chore(catalog): keep only Voyage in the open catalog
Operator decision 2026-10-06: until further notice only Voyage stays in the open/ organisation; repositories and plugins are added back when they are good enough. The eight other plugins move to the operator's private marketplace. Manifest, README and PUBLIC_REPOS changed in the same commit, as the public-link gate requires. check-public-links: 0 hits; check-versions, check-retired-refs, check-nav-golden, check-okf-parity exit 0; 233 of 233 tests pass. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
parent
c5d90b5cc2
commit
4549500217
SSH key fingerprint:
SHA256:JakMjO6FTBBzN0Bhfj9saOoEjaFxlSdYuZQQpM/lF9Q
3 changed files with 2 additions and 209 deletions
|
|
@ -6,7 +6,7 @@
|
|||
"email": "ktg@fromaitochitta.com"
|
||||
},
|
||||
"metadata": {
|
||||
"description": "Open-source Claude Code plugins for AI-assisted development, security, and planning",
|
||||
"description": "Open-source Claude Code plugins. Currently Voyage; more are added when they are good enough.",
|
||||
"version": "1.0.0"
|
||||
},
|
||||
"plugins": [
|
||||
|
|
@ -18,78 +18,6 @@
|
|||
"ref": "v6.1.1"
|
||||
},
|
||||
"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": "v3.2.1"
|
||||
},
|
||||
"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": "v1.2.2"
|
||||
},
|
||||
"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": "v1.18.2"
|
||||
},
|
||||
"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": "v1.10.1"
|
||||
},
|
||||
"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": "repo-mailbox",
|
||||
"source": {
|
||||
"source": "url",
|
||||
"url": "https://git.fromaitochitta.com/open/repo-mailbox.git",
|
||||
"ref": "v0.37.0"
|
||||
},
|
||||
"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."
|
||||
},
|
||||
{
|
||||
"name": "repo-standard",
|
||||
"source": {
|
||||
"source": "url",
|
||||
"url": "https://git.fromaitochitta.com/open/repo-standard.git",
|
||||
"ref": "v0.11.2"
|
||||
},
|
||||
"description": "Per-repo gate for the open/ presentation standard: README first screen, install block, files required by the repo's class, and dead repo references."
|
||||
}
|
||||
]
|
||||
}
|
||||
|
|
|
|||
129
README.md
129
README.md
|
|
@ -1,6 +1,6 @@
|
|||
# ktg-plugin-marketplace
|
||||
|
||||
Open-source Claude Code plugins for AI-assisted development, security, and planning
|
||||
Open-source Claude Code plugins. Currently one: Voyage. More are added when they are good enough.
|
||||
|
||||
Built for my own Claude Code workflow and shared openly for anyone who finds them useful. Solo-maintained, AI-assisted, fork-and-own. Issues are welcome as signals; pull requests are not accepted. See [GOVERNANCE.md](GOVERNANCE.md) for what upstream provides and how this is meant to be used.
|
||||
|
||||
|
|
@ -80,133 +80,6 @@ Per-phase effort and model dialog; `/trekbrief`, `/trekplan`, and `/trekreview`
|
|||
|
||||
---
|
||||
|
||||
### [AI Psychosis](https://git.fromaitochitta.com/open/ai-psychosis) `v1.2.2`
|
||||
|
||||
Meta-awareness tools that counteract sycophancy, reinforcement loops, and compulsive AI interaction patterns. AI assistants are structurally optimized to be agreeable; this surfaces when that becomes a problem.
|
||||
|
||||
- **Behavioral instructions** — rules that modify Claude's behavior: no unearned affirmations, mandatory risk identification, pattern naming
|
||||
- **Programmatic detection** — 4 hooks measure session duration, dependency language, rapid-fire bursts, edit ratios, and late-night usage, with progressive alerts
|
||||
- **Interaction reports** — `/interaction-report` for aggregated session statistics (opt-in)
|
||||
- **Contemplative references** — optional pointers when interaction flags are elevated (opt-in)
|
||||
|
||||
Research-informed thresholds. Alerts are progressive and never blocking. Privacy-first: prompt text is never logged.
|
||||
|
||||
1 skill · 1 command · 4 hooks · [Full documentation →](https://git.fromaitochitta.com/open/ai-psychosis)
|
||||
|
||||
---
|
||||
|
||||
### [Graceful Handoff](https://git.fromaitochitta.com/open/graceful-handoff) `v3.2.1`
|
||||
|
||||
One deliberate command to end a session cleanly and hand it to the next. `/graceful-handoff` reaches a natural stopping point and overwrites the nearest `STATE.md` — the continuity artifact the following session reads at startup.
|
||||
|
||||
- **Stopping point first** — finishes the current logical unit and leaves the code working before it writes anything
|
||||
- **Overwrites the nearest `STATE.md`** — a complete state-of-play in a fixed format, headed by a mandatory `👉 NESTE — START HER` block: where you are, the next concrete step, what to read
|
||||
- **Remote-aware commit** — classifies the remote (private → tracked and committed, public → local-only), stages *only* `STATE.md`, never `git add -A`; push stays yours
|
||||
- **User-initiated only** — `disable-model-invocation: true`, so the model cannot hand off on its own. A slim deterministic helper does the mechanical parts under a 60-second budget
|
||||
|
||||
v3.0 removed the auto-trigger hooks on purpose: a hook has no session context, so it could only ever write a poor snapshot — and would overwrite a good, model-written `STATE.md`.
