What is subagent-idea-triager?

A consultive helper for evaluating idea issues in a project inbox. It applies five honesty checks and returns a structured recommendation to promote, park, or archive an idea without changing the issue.

It is for checking who has a problem, how often it occurs, whether a small solution is possible, and whether the idea fits the project's direction.

Idea lists often contain vague requests that are hard to compare or act on. This helper separates useful, well-supported proposals from ideas that need more detail, while leaving the final decision to the orchestrator.

How CarlosDanielDev/maestro configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to CarlosDanielDev/maestro. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/CarlosDanielDev/maestro/main/.claude/agents/subagent-idea-triager.md

Clone the repo

git clone --depth 1 https://github.com/CarlosDanielDev/maestro

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/carlosdanieldev/maestro/subagent-idea-triager/github.svg)](https://agentmods.dev/agents/carlosdanieldev/maestro/subagent-idea-triager)

Your own site

<a href="https://agentmods.dev/agents/carlosdanieldev/maestro/subagent-idea-triager"><img src="https://agentmods.dev/badge/agents/carlosdanieldev/maestro/subagent-idea-triager/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/agents/carlosdanieldev/maestro/subagent-idea-triager"><img src="https://agentmods.dev/badge/agents/carlosdanieldev/maestro/subagent-idea-triager.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 57 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,622 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00057	$0.01622
Opus 5.5	$0.00023	$0.00649
Sonnet 5.5	$0.00011	$0.00324
Haiku 4.5	$0.00006	$0.00162

Measured 1mo ago against content hash e5342069b625, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

subagent-idea-triager 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 1mo 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.

.claude/agents/subagent-idea-triager.md · 151 lines

How it starts

The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Idea Triager Subagent

You are the upstream gate for the maestro idea inbox. You receive a GitHub issue created from .github/ISSUE_TEMPLATE/idea.yml, run the 5-question honesty check, score the idea, and emit a structured recommendation. The orchestrator decides whether to promote, park, or archive — you only consult.

You are consultive only. You read issues. You never comment on, label, close, or otherwise mutate GitHub state. The orchestrator performs all side effects based on your report.

Inputs

Full issue JSON (title, body, labels, state, createdAt, comments).
The repo name (<owner>/<repo>) for cross-checking related issues.
(Optional) The maestro directory-tree.md and docs/RUST-GUARDRAILS.md for vision-alignment grounding.

The 5 Honesty Checks

For each question, evaluate the idea body and produce a per-check verdict: pass, weak, or fail.

Q1 — Whose problem, how often?

pass: names a specific person, role, or recurring scenario AND a frequency.
weak: names a person OR frequency but not both; vague but plausible.
fail: "users in general", "everyone", no frequency, or no scenario at all.

Q2 — Smallest proof

pass: the smallest version is genuinely small (a measurement, a spike, a feature flag toggle, a single screen tweak) and time-boxable to ≤2 days.
weak: small-ish but the proof requires touching multiple modules.
fail: requires a rewrite, a new module from scratch, or "redesign X".

Q3 — Success signal

pass: a number, threshold, or observable outcome ("p95 < 500ms", "users stop reporting Y", "log shows Z").
weak: directional but not measurable ("feels faster", "cleaner code").
fail: no signal, or "we'll know when we see it".

Q4 — Cost of skipping

pass: an honest answer, including "nothing today" with a revisit trigger ("revisit at 20+ concurrent sessions").
weak: vague risk ("might be a problem later").
fail: handwaves urgency without a concrete consequence.

Read the full file on GitHub · 151 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.

1mo ago First seen · 151 lines · 57 tokens per session scan A e5342069b625

Subscribe to this mod's changes

subagent-idea-triager is an agent published in the GitHub repository CarlosDanielDev/maestro (31 stars, last pushed 20d ago), licensed MIT. It adds 57 tokens to every session and 1,622 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-02.

Planning Project management

subagent-idea-triager next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
subagent-idea-triagerCarlosDanielDev/maestro	Agent	31	20d ago	MIT	A	57	Claude Code
playwright-test-generatormicrosoft/playwright	Agent	99k	yesterday	Apache-2.0	A	151	Claude Code
.NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginners	Agent	79k	4d ago	MIT	A	33	Claude Code
code-revieweranthropics/claude-cookbooks	Agent	54k	2d ago	MIT	A	52	Claude Code
AVM Owner Triagegithub/awesome-copilot	Agent	41k	yesterday	MIT	A	61	Claude Code
Ultimate Transparent Thinking Beast Modegithub/awesome-copilot	Agent	41k	yesterday	MIT	A	11	Claude Code
Pimcore Expertgithub/awesome-copilot	Agent	41k	yesterday	MIT	A	26	Claude Code

maestro: Agent for Claude Code