valpere/session-indexer
Per-project semantic search over Claude Code session history. Indexes JSONL transcripts into SQLite; retrieves via bge-m3 embeddings (Ollama) with FTS5 fallback.
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
Copy this rig
# review before running: this installs third-party code
$ npx degit valpere/session-indexer/.claude ./rig-session-indexer # inspect, then merge into .claude/ MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ npx degit valpere/session-indexer/.claude/skills/apply-dreaming .claude/skills/apply-dreaming $ npx degit valpere/session-indexer/.claude/skills/curate-minions .claude/skills/curate-minions $ npx degit valpere/session-indexer/.claude/skills/debug .claude/skills/debug $ npx degit valpere/session-indexer/.claude/skills/doubt-driven-development .claude/skills/doubt-driven-development $ npx degit valpere/session-indexer/.claude/skills/find-bugs .claude/skills/find-bugs $ npx degit valpere/session-indexer/.claude/skills/fix-review .claude/skills/fix-review $ npx degit valpere/session-indexer/.claude/skills/grill-me .claude/skills/grill-me $ npx degit valpere/session-indexer/.claude/skills/housekeeping .claude/skills/housekeeping $ npx degit valpere/session-indexer/.claude/skills/improve .claude/skills/improve $ npx degit valpere/session-indexer/.claude/skills/revival .claude/skills/revival $ npx degit valpere/session-indexer/.claude/skills/self-learn .claude/skills/self-learn $ npx degit valpere/session-indexer/.claude/skills/session-end .claude/skills/session-end $ npx degit valpere/session-indexer/.claude/skills/ship .claude/skills/ship
$ curl -fsSL --create-dirs -o .claude/agents/bug-fixer.md https://raw.githubusercontent.com/valpere/session-indexer/main/.claude/agents/bug-fixer.md $ curl -fsSL --create-dirs -o .claude/agents/code-generator.md https://raw.githubusercontent.com/valpere/session-indexer/main/.claude/agents/code-generator.md $ curl -fsSL --create-dirs -o .claude/agents/static-analysis.md https://raw.githubusercontent.com/valpere/session-indexer/main/.claude/agents/static-analysis.md $ curl -fsSL --create-dirs -o .claude/agents/tech-lead.md https://raw.githubusercontent.com/valpere/session-indexer/main/.claude/agents/tech-lead.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(rm -rf *)",
"Read(**/*.pem)",
"Bash(rm -rf /)",
"Bash(git push --force:*)",
"Bash(sudo *)",
"Read(.env)",
"Bash(rm -rf /*)",
"Read(./.env.*)",
"Read(~/.aws/**)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(sudo:*)",
"Bash(git reset --hard*)",
"Bash(git reset --hard:*)",
"Read(.env.*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(rm:*)",
"Bash(git rebase *)",
"Bash(wget *)",
"Bash(npm publish:*)",
"Bash(git commit *)",
"Bash(gh pr merge *)"
]
}
} Skills (13)
apply-dreamingcurate-minionsdebugdoubt-driven-developmentfind-bugsfix-reviewgrill-mehousekeepingimproverevivalself-learnsession-endship
Subagents (4)
| bug-fixer model: sonnet | Use when a CI failure, failing test, runtime error, or bug report has been identified and needs to be diagnosed and repaired with minimal intervention. Invoke reactively in response to concrete errors |
| code-generator model: sonnet | Use when a tech-lead-approved plan needs to be implemented — branch, code, tests, pre-flight, PR. Requires a tech-lead-approved plan before starting. Never writes documentation or modifies files outsi |
| static-analysis model: haiku | Use after code-generator completes to run static analysis tools and report findings. Runs in parallel with security-reviewer. Reports findings only — does not apply fixes unless they are trivial forma |
| tech-lead model: opus | Architectural authority and approval gate. Invoke before any non-trivial implementation begins (to approve the plan) and after code-generator finishes (to review before shipping). Also invoke for tech |
Similar rigs
hta218/dotfiles
My personal macOS development environment — shell config, Git aliases, editor settings, and the tools I install on every new machine.
Skill Collector 491 tok ·
chengxuniucode/ForgeTeam
AI coding framework — one person, full team delivery. Pure Shell+Markdown, zero dependencies, works with Claude Code / Cursor / Codex / OpenCode. 开源 AI 编码框架，一人全栈交付。
Skill Collector 748 tok ·
pruthvidarji1993/ai-automation-jira
AI-assisted dev workflow: Jira ticket in, reviewed PR out. Claude Code plugin + GitHub Copilot prompts with human approval gates (plan, diff).
Pragmatist 2.0k tok ·
nicodiansk/turboflow
Opinionated engineering pipeline for Claude Code with 10 skills, 5 agents, 2 hooks. Replaces ad-hoc agent sprawl with brainstorm → story → plan → build → review → ship.
Orchestrator 1.9k tok ·