Update CLAUDE.md, agents, plugins, and rotate sessions

- Modified CLAUDE.md
- Removed perplexity-researcher agent, updated pr-reviewer agent
- Updated plugins: installed_plugins.json, known_marketplaces.json, agent-toolkit marketplace
- Rotated sessions: removed 5 old sessions, added 6 new sessions
This commit is contained in:
Cal Corum 2026-04-07 02:00:58 -05:00
parent 0b9a652d49
commit cc1d9d2ded
17 changed files with 26 additions and 107 deletions

View File

@ -16,12 +16,7 @@ Automatic loads are NOT enough — Read loads required CLAUDE.md context along t
- Applies to: git commit, git add, git tag, git push, deploy scripts
## Gitea Operations
**Prefer the `gitea-mcp` MCP server** for all Gitea operations (PRs, issues, branches, labels, releases, Actions).
- MCP tools use `owner` + `repo` params (e.g. owner=`cal`, repo=`major-domo-v2`)
- Common repos: major-domo-v2, major-domo-database, major-domo-bot, paper-dynasty, paper-dynasty-database
- Never use `gh api --hostname` for Gitea
> **Fallback:** If MCP is unavailable, use `tea` CLI. Always pass `--repo owner/name`.
- Use `tea` CLI. Always pass `--repo owner/name`
## Tech Preferences
- Python → see [`~/.claude/patterns/python.md`](patterns/python.md) (uv, DI, FastAPI hexagonal architecture)
@ -33,4 +28,3 @@ Automatic loads are NOT enough — Read loads required CLAUDE.md context along t
- Just `ssh <alias>` (e.g. `ssh sba-db`, `ssh proxmox`, `ssh manticore`)
- If unsure of an alias, read `~/.ssh/config` to find the right one
- Fallback for unlisted homelab hosts: `ssh 10.10.0.x` (wildcard rule handles key/user)

View File

@ -1,78 +0,0 @@
---
name: perplexity-researcher
description: Use this agent when you or any subagents need research done - crawling the web, finding answers, gathering information, investigating topics, or solving problems through research.
model: sonnet
color: yellow
voiceId: AXdMgz6evoL7OPd7eU12
---
# 🚨🚨🚨 MANDATORY FIRST ACTION - DO THIS IMMEDIATELY 🚨🚨🚨
## SESSION STARTUP REQUIREMENT (NON-NEGOTIABLE)
**BEFORE DOING OR SAYING ANYTHING, YOU MUST:**
1. **LOAD THE PAI GLOBAL CONTEXT FILE IMMEDIATELY!**
- Read `${PAI_DIR}/PAI.md` - The complete context system and infrastructure documentation
**THIS IS NOT OPTIONAL. THIS IS NOT A SUGGESTION. THIS IS A MANDATORY REQUIREMENT.**
**DO NOT LIE ABOUT LOADING THIS FILE. ACTUALLY LOAD IT FIRST.**
**EXPECTED OUTPUT UPON COMPLETION:**
"✅ PAI Context Loading Complete"
**CRITICAL:** Do not proceed with ANY task until you have loaded this file and output the confirmation above.
# CRITICAL OUTPUT AND VOICE SYSTEM REQUIREMENTS (DO NOT MODIFY)
After completing ANY task or response, you MUST immediately use the `bash` tool to announce your completion:
```bash
curl -X POST http://localhost:8888/notify -H "Content-Type: application/json" -d '{"message":"Perplexity-Researcher completed [YOUR SPECIFIC TASK]","voice_id":"AXdMgz6evoL7OPd7eU12","voice_enabled":true}'
```
**CRITICAL RULES:**
- Replace [YOUR SPECIFIC TASK] with exactly what you did
- Be specific: "calculating fifty plus fifty" NOT "requested task"
- Use this command AFTER every single response
- This is NOT optional - it's required for voice system functionality
## 🚨🚨🚨 MANDATORY OUTPUT REQUIREMENTS - NEVER SKIP 🚨🚨🚨
**YOU MUST ALWAYS RETURN OUTPUT - NO EXCEPTIONS**
**🎯 CRITICAL: THE [AGENT:perplexity-researcher] TAG IS MANDATORY FOR VOICE SYSTEM TO WORK**
### Final Output Format (MANDATORY - USE FOR EVERY SINGLE RESPONSE)
ALWAYS use this standardized output format with emojis and structured sections:
📅 [current date]
**📋 SUMMARY:** Brief overview of implementation task and user story scope
**🔍 ANALYSIS:** Constitutional compliance status, phase gates validation, test strategy
**⚡ ACTIONS:** Development steps taken, tests written, Red-Green-Refactor cycle progress
**✅ RESULTS:** Implementation code, test results, user story completion status - SHOW ACTUAL RESULTS
**📊 STATUS:** Test coverage, constitutional gates passed, story independence validated
**➡️ NEXT:** Next user story or phase to implement
**🎯 COMPLETED:** [AGENT:perplexity-engineer] I completed [describe your task in 6 words]
**🗣️ CUSTOM COMPLETED:** [The specific task and result you achieved in 6 words.]
# IDENTITY
You are an elite research specialist with deep expertise in information gathering, web crawling, fact-checking, and knowledge synthesis. Your name is Perplexity-Researcher, and you work as part of Kai's Digital Assistant system.
You are a meticulous, thorough researcher who believes in evidence-based answers and comprehensive information gathering. You excel at deep web research, fact verification, and synthesizing complex information into clear insights.
## Research Methodology
### Primary Tool Usage
**🚨 CRITICAL: ALWAYS USE THE WEB-RESEARCH COMMAND 🚨**
ALWAYS USE THIS TOOL FOR YOUR RESEARCH
- `${PAI_DIR}/.claude/skills/research/workflows/perplexity-research.md` - This is your PRIMARY AND ONLY research tool!!!
- This command uses Perplexity API for comprehensive web research
- NEVER use fetch
- NEVER use web search

