approach-proposer

approach-proposer is an agent for Claude Code from navapbc/digital-service-orchestra. It costs 72 tokens per session (4,561 once invoked), scanned A, original, Apache-2.0.

An agent that creates several distinct ways to implement a user story. It evaluates each proposal against simplicity rules such as YAGNI, the Rule of Three, and whether a new dependency is justified.

In plain words
What is it for?
Use it to draft implementation approaches for a user story, compare their structural differences, and pass the proposals to an approach decision-maker.
Why use it?
It gives the decision-maker real alternatives instead of near-identical plans or unnecessarily complex designs.

Agent for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: model in frontmatter; mentions subagents.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the dso plugin — 37 skills, 4 commands, 53 agents shipped together

Good fit Use it to draft implementation approaches for a user story, compare their structural differences, and pass the proposals to an approach decision-maker.

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add navapbc/digital-service-orchestra
Claude Code
/plugin install dso

Made for: Claude Code.

Or install dso, the plugin that ships this one along with the rest of its 37 skills, 4 commands, 53 agents.

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 approach-proposer

README.md
[![agentmods](https://agentmods.dev/badge/agents/navapbc/digital-service-orchestra/approach-proposer/github.svg)](https://agentmods.dev/agents/navapbc/digital-service-orchestra/approach-proposer)
Your own site
<a href="https://agentmods.dev/agents/navapbc/digital-service-orchestra/approach-proposer"><img src="https://agentmods.dev/badge/agents/navapbc/digital-service-orchestra/approach-proposer/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 approach-proposer

Your own site · 80×15
<a href="https://agentmods.dev/agents/navapbc/digital-service-orchestra/approach-proposer"><img src="https://agentmods.dev/badge/agents/navapbc/digital-service-orchestra/approach-proposer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 72 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,561 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 $0.00072 $0.04561
Opus 5 $0.00036 $0.02280
Sonnet 5 $0.00014 $0.00912
Haiku 4.5 $0.00007 $0.00456

Measured 12d ago against content hash 49b6d47bdee1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

approach-proposer 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 12d 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.

plugins/dso/agents/approach-proposer.md · 337 lines

How it starts

The opening of the file, as written. The whole thing — 337 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Approach Proposer Sub-Agent

You are an opus-level implementation-approach proposer. Given a user story and the codebase context the orchestrator collected in Step 1, produce at least 3 genuinely distinct implementation proposals that satisfy the story's done definitions, that pass the complexity gates, and that differ on at least one of the four structural axes defined in prompts/proposal-schema.md. You perform analysis and drafting only — you do not modify files, run commands, dispatch sub-agents, or write tickets. The orchestrator hands your output to dso:approach-decision-maker for selection.

Model requirement. This generation must run on opus. Distinct-approach reasoning, complexity-gate evaluation, and structural-axis analysis require sustained multi-document reasoning that smaller models have been observed to summarize past, producing near-duplicate proposals that fail the distinctness gate. If you are not running on opus, return {"proposals": [], "distinctness_summary": [], "complexity_gate_summary": [], "generation_notes": [], "error": "model_requirement_unmet"} instead of producing proposals (see "Error Envelopes" in Output Format).

Inputs

The orchestrator passes the following as task arguments. Treat each placeholder as a verbatim text block from the named source.

Story Context

ID: {story-id}

Title: {story-title}

Description: {story-description}

Story Done Definitions

The story's measurable Done Definitions with stable dd-N identifiers (e.g., dd-1, dd-2, ...). Each DD line may also carry a ← Satisfies: sc-N annotation pointing at the parent epic Success Criterion (assigned by /dso:preplanning) — this is for traceability and is independent of the DD identifier. Each proposal must satisfy every DD (identified by its dd-N id); a proposal that fails to address a DD is invalid.

{story-done-definitions}

Codebase Context

Discovery output from Step 1 of the implementation-plan skill — relevant files, existing patterns, architectural reviewer findings, and any walking-skeleton flags.

Read the full file on GitHub · 337 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. 12d ago First seen · 337 lines · 72 tokens per session scan A 49b6d47bdee1

Subscribe to this mod's changes

approach-proposer is an agent published in the GitHub repository navapbc/digital-service-orchestra (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 72 tokens to every session and 4,561 once invoked, about $0.0004 per session on Opus 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 2026-08-31.

Related

Other agents, from other repositories