for air-gapped machines.",
"category": "Development",
"capabilities": [
"Interactive",
"Read"
],
"websiteURL": "https://github.com/AmethystLuna/logicprobe"
},
"holManifestOrigin": "repository",
"registryIndexVersion": 5
}Marketplace Source
- Repo URL
- https://github.com/AmethystLuna/logicprobe
- Marketplace path
- Unknown
- Source path
- .
- Install policy
- Unspecified
Skills
2 SKILL.md files ship with this plugin. Preview, copy, or download each one, then install them with the Skills CLI.
logicprobe-datamodel
skills/logicprobe-datamodel/SKILL.md
Use when reviewing design documents, architecture specs, technical proposals, schema changes, data contracts, or refactoring plans that make claims about entities, fields, constraints, relationships, data invariants, migration coverage, copy consistency, rollback symmetry, or before/after data-model equivalence. When the document contains schema changes, data migration logic, or data-behavioural assertions ('all records must have X', 'target count equals source count', 'no orphan rows', 'ids never move backwards', 'exactly one row per event', 'rollback restores the old shape', 'migration is non-breaking'), escalate into data-model verification — generate and run executable checks for structural consistency (DS1-DS4), data invariants and adversarial probes (DA1-DA12: null/boundary injection, uniqueness, referential integrity, migration coverage, copy consistency, rollback symmetry, idempotency, monotonicity, ordering, leads-to, atomicity), and before/after data regression (DD1-DD4) before trusting any claim. Behavioural, state-machine, protocol and concurrency claims belong to the sibling logicprobe skill. Also proactively SUGGEST this skill for code-level data/schema behavioural questions.
SKILL.md content is not in this snapshot. Open the raw file to copy it from the source repository.
logicprobe
skills/logicprobe/SKILL.md
Use when reviewing design documents, architecture specs, technical proposals, or refactoring plans that make claims about API names, file locations, enum values, or mechanism feasibility. Escalate into logic-primitive verification — generate and run an executable model before trusting the claim — when the document asserts state-machine or protocol behaviour (≥3 states, ACK/NACK/retry sequences, guards, lock/unlock pairing), a quantitative or temporal guarantee (worst-case path cost ≤ budget, P(reach SAFE) ≥ p, 'must leave within 2 ticks'), a cross-machine handshake (req/ack, power-up sequencing between two components), concurrency guarantees ('thread-safe', 'lock-free', 'ISR-safe' — mined and routed, never proven here), or a refactoring that changes state topology or guard conditions, where the pipeline compares before/after models for behavioral preservation and regression freedom. ALSO use when the task is to model a code flow as UML, or to audit a diagram somebody drew: the skill renders the model as a state, activity or sequence diagram, reads a hand-drawn diagram back into a model, and reviews the modelling — unreachable states, dead ends, ambiguous branches, documentation gaps, diagram-versus-model round-trip fidelity. Data-model, schema and migration claims belong to the sibling logicprobe-datamodel skill. ALSO proactively SUGGEST this skill (do not require) when a user asks code-level behavioral questions — 'check this timing for bugs', 'could this state machine deadlock', 'is this retry limit safe' — since plan-level verification has usually already been done.
SKILL.md content is not in this snapshot. Open the raw file to copy it from the source repository.
File Inventory
.claude-plugin/plugin.json
file
913 bytes
4c385a79fb7ba5e5…
.codex-plugin/plugin.json
plugin-manifest
1,879 bytes
2692dfdbb07d58c9…
.cursor-plugin/plugin.json
file
1,071 bytes
9b7651d7dfe742ff…
.kimi-plugin/plugin.json
file
1,560 bytes
be11d0d007e8a64a…
CLAUDE.md
file
5,710 bytes
8b0bee1e3a4af1f7…
hooks/hooks.json
file
326 bytes
3ffd8364d5f97c52…
hooks/session-start-content.md
file
2,891 bytes
d9ae6cc3581f7b69…
package-lock.json
file
31,685 bytes
8bba483c981f1caf…
package.json
file
5,415 bytes
0aaef24bc30e1695…
README.md
file
16,257 bytes
12dda99445fb594a…
SECURITY.md
file
780 bytes
4baf13a9e39fdfa0…
skills/logicprobe-datamodel/references/data-model-guide.md
skill
2,608 bytes
39218883a941b963…
skills/logicprobe-datamodel/references/data-model-harness.py
skill
33,762 bytes
7450748e952186e0…
skills/logicprobe-datamodel/references/data-model-schema.md
skill
4,732 bytes
99ea87285c8698fb…
skills/logicprobe-datamodel/SKILL.md
skill
6,206 bytes
f25f1b4d39ad9bbd…
skills/logicprobe/references/concurrency-risk-guide.md
skill
2,730 bytes
0585ca74282cee94…
skills/logicprobe/references/dsh-model-schema.md
skill
21,221 bytes
165f5a13d8e94de7…
skills/logicprobe/references/gap-routing-guide.md
skill
3,514 bytes
173405d99a200724…
skills/logicprobe/references/logic-verification-guide.md
skill
29,174 bytes
63ab27814a606129…
skills/logicprobe/references/logicprobe-engine.py
skill
230,567 bytes
b775178c721c1cf0…
skills/logicprobe/references/uml-modeling-guide.md
skill
13,172 bytes
6a3fba3cd581949b…
skills/logicprobe/references/verification-harness.py
skill
38,928 bytes
5e589626a3975985…
skills/logicprobe/SKILL.md
skill
28,769 bytes
bbaaccc237198b78…
tsconfig.json
file
470 bytes
5afe18007f03fec7…