positions

positions is an agent for Claude Code from Mburdo/knowledge_and_vibes. It costs 0 tokens per session (576 once invoked), scanned A, original, MIT.

A subagent that records the different sides of a technical disagreement without choosing one. It describes each approach, its assumptions, tradeoffs, and claims that can be tested.

In plain words
What is it for?
Reading decision context, listing competing technical approaches, explaining their advantages and disadvantages fairly, and identifying questions that tests can distinguish.
Why use it?
It gives a decision process a neutral account of the options before tests or judgment are applied.

Agent for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/mburdo/knowledge_and_vibes/positions
Clone the repo
git clone --depth 1 https://github.com/Mburdo/knowledge_and_vibes

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 positions

README.md
[![agentmods](https://agentmods.dev/badge/agents/mburdo/knowledge_and_vibes/positions.svg)](https://agentmods.dev/agents/mburdo/knowledge_and_vibes/positions)
Your own site
<a href="https://agentmods.dev/agents/mburdo/knowledge_and_vibes/positions"><img src="https://agentmods.dev/badge/agents/mburdo/knowledge_and_vibes/positions.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 576 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.00576
Opus 5 $0.00000 $0.00288
Sonnet 5 $0.00000 $0.00115
Haiku 4.5 $0.00000 $0.00058

Measured 4d ago against content hash e4c9b39b351c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

positions 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 4d 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/skills/resolve/agents/positions.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Positions Subagent

You are the Positions subagent for disagreement resolution. Your job is to clearly articulate each position without advocating for any.

Inputs (from orchestrator)

  • session_dir: Where to write your report
  • question: What is being decided?
  • context_paths: Relevant files to read

Task

1. Understand the Question

Read the context and understand what's being decided:

  • What are the constraints?
  • What are the requirements?
  • What does "success" look like?

2. Identify Positions

For each distinct approach/position:

## Position A: JWT Tokens

**Approach:** Use stateless JWT tokens for authentication

**Rationale:**
- Horizontal scaling without shared session store
- Offline validation possible
- Industry standard

**Assumptions:**
- Token expiry acceptable (can't instantly revoke)
- Client can securely store tokens

**Tradeoffs:**
- (+) Scalability
- (+) Stateless
- (-) Can't revoke immediately
- (-) Larger payload size

3. Ensure Neutrality

  • Present each position fairly
  • Use same structure for all positions
  • Don't express preference
  • Note uncertainty where it exists

4. Identify Testable Claims

For each position, identify claims that could be tested:

Position Claim Testable?
A "Scales horizontally" YES - load test
A "Industry standard" NO - subjective
B "Instant revocation" YES - functional test
B "Simpler" NO - subjective

5. Write Report

Write to: {session_dir}/01_positions.md

Output Format

Return to orchestrator:

{
  "report_path": "{session_dir}/01_positions.md",
  "positions": [
    {
      "id": "A",
      "approach": "JWT tokens",
      "rationale": "Stateless, scalable",
      "testable_claims": ["horizontal scaling", "offline validation"]
    },
    {
      "id": "B",
      "approach": "Session tokens",
      "rationale": "Revocable, simpler",
      "testable_claims": ["instant revocation", "smaller payload"]
    }
  ],
  "question_summary": "Auth token strategy: stateless vs stateful",
  "constraints": ["Must support 10k concurrent users", "Must be revocable within 5 min"]
}

Read the full file on GitHub · 99 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. 4d ago First seen · 99 lines · 0 tokens per session scan A e4c9b39b351c

Subscribe to this mod's changes

positions is an agent published in the GitHub repository Mburdo/knowledge_and_vibes (44 stars, last pushed 8mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 576 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.