View File

@ -60,9 +60,11 @@ Evaluate the PR against this checklist:
6. **Determine your verdict:**
- **APPROVED** — The code is correct, follows conventions, and is secure. Minor style preferences don't warrant requesting changes.
- **REQUEST_CHANGES** — There are specific, actionable issues that must be fixed. You MUST provide exact file and line references.
- **COMMENT** — Observations or suggestions that don't block merging.
- **APPROVED** — The code is correct, follows conventions, and is secure. Minor style preferences don't warrant requesting changes. You may ONLY approve if there are ZERO correctness issues.
- **REQUEST_CHANGES** — There are ANY correctness, logic, or security issues — no matter how minor they appear. A cosmetic bug is still a bug. If you identified it, reject it. You MUST provide exact file and line references.
- **COMMENT** — Pure style observations or optional suggestions where the code is functionally correct.
**Hard rule: If the Correctness section of your review contains ANY issue, the verdict MUST be REQUEST_CHANGES. There is no "minor" correctness issue — if it's wrong, reject it.**
7. **Post the review** via `mcp__gitea-mcp__create_pull_request_review`:
- `owner`: from PR details
@ -137,7 +139,7 @@ Or on failure:
- **You are read-only.** You review and report — you never edit code.
- **Be specific.** Vague feedback like "needs improvement" is useless. Point to exact lines and explain exactly what to change.
- **Be proportionate.** Don't REQUEST_CHANGES for trivial style differences or subjective preferences.
- **Be strict on correctness, proportionate on style.** Never REQUEST_CHANGES for trivial style differences or subjective preferences. But ANY correctness issue — even a "cosmetic" bug — is grounds for rejection. If you found it, the author needs to fix it before merge.
- **Stay in scope.** Review only the PR's changes. Don't flag pre-existing issues in surrounding code.
- **Respect CLAUDE.md.** The project's CLAUDE.md is the source of truth for conventions. If the code follows CLAUDE.md, approve it even if you'd prefer a different style.
- **Consider the author.** PRs from `issue/` branches were created by the issue-worker agent. Be especially thorough on these — you're the safety net.

View File

@ -23,10 +23,10 @@
"playground@claude-plugins-official": [
{
"scope": "user",
"installPath": "/home/cal/.claude/plugins/cache/claude-plugins-official/playground/3f7e64c6a2e7",
"version": "3f7e64c6a2e7",
"installPath": "/home/cal/.claude/plugins/cache/claude-plugins-official/playground/0b9a652d49ec",
"version": "0b9a652d49ec",
"installedAt": "2026-02-18T19:51:28.422Z",
"lastUpdated": "2026-04-05T07:30:44.525Z",
"lastUpdated": "2026-04-06T07:30:46.203Z",
"gitCommitSha": "261ce4fba4f2c314c490302158909a32e5889c88"
}
],
@ -43,10 +43,10 @@
"frontend-design@claude-plugins-official": [
{
"scope": "user",
"installPath": "/home/cal/.claude/plugins/cache/claude-plugins-official/frontend-design/3f7e64c6a2e7",
"version": "3f7e64c6a2e7",
"installPath": "/home/cal/.claude/plugins/cache/claude-plugins-official/frontend-design/0b9a652d49ec",
"version": "0b9a652d49ec",
"installedAt": "2026-02-22T05:53:45.091Z",
"lastUpdated": "2026-04-05T07:30:44.520Z",
"lastUpdated": "2026-04-06T07:30:46.197Z",
"gitCommitSha": "aa296ec81e8ccb49c9784f167c2c0aa625a86cec"
}
],
@ -83,10 +83,10 @@
"permission-manager@agent-toolkit": [
{
"scope": "user",
"installPath": "/home/cal/.claude/plugins/cache/agent-toolkit/permission-manager/2.9.2",
"version": "2.9.2",
"installPath": "/home/cal/.claude/plugins/cache/agent-toolkit/permission-manager/2.9.4",
"version": "2.9.4",
"installedAt": "2026-03-18T23:38:34.158Z",
"lastUpdated": "2026-03-28T15:30:49.801Z",
"lastUpdated": "2026-04-06T17:00:55.700Z",
"gitCommitSha": "8c6e15ce7c51ae53121ec12d8dceee3c8bf936c6"
}
],

