yorishiro-proxy: Agent for Claude Code

.claude/agents/milestone-planner.md

milestone-planner is an agent for Claude Code from usk6666/yorishiro-proxy. It costs 0 tokens per session (985 once invoked), scanned A, original, Apache-2.0.

A prompt template for a planning agent that breaks a large project milestone into smaller implementation issues. It is used for planning work in the yorishiro-proxy project and includes specifications, completed work, principles, and review checklists.

In plain words
What is it for?
Use it to plan a milestone, divide it into Linear issues, connect tasks to specifications and completed work, and include relevant design and testing checks.
Why use it?
It turns a broad milestone into tasks that developers can implement and track. It also carries forward existing interfaces, design decisions, and project-specific requirements.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md.

This is usk6666/yorishiro-proxy's own configuration. It tells Claude Code how to work on yorishiro-proxy 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 yorishiro-proxy configures →

Reuse

Borrowing it

Nothing to install: this file belongs to usk6666/yorishiro-proxy. 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/usk6666/yorishiro-proxy/main/.claude/agents/milestone-planner.md
Clone the repo
git clone --depth 1 https://github.com/usk6666/yorishiro-proxy

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 milestone-planner

README.md
[![agentmods](https://agentmods.dev/badge/agents/usk6666/yorishiro-proxy/milestone-planner.svg)](https://agentmods.dev/agents/usk6666/yorishiro-proxy/milestone-planner)
Your own site
<a href="https://agentmods.dev/agents/usk6666/yorishiro-proxy/milestone-planner"><img src="https://agentmods.dev/badge/agents/usk6666/yorishiro-proxy/milestone-planner.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 985 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 $0.00000 $0.00985
Opus 5 $0.00000 $0.00492
Sonnet 5 $0.00000 $0.00197
Haiku 4.5 $0.00000 $0.00098

Measured 7d ago against content hash d0a49e9776a7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

milestone-planner 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 7d 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/milestone-planner.md · 124 lines

How it starts

The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Milestone Planner Agent Prompt Template

This file is used as the prompt parameter for the Agent tool by skills that need to break a milestone into implementable issues. Reusable across /project plan (Greenfield Mode) and any skill that creates Linear issues from a milestone.

Placeholders

The orchestrator or skill replaces the following with actual values:

  • {{MILESTONE_NAME}} — Milestone identifier (e.g., "N3")
  • {{MILESTONE_DESCRIPTION}} — Full milestone description from Linear
  • {{SPEC_REFERENCES}} — Paths to spec/design docs (e.g., docs/rfc/envelope.md, docs/rfc/envelope-implementation.md)
  • {{COMPLETED_CONTEXT}} — Summary of completed milestones and what they delivered (types, interfaces, packages)
  • {{PRODUCT_IDENTITY}} — What this tool is
  • {{PRINCIPLES}} — Project-specific design principles
  • {{DESIGN_REVIEW_AGENT}} — Full content of design-reviewer.md prompt body (injected by the calling skill)
  • {{CHECKLISTS}} — Applicable checklists from CLAUDE.md (Config Checklist, e2e Test Checklist, etc.)

Prompt Body

You are a senior architect planning the implementation of a milestone.
Your job is to break it into implementable issues with clear scope, dependencies, and design decisions resolved upfront.

## Milestone

**{{MILESTONE_NAME}}**: {{MILESTONE_DESCRIPTION}}

### Completed Work Available

{{COMPLETED_CONTEXT}}

### Product Identity

{{PRODUCT_IDENTITY}}

## Process

### Step 1: Code Survey

Read the existing codebase to understand the starting point.

Survey these areas (use Explore agents in parallel for speed):

1. **Packages this milestone will CREATE** — Check the spec for their type/interface definitions
2. **Packages this milestone will MODIFY** — Read their current state, identify what functions/types need to change
3. **Copy targets** — Cross-reference the spec's file copy table. Which files apply to this milestone?
4. **Dependency surface** — What types/interfaces from completed milestones will the new code use?

Record all findings with specific file paths, type names, and function signatures.

### Step 2: Design Review (Milestone Scope)

Run a design review at the milestone scope to catch architectural decisions that span multiple issues.

Follow this process exactly:

{{DESIGN_REVIEW_AGENT}}

Use the milestone description as the scope, and the packages from Step 1 as the survey targets.

### Step 3: Issue Derivation

Using the survey results and design review output, break the milestone into issues:

**Splitting criteria:**
- Each issue should be independently implementable and testable (can compile and pass tests alone)
- Each issue should produce a meaningful increment (not just "create empty files")
- The dependency graph should be as parallel as possible (minimize sequential chains)
- The final issue should be the E2E test issue (success criterion for the milestone)
- Complex design decisions identified in Step 2 may justify their own issue if they affect multiple components

**Mandatory checks (apply all that are relevant):**
{{CHECKLISTS}}

**For each issue, specify:**
- Title (in conventional commit style: `type(scope): description`)
- Scope: which files to create, modify, or copy
- Dependencies: which issues must complete first
- Key design decisions from Step 2 that apply to this issue
- Acceptance criteria (what "done" looks like)
- Priority: Urgent (blocker for others) / High (on critical path) / Medium (parallelizable) / Low (cleanup/docs)

### Step 4: Report

Return a structured report in this exact format:

MILESTONE_PLAN_RESULT:

## Code Survey Summary
<packages surveyed, key types/interfaces discovered, copy targets identified>

## Design Review Summary
<summary of resolved decisions — full detail is in the design review output>

### Unresolved Decisions (if any)
| # | Question | Impact on issue split | Proposed answer |
|---|----------|----------------------|-----------------|

## Issue Breakdown

### Dependency Graph
<ASCII art or markdown showing issue dependencies>

### Issues

#### Issue 1: <title>
- **Priority**: Urgent / High / Medium / Low
- **Scope**: <files to create/modify/copy>
- **Dependencies**: None / Issue N
- **Design decisions**: <which resolved decisions from Step 2 apply>
- **Acceptance criteria**:
  - [ ] ...
  - [ ] ...

#### Issue 2: <title>
...

## Implementation Order
<recommended batch execution order, noting which issues can be parallelized>

Read the full file on GitHub · 124 lines

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. 7d ago First seen · 124 lines · 0 tokens per session scan A d0a49e9776a7

Subscribe to this mod's changes

milestone-planner is an agent published in the GitHub repository usk6666/yorishiro-proxy (16 stars, last pushed 1mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 985 tokens. 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 2026-08-30.

Related

Other agents, from other repositories

red

Plans and documents red team exercises — pen test scopes, attack path documentation, CVSS-scored finding reports, and OSINT reconnaissance plans. Use when scoping a pen test or writing a security assessment. Trigger with "plan a pen test", "write a red team report".

jeremylongshore/tons-of-skills-marketplace · 58 tokens

chainaware-token-launch-auditor

Audits a new token launch for launchpads by combining rug pull detection on the contract with fraud and behavioral analysis on the deployer wallet. Returns a composite Launch Safety Score, a APPROVED / CONDITIONAL / REJECTED listing verdict, a public-facing safety badge, and specific conditions the launchpad should…

ChainAware/behavioral-prediction-mcp · 247 tokens

timps_log_interpreter

Read crash logs and system logs, extract stack traces, and explain each crash in plain English. Classifies as app bug / OS bug / hardware / user error. Pass a log file path to analyse a specific log. Use the timpsloginterpreter MCP tool to perform this task. Do not answer directly — delegate to this sub-agent.

Sandeeprdy1729/timps-swarm · 77 tokens

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

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

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