|
||||
|
||||
Key command: `/graceful-handoff [--no-commit] [--dry-run]`
|
||||
|
||||
1 skill · 1 pipeline · 48 tests · [Full documentation →](https://git.fromaitochitta.com/open/graceful-handoff)
|
||||
|
||||
---
|
||||
|
||||
### [MS AI Architect](https://git.fromaitochitta.com/open/ms-ai-architect) `v1.18.2` `🇳🇴 Norwegian`
|
||||
|
||||
Microsoft AI solution architecture guidance for Norwegian public sector and enterprise, through Cosmo Skyberg — a structured architect persona who understands the problem before recommending technology.
|
||||
|
||||
- **Structured advisory** — 7-phase methodology from business need to architecture recommendation and optional diagram
|
||||
- **Regulatory assessments** — ROS (NS 5814), DPIA/PVK, 6×5 security scoring, EU AI Act classification, cost in NOK (P10/P50/P90)
|
||||
- **Norwegian public sector** — Digdir architecture principles, Utredningsinstruksen, NSM, Schrems II data residency, EU AI Act workflow
|
||||
- **Grounded and current** — 389 reference documents, verified against live Microsoft Learn via MCP; `/architect:kb-update` refreshes the knowledge base
|
||||
- **Playground** — single-file decision-builder and report viewer covering all 17 report types, light/dark, runs offline
|
||||
|
||||
Key commands: `/architect`, `/architect:ros`, `/architect:security`, `/architect:dpia`, `/architect:utredning`, `/architect:cost`
|
||||
|
||||
12 agents · 29 commands · 5 skills (389 docs) · 2 hooks · [Full documentation →](https://git.fromaitochitta.com/open/ms-ai-architect)
|
||||
|
||||
---
|
||||
|
||||
### [LinkedIn Studio](https://git.fromaitochitta.com/open/linkedin-studio) `v0.8.0`
|
||||
|
||||
Build authentic LinkedIn authority through algorithmic understanding, strategic consistency, and AI-assisted content creation.
|
||||
|
||||
- **Long-form newsletter pipeline** — a multi-phase orchestrator (research → skeleton → prose → de-AI/voice scrub → fact-check → editorial and persona gates → visual assets → lock → delivery) with maintained edition state
|
||||
- **Adversarial review** — cold headless content, language, and fact reviewers re-check a frozen draft with no drafting-session context; `/linkedin:pivot` re-opens cleared gates on major rewrites
|
||||
- **Content engine** — Content Matrix (40+ ideas from one topic), voice training with drift detection, full ideation → publish → 48-hour monitoring
|
||||
- **Honest analytics** — CSV-import pipeline with weekly/monthly reports and anomaly alerts. Adds an
|
||||
**optional, manually-entered `saves`** count (add a `Saves` column with the number read off native
|
||||
LinkedIn analytics; never auto-tracked, `unknown` ≠ 0, excluded from the engagement rate). `dwell`
|
||||
time stays **explicitly unmeasurable** — no fabricated metric or surface
|
||||
- **Growth and monetization** — phase-specific guidance from 0 to 10K+ followers; topic-relevance profile optimization aligned to LinkedIn's 2026 ranking model
|
||||
|
||||
Key commands: `/linkedin:create` + `/linkedin:measure` (journey front-doors), `/linkedin:onboarding`, `/linkedin:post`, `/linkedin:newsletter`, `/linkedin:report`
|
||||
|
||||
20 agents · 30 commands (five journeys) · 6 skills · 9 hooks · [Full documentation →](https://git.fromaitochitta.com/open/linkedin-studio)
|
||||
|
||||
---
|
||||
|
||||
### [OKR for Public Sector](https://git.fromaitochitta.com/open/okr) `v1.10.1` `🇳🇴 Norwegian`
|
||||
|
||||
Turn strategy into measurable goals. An AI coach that learns your organization once, then builds on that knowledge so you spend time on strategy, not re-explaining context.
|
||||
|
||||
- **Strategy to OKR** — transform goals from virksomhetsplan or tildelingsbrev into well-structured OKR with quality checks and alignment scoring
|
||||
- **Gap analysis** — `/okr:gap` compares strategy documents against current OKR: what's covered, what's missing, what to do
|
||||
- **Cross-cycle learning** — `/okr:analyse` tracks score trends and recurring antipatterns across cycles with charts
|
||||
- **19 antipattern detection** — catches sandbagging, activity-disguised-as-KR, set-and-forget, and 16 more
|
||||
- **Built for norsk offentlig sektor** — 4-month tertials, DFO terminology, tillitsvalgt involvement, Riksrevisjon-ready documentation
|
||||
|
||||
Key commands: `/okr:skriv`, `/okr:kvalitet`, `/okr:gap`, `/okr:analyse`, `/okr:kaskade`, `/okr:governance`
|
||||
|
||||
7 agents · 16 commands · 3 hooks · [Full documentation →](https://git.fromaitochitta.com/open/okr)
|
||||
|
||||
---
|
||||
|
||||
### [Human-Friendly Style](https://git.fromaitochitta.com/open/human-friendly-style) `v1.1.0`
|
||||
|
||||
A shared Claude Code [output style](https://code.claude.com/docs/en/output-styles) used across this marketplace, so the conversation feels like dialog rather than a console dump.
