clarify

A decision guide for when a coding agent should interrupt you with a question, with a plugin that checks the repository and prior discussion first.

In plain words
What is it for?
It helps batch necessary choices into simple options, include trade-offs, and preserve notes or instructions attached to your answer.
Why use it?
It removes questions whose answers can already be found and refers genuinely open technical choices for additional evaluation before asking you.

Plugin for Claude Code

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.

Claude Code
/plugin marketplace add fledgeling-co/fledgeling-plugins
agentmods
npx agentmods add plugins/fledgeling-co/fledgeling-plugins/clarify
Clone the repo
git clone --depth 1 https://github.com/fledgeling-co/fledgeling-plugins

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

clarify 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 yesterday.

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.

plugins/clarify/.claude-plugin/plugin.json · 10 lines

What it actually says

{
  "name": "clarify",
  "description": "Decide whether to interrupt the user with a question, then ask it so it takes one click to answer. Sweeps the conversation, the repo and earlier agent output for the answer, kills questions whose answer would not change the work, then refers every surviving technical fork to another model family before the user sees it — fable-5, gpt-5.6-sol, gemini-3.7-flash-high and grok-4.6 at xhigh, a three-family panel for genuinely open forks, and Dossier deep research for questions about the world. A fork whose axis is yours is one you settle and report, not one you ask; what reaches the user is taste, cost, scope, risk and anything irreversible, as one batched AskUserQuestion with two options and no recommendation to nudge them. Treats a note attached to an answer as binding. Ships a deterministic linter that enforces the invariant.",
  "version": "1.5.0",
  "author": {
    "name": "Fledgeling",
    "email": "[email protected]"
  }
}
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. yesterday First seen · 10 lines scan A f5345e5eadfc

Subscribe to this mod's changes

clarify is a plugin published in the GitHub repository fledgeling-co/fledgeling-plugins (2 stars, last pushed 2d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.