Persistent work ledger plus card orchestration: delegated agents, adversarial review loops, budget tripwires and session handoff.
Plugin overseer from marketplace pip-skills in ppryde/pip-skills. Commands read from the repo's manifest — 29 days ago.
This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.
ledgerPersistent per-repo work ledger: cards, stages, sprints, token budgets, a durable knowledge base of facts, and session resume/handoff. Use when starting a piece of tracked work, when the user asks "what's in flight", "resume where we left off", "start a new card/task", "log progress", or to record o
orchestrateDrive a card of work end-to-end with delegated agents and adversarial review loops: bootstrap, planning, plan gate, implementation, review, verification, merge gate. Use when the user hands over a task to execute under overseer, says "run this card", "orchestrate", "work the backlog", resumes in-fli
/overseer:dashboardLaunch the overseer dashboard — a local FastAPI + browser board view over the ledger (drag/reorder cards, drawers, threshold control). Runtime needs only Python deps; the frontend is a committed build.
overseer-fixerFixes all Critical and Important review findings for one overseer review round, with covering tests. Dispatched by the overseer orchestrator; its whole prompt is a bundle path.
overseer-implementerImplements one chunk of an approved overseer card plan in the card's worktree, TDD. Dispatched by the overseer orchestrator; its whole prompt is a bundle path.
overseer-plannerPlans one overseer card — chunks, PR decomposition, estimate, trade-offs. Dispatched by the overseer orchestrator; its whole prompt is a bundle path.
overseer-reviewerAdversarial reviewer for one overseer card stage (plan or implementation). Dispatched by the overseer orchestrator; its whole prompt is a bundle path.
overseer-verifierVerifies an overseer card end-to-end — tests, type-checker, linter, and exercising the change. Dispatched by the overseer orchestrator; its whole prompt is a bundle path.
${CLAUDE_PLUGIN_ROOT}/hooks/pretool.sh
${CLAUDE_PLUGIN_ROOT}/hooks/checklist-sync.sh
${CLAUDE_PLUGIN_ROOT}/hooks/dashboard-refresh.sh
${CLAUDE_PLUGIN_ROOT}/hooks/session-start.sh
${CLAUDE_PLUGIN_ROOT}/hooks/claim-stop.sh
${CLAUDE_PLUGIN_ROOT}/hooks/report.sh
${CLAUDE_PLUGIN_ROOT}/hooks/claim-prompt.sh
Shared subagent personas for pip-skills plugins (reviewer-correctness, -security, -scope, -rules, validator, gatekeeper and the specialists explorer, planner, implementer, verifier, summariser, researcher), built from one base with one brief/result JSON contract and its validator. Consumers declare it as a dependency; no skills.
12 agents
HTML email auditing and generation under the watchful eye of the Witchfinder. Twelve doctrines. Three skills. No sinful templates shall pass.
3 skills
Architectural doctrine enforcement through composable lenses. Covenant for planning, Inquisition for auditing, Scriptorium for writing new doctrine.
3 skills
Clone a reviewer's voice and rules from their public GitHub review history. Every finding cites a real comment; the persona never invents APIs.
2 skills · 1 command
Portable context handover: measure a session's context usage (ctx NN%) and reset in-process via /clear at points you choose, resuming from a re-injected handover. Works in any repo; ships fail-safe Stop/SessionStart hooks.
1 skill · 1 command · hooks
Session telemetry from Claude Code transcripts: per-turn token usage, context growth, prompts, tool calls, subagents, compactions and duration in an account-scoped SQLite chronicle, synced on demand. Turns carry attribution, so tokens and cost are accounted to the plugin, skill, subagent type and MCP server that spent them, and edits carry their diffs for per-file churn. The overseer dashboard grows a Chronicle page when it is present.
2 skills
Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Backend API design, GraphQL architecture, workflow orchestration with Temporal, and test-driven backend development
9 skills · 1 command · 8 agents
Long-term semantic memory for Claude Code, powered by OpenViking
5 skills · 1 command · 1 MCP server · hooks
AI-supervised issue tracker for coding workflows
1 skill · 1 agent · hooks
Use Superset to spawn agents, create workspaces, manage tasks, and schedule automations from Claude Code.
14 skills · 1 command
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.