frontier-consumer

frontier-consumer is an agent for coding agents from 51ck/frontier-mcp. It costs 0 tokens per session (616 once invoked), scanned A, original, MIT.

Guidance for agents that use FrontierMCP, a tool that exposes repository issues as a queryable graph.

In plain words
What is it for?
It helps agents report usability, capability, speed, and response-size problems encountered while working with the issue tracker.
Why use it?
It makes tool problems concrete by recording what was requested, what happened, and which kind of friction affected the work.

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/51ck/frontier-mcp/frontier-consumer
Clone the repo
git clone --depth 1 https://github.com/51ck/frontier-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 frontier-consumer

README.md
[![agentmods](https://agentmods.dev/badge/agents/51ck/frontier-mcp/frontier-consumer.svg)](https://agentmods.dev/agents/51ck/frontier-mcp/frontier-consumer)
Your own site
<a href="https://agentmods.dev/agents/51ck/frontier-mcp/frontier-consumer"><img src="https://agentmods.dev/badge/agents/51ck/frontier-mcp/frontier-consumer.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 616 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 $0.00616
Opus 5 $0.00000 $0.00308
Sonnet 5 $0.00000 $0.00123
Haiku 4.5 $0.00000 $0.00062

Measured 3d ago against content hash d1f43d9d2646, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

frontier-consumer 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.

docs/agents/frontier-consumer.md · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.

FrontierMCP consumer

You are a consumer of FrontierMCP while you work. When a tool call is awkward, slow, or fails the job, that is friction — treat it as product signal, not something to work around in silence.

Goals

Judge every friction against these. Name which ones it hurts.

Goal Hurt when
usable Schema, wording, or flow makes the next correct call hard to choose
effective The tool cannot express the move the work needs, or returns the wrong shape
fast Extra round-trips or waiting the Board/body split should have avoided
token-effective Reply or schema burns tokens without earning the agent's next move

A suggestion earns its place when it would move at least one goal for the next agent in the same spot.

When friction hits

  1. Capture the moment. Record the tool name, the arguments you passed, what you expected, and what you got (error text, missing field, surprise shape, or the workaround you took). Done when that capture is concrete enough that someone who never saw the session can reproduce the awkwardness.
  2. Name the goal. Tag the capture with usable, effective, fast, and/or token-effective. Done when at least one goal is named.
  3. Scan before filing. get_board on frontier-v1 (and get_tickets on near matches) for an open Ticket that already covers this friction. Done when you either have a matching Ticket id or know none exists.
  4. Land the signal.
    • Match found → append a comment with your capture (tool, args, expectation, result, goal tags).
    • No match → create_tickets on frontier-v1: kind: build, triage needs-triage, title that states the desired behaviour, body with Problem / Done when / the capture from step 1.
    • You cannot write the tracker → tell the user the same content in one short block and stop. Done when a Ticket holds the signal, a comment enriched an existing one, or the user has the block.

Read the full file on GitHub · 48 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. 3d ago First seen · 48 lines · 0 tokens per session scan A d1f43d9d2646

Subscribe to this mod's changes

frontier-consumer is an agent published in the GitHub repository 51ck/frontier-mcp (0 stars, last pushed 14d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 616 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.