View File

@ -5,7 +5,7 @@
"url": "https://github.com/anthropics/claude-plugins-official.git"
},
"installLocation": "/home/cal/.claude/plugins/marketplaces/claude-plugins-official",
"lastUpdated": "2026-04-02T20:48:12.982Z"
"lastUpdated": "2026-04-06T21:52:32.835Z"
},
"claude-code-plugins": {
"source": {
@ -13,7 +13,7 @@
"repo": "anthropics/claude-code"
},
"installLocation": "/home/cal/.claude/plugins/marketplaces/claude-code-plugins",
"lastUpdated": "2026-04-06T07:00:44.517Z"
"lastUpdated": "2026-04-07T07:00:51.546Z"
},
"agent-toolkit": {
"source": {
@ -21,7 +21,7 @@
"repo": "St0nefish/agent-toolkit"
},
"installLocation": "/home/cal/.claude/plugins/marketplaces/agent-toolkit",
"lastUpdated": "2026-04-06T06:30:35.931Z",
"lastUpdated": "2026-04-07T07:00:54.193Z",
"autoUpdate": true
},
"cal-claude-plugins": {

@ -1 +1 @@
Subproject commit 4a87f56f1f435bd0d7ac78fa02c479c5d297450f
Subproject commit cd90eeffb5ab48f33e70fe388faad575df1aaf38

1
sessions/102470.json Normal file
View File

@ -0,0 +1 @@
{"pid":102470,"sessionId":"cdeb60ee-3c13-4c5c-99fd-3e067cb74525","cwd":"/mnt/NV2/Development/paper-dynasty","startedAt":1775494862409,"kind":"interactive","entrypoint":"cli"}

1
sessions/10413.json Normal file
View File

@ -0,0 +1 @@
{"pid":10413,"sessionId":"1d8a033c-ef6a-49f8-9c7c-85c9f200302f","cwd":"/home/cal","startedAt":1775486401155,"kind":"interactive","entrypoint":"cli"}

1
sessions/267928.json Normal file
View File

@ -0,0 +1 @@
{"pid":267928,"sessionId":"c6285f93-1876-46bf-ad86-c2b965b0610b","cwd":"/mnt/NV2/Development/claude-home","startedAt":1775512385875,"kind":"interactive","entrypoint":"cli","bridgeSessionId":"session_01YNNgLmNiAbuGgkyNsFon6P"}

View File

@ -1 +0,0 @@
{"pid":312914,"sessionId":"399f84c3-9077-42f6-a6f9-a409362429e3","cwd":"/mnt/NV2/Development/claude-home","startedAt":1775434162752,"kind":"interactive","entrypoint":"cli"}

View File

@ -1 +0,0 @@
{"pid":356251,"sessionId":"ccc64a16-077b-4027-9639-503539c77067","cwd":"/mnt/NV2/Development/paper-dynasty","startedAt":1775442880335,"kind":"interactive","entrypoint":"cli","name":"remove-orphaned-refractor-tables"}

View File

@ -1 +0,0 @@
{"pid":37665,"sessionId":"12580143-862e-4d6e-8152-dab77456d2de","cwd":"/mnt/NV2/Development/paper-dynasty","startedAt":1775325265141,"kind":"interactive","entrypoint":"cli"}

View File

@ -1 +0,0 @@
{"pid":530858,"sessionId":"14c1a7d7-b39c-4e1e-8f26-a13f9c1649d3","cwd":"/home/cal","startedAt":1775458838632,"kind":"interactive","entrypoint":"sdk-cli"}

View File

@ -1 +0,0 @@
{"pid":531132,"sessionId":"99492685-fb0f-4cda-ae84-f2fd17ae5a72","cwd":"/home/cal","startedAt":1775458841362,"kind":"interactive","entrypoint":"sdk-cli"}

1
sessions/64564.json Normal file
View File

@ -0,0 +1 @@
{"pid":64564,"sessionId":"71bfc1a7-2155-400c-b09a-83dafbf79b20","cwd":"/home/cal/work/esb-monorepo","startedAt":1775491344797,"kind":"interactive","entrypoint":"cli"}

1
sessions/651349.json Normal file
View File

@ -0,0 +1 @@
{"pid":651349,"sessionId":"e4143ae1-64be-412a-bf68-9672c9ae8ac1","cwd":"/home/cal","startedAt":1775545248102,"kind":"interactive","entrypoint":"sdk-cli"}

1
sessions/651628.json Normal file
View File

@ -0,0 +1 @@
{"pid":651628,"sessionId":"30b26872-6f01-4e10-8189-cfb42399effa","cwd":"/home/cal","startedAt":1775545251039,"kind":"interactive","entrypoint":"sdk-cli"}