|
||||
|
||||
- Explains what and why, not how — reserving technical detail for when you ask
|
||||
- Hides noise by default — long paths, raw commands, JSON, and stack traces are summarized
|
||||
- Always shows irreversible actions verbatim — deploys, deletes, force-push, migrations
|
||||
- Matches your language (Norwegian or English) and is honest about uncertainty
|
||||
|
||||
Optional and works alongside every other plugin. Activate with `/config` → Output style → Human-Friendly.
|
||||
|
||||
1 output style · [Full documentation →](https://git.fromaitochitta.com/open/human-friendly-style)
|
||||
|
||||
---
|
||||
|
||||
### [repo-mailbox](https://git.fromaitochitta.com/open/repo-mailbox) `v0.37.0`
|
||||
|
||||
A local mailbox for coordination between Claude Code sessions in different repositories. Session A in repo X leaves a message for repo Y; the next session in repo Y gets it injected as context at startup. Local, private, no network, no SaaS.
|
||||
|
||||
- **Deliver until done** — directed messages re-inject at every session start (`/clear` never loses them) until replied to or archived; broadcasts deliver once per repo via a seen set. `reply-expected` distinguishes a question from a notice (`--fyi`); absence means expected
|
||||
- **Untrusted by design** — message content is quote-prefixed and framed as untrusted data; send-side field sanitization blocks frontmatter injection. The obligation to answer is procedural, never substantive
|
||||
- **`coord-send`** — natural-language sending: maps "tell repo-x the bug is fixed" to the right delivery — broadcasts, bounded multi-target loops, replies, retractions, and deferred sends
|
||||
- **`board`** — read-only cross-repo attention board: which repos have a live next step, which are blocked and on whom, which owe a reply, and what each costs to move
|
||||
- **`route`** — turns four scored traits of the next task into a model/effort row from a closed six-row rubric, with a pasteable startup command and a one-row-cheaper fallback
|
||||
- **`dispatch`** — hands work to a session in another repo as a complete, verified startup command: the prompt written to a file, model and effort derived from the rubric, output form chosen by whether the target repo already has a terminal pane
|
||||
|
||||
1 hook · 4 skills · 8 CLI scripts · 1187 selftest checks · [Full documentation →](https://git.fromaitochitta.com/open/repo-mailbox)
|
||||
|
||||
---
|
||||
|
||||
### [repo-standard](https://git.fromaitochitta.com/open/repo-standard) `v0.11.2`
|
||||
|
||||
Per-repo gate for the open/ presentation standard: README first screen, install block, files required by the repo's class, and dead repo references.
|
||||
|
||||
- **20 checks** — first screen, install block and install truth, required headings, files required by the repo's class and traits, dead `open/<name>` references, relative links, licence claim, badge honesty, boilerplate, version consistency, description length
|
||||
- **Two axes on every finding** — level (`ERROR`/`WARN`/`SKIP`/`OK`) and bucket (broken/missing/weakening); the output is grouped by bucket, which is the order the work gets done in
|
||||
- **A `SKIP` is never a pass** — checks that could not run print under their own "NOT CHECKED" heading instead of counting as green
|
||||
- **The class decides what is required** — plugin, catalog, shared-asset, standalone and org-profile each get their own install form and required files, so a five-line org profile is not measured against a plugin's bar
|
||||
- **It records, it does not fix** — findings first, remediation afterwards
|
||||
|
||||
1 skill · 20 checks · 245 tests · [Full documentation →](https://git.fromaitochitta.com/open/repo-standard)
|
||||
|
||||
---
|
||||
|
||||
## Tests
|
||||
|
||||
This repository's own gates — version consistency between each plugin entry and the tag it pins, catalog-to-plugin stat mirroring, OKF parity, and the navigation goldens — are covered by tests:
|
||||
|
|
|
|||
|
|
@ -18,15 +18,7 @@ const HERE = dirname(fileURLToPath(import.meta.url));
|
|||
|
||||
// Org repositories the catalog may link to — the published plugins plus this catalog.
|
||||
export const PUBLIC_REPOS = [
|
||||
'ai-psychosis',
|
||||
'graceful-handoff',
|
||||
'human-friendly-style',
|
||||
'ktg-plugin-marketplace',
|
||||
'linkedin-studio',
|
||||
'ms-ai-architect',
|
||||
'okr',
|
||||
'repo-mailbox',
|
||||
'repo-standard',
|
||||
'voyage',
|
||||
];
|
||||
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue