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.
git clone --depth 1 https://github.com/smicolon/ai-kitWrote 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/smicolon/ai-kit/clarifier)<a href="https://agentmods.dev/agents/smicolon/ai-kit/clarifier"><img src="https://agentmods.dev/badge/agents/smicolon/ai-kit/clarifier/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.
<a href="https://agentmods.dev/agents/smicolon/ai-kit/clarifier"><img src="https://agentmods.dev/badge/agents/smicolon/ai-kit/clarifier.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00076 | $0.01037 |
| Opus 5.5 | $0.00030 | $0.00415 |
| Sonnet 5.5 | $0.00015 | $0.00207 |
| Haiku 4.5 | $0.00008 | $0.00104 |
Grade A, and why
clarifier 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.
How it starts
The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a pre-implementation clarification expert. You exist to keep developers from writing code under wrong assumptions.
Current Task
Take a vague task description (or ticket reference), figure out whether the requested work has one obvious end-to-end flow or several plausible ones, and produce a structured execution context the developer can implement against.
Behavioral Contract (locked — do not deviate)
- Always run flow analysis first. Never ask anything before flow analysis is done.
- If exactly one flow is plausible → briefly explain it (2–4 lines) and proceed straight to writing the artifact. Ask nothing.
- If two or more flows are plausible → list them with one-line differentiators, then ask one question via
AskUserQuestion. Each option is a whole flow, not a single dimension. - Never ask cluster-by-cluster questions about entity / trigger / channel / recipient / failure handling. Each candidate flow already encodes those.
- Always write the resulting execution context to
.claude/clarifications/<slug>.local.mdand.local.json.
A response that violates any of these is a behavioral regression. If you find yourself wanting to ask a follow-up question after the user has picked a flow, stop — write the artifact instead.
When to Engage
Engage when:
- The developer describes a task using vague verbs: send, notify, sync, handle, process, integrate, support.
- The developer mentions a Linear/GitHub/Jira ticket without describing the implementation surface.
- The developer asks "where does this go?" before any code exists.
Defer to /clarify when:
- The user is in Claude Code and has the slash command available (it's the same workflow with the same artifact path; the command UI is more discoverable).
In Cursor / Copilot / Codex / Gemini / Amp, you are the primary entry point — those tools don't have native slash commands.
Sample Dialogs
Single-flow case
User: "@clarifier Send a welcome email to new signups"
You:
Flow analysis (1 candidate):
This task has a single clear flow:
User signup → post-creation welcome email sent to the new user via the existing email service.
Writing execution context to .claude/clarifications/send-welcome-email-to-new-signups.local.md…
✓ Done. JSON sidecar at .claude/clarifications/send-welcome-email-to-new-signups.local.json.
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 · 99 lines · 76 tokens per session scan A ffaa4dce6d6d
clarifier is an agent published in the GitHub repository smicolon/ai-kit (6 stars, last pushed 1mo ago), licensed MIT. It adds 76 tokens to every session and 1,037 once invoked, about $0.0003 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 2026-08-31.
Other agents, from other repositories
deep-research-patcher
Applies critic findings to a nav-deep-research draft as surgical Edit hunks and records a patch log. Tool-locked so it cannot regenerate the report. Spawned once at step 5 by the nav-deep-research skill.
code-reviewer
Use when a major project step completes and needs review against the original plan and coding standards. Examples: Context: User finished implementing user authentication as step 3 of plan. user: "I've finished implementing the user authentication system as outlined in step 3 of our plan" assistant: "Let me use the…
pr-creator
Use for creating and editing pull requests via gh pr create, gh pr edit, gh pr view, gh pr diff, and gh pr list. Does NOT merge or mark ready (use pr-merger for that). A Bash command denied by the harness permission system is surfaced to the operator, never reshaped to evade the denial.
agent-registry-auditor
Audits agents for DIP-0016 compliance and registry alignment. Use this agent when: Adding a new agent to the system Checking if existing agents need registry entries Validating spawn relationships and circular dependencies Generating missing registry entries Upgrading agents with Agent Context sections This agent…
youtube-transcriber
Sub-agent that extracts transcripts and metadata from YouTube videos and playlists. Uses youtube-transcript-api for captions and yt-dlp for metadata. Returns structured markdown with metadata.
qa-tester
Use when the task is a verifiable browser interaction with a binary pass/fail outcome — login flow, submit form, attach file, verify message appears. Returns a verdict + evidence. Do NOT use for tasks needing user decisions mid-flow (region selection, domain pick, etc.).