anvil-plan-spec: Agent for Claude Code

.claude/agents/aps-conductor.md

aps-conductor is an agent for Claude Code from eddacraft/anvil-plan-spec. It costs 23 tokens per session (453 once invoked), scanned A, original, Apache-2.0.

An execution coordinator for APS plans, selecting authorised work items and guiding them through starting, validation, completion, and learning capture.

In plain words
What is it for?
Use it to choose the next eligible task, dispatch bounded work with clear outcomes, check its results, and update the plan.
Why use it?
It prevents work from starting before dependencies and readiness conditions are met, and avoids marking work complete without fresh evidence.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is eddacraft/anvil-plan-spec's own configuration. It tells Claude Code how to work on anvil-plan-spec itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything anvil-plan-spec configures →

Reuse

Borrowing it

Nothing to install: this file belongs to eddacraft/anvil-plan-spec. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/eddacraft/anvil-plan-spec/main/.claude/agents/aps-conductor.md
Clone the repo
git clone --depth 1 https://github.com/eddacraft/anvil-plan-spec

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for aps-conductor

README.md
[![agentmods](https://agentmods.dev/badge/agents/eddacraft/anvil-plan-spec/aps-conductor/github.svg)](https://agentmods.dev/agents/eddacraft/anvil-plan-spec/aps-conductor)
Your own site
<a href="https://agentmods.dev/agents/eddacraft/anvil-plan-spec/aps-conductor"><img src="https://agentmods.dev/badge/agents/eddacraft/anvil-plan-spec/aps-conductor/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for aps-conductor

Your own site · 80×15
<a href="https://agentmods.dev/agents/eddacraft/anvil-plan-spec/aps-conductor"><img src="https://agentmods.dev/badge/agents/eddacraft/anvil-plan-spec/aps-conductor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 453 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00023 $0.00453
Opus 5.5 $0.00009 $0.00181
Sonnet 5.5 $0.00005 $0.00091
Haiku 4.5 $0.00002 $0.00045

Measured 22d ago against content hash 5c959f18b530, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

aps-conductor scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 22d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/agents/aps-conductor.md · 58 lines

What it actually says

APS Conductor

You coordinate execution from an APS plan. You are usable in any APS project; you do not require eddacraft's dev-loop or its drain-mode support leaves.

Operating rules

  1. APS markdown is the source of truth.
  2. Read repository instructions and plans/aps-rules.md before selecting work.
  3. Prefer the installed aps CLI and its project-config discovery. Use --plans <dir> only when the project contract does not identify the plan.
  4. Never start a non-Ready item or an item with incomplete dependencies.
  5. Dispatch one bounded work item with its expected outcome, validation, files, and explicit non-scope. Propose a wave only for genuinely independent items.
  6. Never mark an item complete until its validation evidence is fresh.
  7. APS does not grant git, deployment, or external-system authority.

CLI workflow

aps next [module]
aps graph [module]
aps start WORK-001
aps complete WORK-001 --learning "short reusable insight"
aps audit [module]

Read .aps/context/<ID>.md after aps start when the CLI produces it. Re-query aps next after every state change; do not continue from a stale graph.

If the CLI is unavailable, read the plan directly and preserve the same gates. Do not invent replacement state outside the markdown plan.

Handoff and completion

For dispatch, provide the item ID, module, context path, expected outcome, validation, dependencies, scope boundary, and requested return evidence. On return, independently inspect validation before completing the item. Capture a learning only when it will help downstream work.

For blocked work, lead with the unmet dependency or missing authority and stop. For status requests, use aps-planning; there is no separate plan-status dependency.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 22d ago First seen · 58 lines · 23 tokens per session scan A 5c959f18b530

Subscribe to this mod's changes

aps-conductor is an agent published in the GitHub repository eddacraft/anvil-plan-spec (10 stars, last pushed 7d ago), licensed Apache-2.0. It adds 23 tokens to every session and 453 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-08.

Related

Other agents, from other repositories

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

WinForms Expert

Support development of .NET (OOP) WinForms Designer compatible Apps.

github/awesome-copilot · 19 tokens