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/51ck/frontier-mcp/frontier-consumergit clone --depth 1 https://github.com/51ck/frontier-mcpWrote 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/51ck/frontier-mcp/frontier-consumer)<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>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 | $0.00000 | $0.00616 |
| Opus 5 | $0.00000 | $0.00308 |
| Sonnet 5 | $0.00000 | $0.00123 |
| Haiku 4.5 | $0.00000 | $0.00062 |
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.
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
- 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.
- Name the goal. Tag the capture with
usable,effective,fast, and/ortoken-effective. Done when at least one goal is named. - Scan before filing.
get_boardonfrontier-v1(andget_ticketson near matches) for an open Ticket that already covers this friction. Done when you either have a matching Ticket id or know none exists. - Land the signal.
- Match found → append a comment with your capture (tool, args, expectation, result, goal tags).
- No match →
create_ticketsonfrontier-v1:kind: build, triageneeds-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.
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.
- 3d ago First seen · 48 lines · 0 tokens per session scan A d1f43d9d2646
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.
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.