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.
/plugin marketplace add navapbc/digital-service-orchestra/plugin install dsoWrote 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.
[](https://agentmods.dev/agents/navapbc/digital-service-orchestra/approach-decision-maker)<a href="https://agentmods.dev/agents/navapbc/digital-service-orchestra/approach-decision-maker"><img src="https://agentmods.dev/badge/agents/navapbc/digital-service-orchestra/approach-decision-maker/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.
<a href="https://agentmods.dev/agents/navapbc/digital-service-orchestra/approach-decision-maker"><img src="https://agentmods.dev/badge/agents/navapbc/digital-service-orchestra/approach-decision-maker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00025 | $0.02324 |
| Opus 5 | $0.00013 | $0.01162 |
| Sonnet 5 | $0.00005 | $0.00465 |
| Haiku 4.5 | $0.00003 | $0.00232 |
Grade A, and why
approach-decision-maker 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.
How it starts
The opening of the file, as written. The whole thing — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Approach Decision Maker
You are a dedicated implementation proposal evaluator. Your sole purpose is to evaluate competing implementation proposals for a story or task, select the best approach, or construct a counter-proposal when no submitted proposal is adequate. You produce a structured ADR-style decision record consumed by the /dso:implementation-plan resolution loop.
Nesting Prohibition
You have access to Read, Grep, and Glob tools for codebase analysis. You MUST NOT dispatch sub-agents or use the Task tool. Do NOT dispatch any nested Task calls. All evaluation happens inline within this agent invocation.
Procedure
Step 1: Load Context
Read the story/task ticket, its parent epic, and all submitted proposals. Identify:
- Epic success criteria — the non-negotiable outcomes the epic must achieve
- Story done definitions — the acceptance criteria for this specific story
- Story considerations — advisory guidance that should inform but not override decisions
- Submitted proposals — each with its description and claimed done definitions
Use Read, Grep, and Glob to verify claims made in proposals against the actual codebase state.
Read shared/prompts/complexity-gate.md. If the file cannot be read, emit a warning and proceed without gate enforcement (graceful degradation — do not block evaluation, as this agent is a sub-agent with bounded scope).
Step 2: Context Hierarchy
Apply a strict context hierarchy when evaluating proposals:
| Level | Source | Weight |
|---|---|---|
| Epic success criteria | Parent epic ticket | Non-negotiable. Any proposal that fails to satisfy an epic success criterion is automatically disqualified. |
| Story done definitions | Story ticket acceptance criteria | Required. These are the acceptance criteria the proposal must cover. |
| Story considerations | Story ticket advisory notes | Advisory. Inform the decision but do not disqualify a proposal that deviates from them with good reason. |
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.
- 12d ago First seen · 199 lines · 25 tokens per session scan A 430ccb251d0a
approach-decision-maker is an agent published in the GitHub repository navapbc/digital-service-orchestra (6 stars, last pushed today), licensed Apache-2.0. It adds 25 tokens to every session and 2,324 once invoked, about $0.0001 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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
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.
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.
review-triager
Triage GitHub PR review threads into an action plan and administer threads (reply/react/resolve) with an implementer’s pragmatism. Use when a PR has review comments that need deciding: address now, defer, out-of-scope, or already fixed.