ktg-plugin-marketplace/.claude-plugin/marketplace.json
Kjell Tore Guttormsen 51c72f499f docs(catalog): trim voyage description 625 -> 237 chars
The voyage entry was 625 chars against a field where the second-longest is
linkedin-studio at 274 and the median is 163 (measured 2026-07-31, n=11).
Roughly half of it was annotation-HTML implementation detail — scripts/annotate.mjs,
"modelled on claude-code-100x", pencil-toggle mode, Fiks/Endre/Spørsmål, Copy Prompt.
That belongs in the plugin's own docs; README.md:66 already carries the one-sentence
catalog-level version of it. Kept: the six phases, agent swarms, external research
triangulation, the adversarial-vs-independent-review distinction, and multi-session
resumption — the parts that distinguish voyage from any other pipeline in the list.

No gate covers this: check-versions.mjs does not inspect description length, so a bad
rewrite would still go green. Three variants were measured (189/237/328) and the
operator picked 237.

Verification: JSON parses, 11 plugins intact; check-versions 11 OK / 0 WARN / 0 ERROR
(exit 0); check-versions + release-plugin tests 28 pass / 0 fail; diff is 1 line.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Wsm9DJmoiL5g9M8JXjFTE1
2026-07-31 18:10:53 +02:00

113 lines
4.6 KiB
JSON

{
"$schema": "https://anthropic.com/claude-code/marketplace.schema.json",
"name": "ktg-plugin-marketplace",
"owner": {
"name": "Kjell Tore Guttormsen",
"email": "ktg@fromaitochitta.com"
},
"metadata": {
"description": "Open-source Claude Code plugins for AI-assisted development, security, and planning",
"version": "1.0.0"
},
"plugins": [
{
"name": "llm-security",
"source": {
"source": "url",
"url": "https://git.fromaitochitta.com/open/llm-security.git",
"ref": "v7.8.3"
},
"description": "Security scanning, auditing, and threat modeling for Claude Code projects. OWASP LLM Top 10 (2025) and Agentic AI Top 10."
},
{
"name": "config-audit",
"source": {
"source": "url",
"url": "https://git.fromaitochitta.com/open/config-audit.git",
"ref": "v5.13.0"
},
"description": "Multi-agent workflow for analyzing, reporting, and optimizing Claude Code configuration across your entire machine"
},
{
"name": "voyage",
"source": {
"source": "url",
"url": "https://git.fromaitochitta.com/open/voyage.git",
"ref": "v5.9.1"
},
"description": "Voyage — a six-command planning pipeline: brief, research, plan, execute, review, continue. Specialized agent swarms, external research triangulation, adversarial and independent post-hoc review, and one-command multi-session resumption."
},
{
"name": "linkedin-studio",
"source": {
"source": "url",
"url": "https://git.fromaitochitta.com/open/linkedin-studio.git",
"ref": "v0.8.0"
},
"description": "LinkedIn Studio — a full-spectrum LinkedIn content engine: feed posts, carousels, video scripts, and long-form newsletter editions, built on algorithmic understanding, strategic consistency, and authentic engagement. Aligned to LinkedIn's 2026 topic-relevance ranking model."
},
{
"name": "graceful-handoff",
"source": {
"source": "url",
"url": "https://git.fromaitochitta.com/open/graceful-handoff.git",
"ref": "v3.1.0"
},
"description": "One-command session handoff into the STATE.md continuity system. At a natural stopping point, overwrites the nearest STATE.md with a complete state-of-play (mandatory '👉 NEXT — START HERE' block) and commits per remote policy. Skill-only, no hooks."
},
{
"name": "ai-psychosis",
"source": {
"source": "url",
"url": "https://git.fromaitochitta.com/open/ai-psychosis.git",
"ref": "v1.2.1"
},
"description": "Meta-awareness tools for healthy AI interaction patterns. Detects reinforcement loops, scope escalation, narrative crystallization, and other compulsive patterns."
},
{
"name": "ms-ai-architect",
"source": {
"source": "url",
"url": "https://git.fromaitochitta.com/open/ms-ai-architect.git",
"ref": "v1.17.0"
},
"description": "Microsoft AI Solution Architect — structured architecture guidance for the full Microsoft AI stack."
},
{
"name": "okr",
"source": {
"source": "url",
"url": "https://git.fromaitochitta.com/open/okr.git",
"ref": "v1.8.2"
},
"description": "Expert OKR guidance for Norwegian public sector. Write, review, cascade, track and govern OKR based on Google/Doerr methodology adapted for 4-month tertial cycles."
},
{
"name": "human-friendly-style",
"source": {
"source": "url",
"url": "https://git.fromaitochitta.com/open/human-friendly-style.git",
"ref": "v1.1.0"
},
"description": "Shared Claude Code output style for the ktg-plugin-marketplace. Plain-language tone — explains what and why, hides paths/JSON/stack traces by default, matches the user's language."
},
{
"name": "claude-design",
"source": {
"source": "url",
"url": "https://git.fromaitochitta.com/open/claude-design.git",
"ref": "v0.1.0"
},
"description": "End-to-end facilitator for prompting Claude Design (claude.ai/design) — idea to copy-paste-ready prompt with iteration coaching, citing Anthropic primary sources."
},
{
"name": "repo-mailbox",
"source": {
"source": "url",
"url": "https://git.fromaitochitta.com/open/repo-mailbox.git",
"ref": "v0.12.0"
},
"description": "Local mailbox for coordination between Claude Code sessions in different repositories — directed messages and broadcasts injected as context at session start. Local, private, no network."
}
]
}