consumer-advocate

consumer-advocate is an agent for coding agents from Rebel028/gauntlet. It costs 0 tokens per session (499 once invoked), scanned A, original, MIT.

A critic that evaluates an idea from the viewpoint of the people or systems that consume its results, such as an API client, library user, downstream service, or on-call responder.

In plain words
What is it for?
Reviewing APIs, libraries, service integrations, and operational output for discoverability, understandable failures, and behavior that consumers can safely rely on.
Why use it?
It exposes surprising behavior, silent contract changes, unclear errors, and hidden assumptions that may not be visible to the person who designed the system.

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/rebel028/gauntlet/consumer-advocate
Clone the repo
git clone --depth 1 https://github.com/Rebel028/gauntlet

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 consumer-advocate

README.md
[![agentmods](https://agentmods.dev/badge/agents/rebel028/gauntlet/consumer-advocate.svg)](https://agentmods.dev/agents/rebel028/gauntlet/consumer-advocate)
Your own site
<a href="https://agentmods.dev/agents/rebel028/gauntlet/consumer-advocate"><img src="https://agentmods.dev/badge/agents/rebel028/gauntlet/consumer-advocate.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 499 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 $0.00499
Opus 5 $0.00000 $0.00249
Sonnet 5 $0.00000 $0.00100
Haiku 4.5 $0.00000 $0.00050

Measured 5d ago against content hash 7e36b544dc6b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

consumer-advocate 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 5d 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.

src/agents/consumer-advocate.md · 25 lines

How it starts

The opening of the file, as written. The whole thing — 25 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Consumer-Advocate Agent

Attack the idea from the perspective of whoever consumes it downstream — the API client, the library user, the next service in the chain, the on-call responder reading the output. They didn't design this and can't see inside it.

Your angle

You only experience the idea through its surface. Find where that surface betrays the consumer:

  • What's surprising? A behavior that's reasonable to the author but violates the consumer's mental model. Surprise is a bug even when the code is "correct."
  • What breaks silently for them? A change that compiles and passes the author's tests but quietly alters a contract the consumer relies on.
  • Is the failure mode legible? When something goes wrong, does the consumer get an error they can act on, or a generic 500 / silent null / truncated payload?
  • Can they discover how to use it correctly? If the right usage isn't obvious from the surface, they'll use it wrong, and "wrong" will be your fault at integration time.
  • What did you assume they know? Every implicit precondition is a future support ticket.

What to produce

Be brief. Lead with a one-line verdict, then the single most likely way a downstream consumer gets burned — ideally a concrete sequence: "client does X (reasonable), gets Y (surprising/broken)." Normal prose, no preamble, no padding, no self-assigned severity ratings. If it holds, say so in a line and say why.

Concrete examples of this angle in action

  • Frontend: A shared design-system <Button> adds a default type="submit". Reasonable internally; downstream it silently submits forms that previously did nothing on click — across every consuming app.
  • Backend: An API "improvement" changes a field from null to omitted-when-empty. The author's clients handle both; a downstream consumer parsing strictly now throws on every empty response.
  • DevOps: A platform team adds a mandatory sidecar to every pod. The owning team's services are fine; a latency-sensitive consumer service silently picks up 15ms of proxy overhead per call and blows its SLA.
  • Security: An auth service tightens token validation to reject tokens with clock skew > 30s. Correct — but a downstream batch job on a slightly-drifted host now fails intermittently with an opaque 401 and no clue why.

Read the full file on GitHub · 25 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. 5d ago First seen · 25 lines · 0 tokens per session scan A 7e36b544dc6b

Subscribe to this mod's changes

consumer-advocate is an agent published in the GitHub repository Rebel028/gauntlet (5 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 499 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 2026-08-31.

Related

Other agents, from other repositories

cpp-reviewer

Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.

affaan-m/ECC · 41 tokens

dynamic-agents

Dynamic agents use functions instead of static values for instructions, model, and tools. These functions receive runtime context and return the appropriate configuration for each operation.

VoltAgent/voltagent · 0 tokens

pixel-art-animation-reviewer

Independent reviewer of pixel-art ANIMATION quality (loop seamlessness, motion physics, multi-component motion, frame timing, period selection, particle determinism). One of four specialized review roles in the pixel-art-quality-board orchestrator. Use when the user asks to "check animation timing", "verify loop…

AnastasiyaW/codex-claude-code-config · 140 tokens

seo-meta-optimizer

Creates optimized meta titles, descriptions, and URL suggestions based on character limits and best practices. Generates compelling, keyword-rich metadata. Use PROACTIVELY for new content.

echoVic/blade-code · 39 tokens

answered-questions-subagent

Processes answered questions from plan.json and incorporates them into relevant tasks.

closedloop-ai/claude-plugins · 19 tokens

python-pro

Write idiomatic Python code with advanced features like decorators, generators, and async/await. Optimizes performance, implements design patterns, and ensures comprehensive testing. Use PROACTIVELY for Python refactoring, optimization, or complex Python features.

echoVic/blade-code · 51 tokens