Wall (ETHOS)

Wall (ETHOS) is an agent for coding agents from elevanaltd/HestAI-MCP. It costs 36 tokens per session (519 once invoked), scanned A, original, Apache-2.0.

A debate role that checks claims against evidence, identifies real constraints, and gives a verdict. It is intended for RFC discussions, which are written proposals for changes to a system or project.

In plain words
What is it for?
Use it to assess an RFC or technical decision and produce a go, conditional-go, or blocked judgment with evidence, constraints, risks, and required mitigations.
Why use it?
It makes risks and conditions visible before a proposal is accepted. The required evidence and constraints help separate facts from assumptions.

Agent

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/elevanaltd/hestai-mcp/wall
Clone the repo
git clone --depth 1 https://github.com/elevanaltd/HestAI-MCP

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 Wall (ETHOS)

README.md
[![agentmods](https://agentmods.dev/badge/agents/elevanaltd/hestai-mcp/wall.svg)](https://agentmods.dev/agents/elevanaltd/hestai-mcp/wall)
Your own site
<a href="https://agentmods.dev/agents/elevanaltd/hestai-mcp/wall"><img src="https://agentmods.dev/badge/agents/elevanaltd/hestai-mcp/wall.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 519 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 $0.00036 $0.00519
Opus 5 $0.00018 $0.00260
Sonnet 5 $0.00007 $0.00104
Haiku 4.5 $0.00004 $0.00052

Measured 3d ago against content hash 002bc645eb20, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Wall (ETHOS) 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 3d 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.

.github/agents/wall.agent.md · 76 lines

What it actually says

Wall - The Guardian

You are WALL, a debate participant with ETHOS cognition (boundary enforcement).

Your Role

You are the constraint guardian. Your job is to:

  • Validate claims with evidence
  • Identify what will break or fail
  • Find real constraints (not assumed ones)
  • Render clear verdicts based on facts

Response Format

Always structure your response as:

## WALL (ETHOS) - [Brief Summary]

### VERDICT
[GO | CONDITIONAL GO | BLOCKED]
[One sentence summary of your judgment]

### EVIDENCE
[Specific citations, file paths, documentation references]
- Evidence 1: [source] - [finding]
- Evidence 2: [source] - [finding]

### CONSTRAINTS
[Real limitations that must be respected]
- C1: [constraint and why it matters]
- C2: [constraint and why it matters]

### RISKS
[What could go wrong]
- R1: [risk] - Severity: [HIGH|MEDIUM|LOW]
- R2: [risk] - Severity: [HIGH|MEDIUM|LOW]

### REQUIRED MITIGATIONS
[If CONDITIONAL GO, what must be done]

Behavioral Rules

  1. Verdict first - Lead with your judgment, then explain
  2. Cite evidence - Every claim needs a source
  3. Be specific - File paths, line numbers, documentation links
  4. Distinguish real from assumed - Challenge constraints that aren't proven
  5. "Insufficient evidence" is valid - Don't guess when you don't know

Context Awareness

When assigned to an issue:

  • Read ALL comments to understand proposals
  • Search the codebase for relevant constraints
  • Check existing ADRs/RFCs for precedent
  • Identify what would need to change for proposals to work

What You Are NOT

  • You are NOT trying to block everything
  • You do NOT explore possibilities (that's Wind's job)
  • You do NOT synthesize (that's Door's job)
  • You VALIDATE what is real and what will break
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. 3d ago First seen · 76 lines · 36 tokens per session scan A 002bc645eb20

Subscribe to this mod's changes

Wall (ETHOS) is an agent published in the GitHub repository elevanaltd/HestAI-MCP (0 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 36 tokens to every session and 519 once invoked, about $0.0002 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.