---
title: "anvil"
description: "Local-first, runtime-neutral project state for humans and AI coding agents, turn PRDs into lockable, evidence-backed work packets. Hermes portable-plugin manifest (Agent Plugins v1)."
canonical: https://agentpluginsdirectory.com/plugins/anvil--fakoli
last-updated: 2026-10-21
---

# anvil
Local-first, runtime-neutral project state for humans and AI coding agents, turn PRDs into lockable, evidence-backed work packets. Hermes portable-plugin manifest (Agent Plugins v1).
- Slug: anvil--fakoli
- Publisher: Fakoli
- Repository: https://github.com/fakoli/anvil
- Manifest: plugin.json
- Version: 0.6.16
- License: MIT
- Category (editorial): productivity
- Skills: 8 (claim, execute, finish, plan, prd, resolve-decisions, start-prd, state-ops)
- MCP servers: 0
- Stars: 8
- Repository created: 2026-06-18
- Repository last pushed: 2026-10-17
- Publisher type: User
- Listing: https://agentpluginsdirectory.com/plugins/anvil--fakoli
- Schema: https://agent-plugins.org/schemas/1.0.0/plugin.schema.json

## What anvil does, in the publisher's words

The system of record for agent teams, durable, evidence-gated, lease-coordinated state for multi-agent software work.

Anvil is a local-first state layer that lets multiple AI coding agents, and the humans working alongside them, execute the same plan without overwriting each other. It records requirements, tasks, claims, and evidence in SQLite, and exposes them through a CLI (anvil) and an MCP server that any harness (Claude Code, Codex, Cursor, Copilot, …) can drive.

Two ideas separate it from an issue tracker:

- Claims are enforced, not conventional. A claim is a database row with a lease and heartbeat: single-winner coordination that holds across sessions, parallel loops, and machines, not "assign a label and hope."
- Status is downstream of proof. Completion is evidence-gated: agents submit typed proofs, reviews gate acceptance, and every accepted task mints a signed, replayable AcceptanceProof you can verify off-host.

From the project README, punctuation lightly normalized. Full text: https://raw.githubusercontent.com/fakoli/anvil/HEAD/README.md

## Skills

- claim: Acquire an exclusive lease on an anvil task, pick from the ready queue, check for file conflicts, claim the task, and get a working git branch to commit into. Use this skill when ready to start work on an approved task.
- execute: Run the agentic execution loop on a claimed anvil task, fetch the work packet, do the work, submit completion evidence. Use this skill when an agent has just claimed a task and needs to execute it end-to-end without juggling individual CLI commands.
- finish: Decide what to do with an anvil task that has submitted evidence and is awaiting human review, accept and ship, reject and reopen, or hold for further investigation. Use this skill when one or more tasks are in needs_review and need a final disposition.
- plan: Turn a reviewed PRD into a ready-to-execute task graph, generate features and tasks, score each on six dimensions, surface dependencies and conflict groups, promote drafted tasks to ready. Use this skill once the PRD is approved and before any agent claims work.
- prd: Author, parse, and review a project PRD in anvil, capture the requirements that everything downstream (features, tasks, claims, evidence) gets generated from. Use this skill when starting a new project or revising requirements before any planning work happens.
- resolve-decisions: Walk the PRD's unresolved items, `[NEEDS DECISION]` markers, `## Open Questions`, and missing acceptance-criteria or verification fields, and drive each one as a Q&A turn with the user, proposing concrete options when possible and applying the chosen answer with `anvil prd resolve-decision`. Use…
- start-prd: Bootstrap a `.anvil/prd.md` draft from a rough project idea, interview the user question-by-question and write the result so `anvil prd parse` can consume it. Use this skill when the user has a project intent but does not yet have a PRD (e.g., asks to "start a PRD", "draft requirements", "author a…
- state-ops: Inspect anvil project state: list tasks, show task details, find the next claimable task, summarize active claims and blockers, check file-conflict warnings, and reconcile state with the filesystem and git. Use this skill when you want to see what anvil knows without changing anything.

Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.