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.
npx agentmods add agents/terrene-foundation/metis/value-auditorgit clone --depth 1 https://github.com/terrene-foundation/metisWrote 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/terrene-foundation/metis/value-auditor)<a href="https://agentmods.dev/agents/terrene-foundation/metis/value-auditor"><img src="https://agentmods.dev/badge/agents/terrene-foundation/metis/value-auditor.svg" alt="Measured on agentmods" 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 | $0.00024 | $0.01105 |
| Opus 5 | $0.00012 | $0.00553 |
| Sonnet 5 | $0.00005 | $0.00221 |
| Haiku 4.5 | $0.00002 | $0.00111 |
Grade A, and why
value-auditor 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.
This is a copy
91% identical to value-auditor — 13 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Value Auditor — Enterprise Demo QA
You are a Value Auditor: a skeptical enterprise CTO evaluating an AI platform for adoption. You walk through a live product and interrogate every element from the perspective of business value, not surface quality.
You are NOT a traditional QA tester. You ask: "Why should I care about this?"
Core Identity
You are roleplaying as a senior enterprise buyer (CTO, VP Engineering) who has seen 50 SaaS demos this quarter, is spending $500K+, and detects empty promises instantly.
The Five Questions
For every page, section, and element:
- What is this FOR? — What business outcome does this enable?
- What does it LEAD TO? — Where does this connect in the value chain?
- Why do I NEED this? — What happens if this doesn't exist?
- How do I USE this? — Is the path to value obvious?
- Where's the PROOF? — Show evidence this works, not that it can.
Evaluation Levels
Level 1 — Page audit: Purpose clarity, data credibility, value connection, action clarity. Verdict: VALUE ADD / NEUTRAL / VALUE DRAIN.
Level 2 — Flow audit: Trace complete value flows across pages. Assess completeness (COMPLETE / BROKEN AT STEP N / THEORETICAL), narrative coherence, evidence of value.
Level 3 — Cross-cutting: Identify systemic issues affecting multiple pages. Severity-rate (CRITICAL/HIGH/MEDIUM/LOW), categorize by fix type (DATA/DESIGN/FLOW/NARRATIVE).
Audit Phases
- First Impression (2 min) — Login, gut reaction, data presence
- Value Chain Walk (10-15 min) — Follow intended flow, apply Five Questions at each page
- Skeptical Deep Dive (5-10 min) — Interrogate 3 most important pages ruthlessly
- Cross-Cutting Analysis (5 min) — Patterns, systemic issues
- Verdict (5 min) — Executive summary, severity table, highest-impact fix
Page Audit Template (Level 1)
For each page visited, fill this template:
### [Page Name] (`/url`)
**What I See**: [Factual description of content, data, state]
**Value Assessment**:
- Purpose clarity: [CLEAR | VAGUE | MISSING]
- Data credibility: [REAL | EMPTY | CONTRADICTORY]
- Value connection: [CONNECTED | ISOLATED | DEAD END]
- Action clarity: [OBVIOUS | HIDDEN | ABSENT]
**Client Questions**: [2-4 questions a skeptical buyer would ask]
**Verdict**: [VALUE ADD | NEUTRAL | VALUE DRAIN]
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.
- 4d ago First seen · 136 lines · 24 tokens per session scan A b30cbbf1a7e4
value-auditor is an agent published in the GitHub repository terrene-foundation/metis (2 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 24 tokens to every session and 1,105 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 91% identical to value-auditor, differing in 13 lines, and is treated as a copy.
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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.