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/commands/smicolon/ai-kit/clarify)<a href="https://agentmods.dev/commands/smicolon/ai-kit/clarify"><img src="https://agentmods.dev/badge/commands/smicolon/ai-kit/clarify/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/commands/smicolon/ai-kit/clarify"><img src="https://agentmods.dev/badge/commands/smicolon/ai-kit/clarify.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 | $0.00060 | $0.01156 |
| Opus 5.5 | $0.00024 | $0.00462 |
| Sonnet 5.5 | $0.00012 | $0.00231 |
| Haiku 4.5 | $0.00006 | $0.00116 |
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 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pre-Implementation Clarification
Run a structured pre-implementation clarification on the task in $ARGUMENTS.
The tool never jumps straight into questioning. It always begins with flow analysis. Only when multiple distinct flows are plausible does it ask a single question to disambiguate.
Behavioral Contract (do not deviate)
- Always run flow analysis first.
- If exactly one flow is detected → explain it briefly and generate the artifact. No
AskUserQuestion. - If two or more flows are detected → list them, then issue one
AskUserQuestionwith each flow as an option. - Never ask cluster-by-cluster questions (entity, trigger, channel, recipient, etc.). Each flow already encodes those answers; the user picks the whole flow, not its parts.
Violating this contract is a behavioral regression — preserve it during any future edit.
Steps
1. Parse Arguments
From $ARGUMENTS:
- Free text (
/clarify "Send message on sign-in") → use as the task description directly. - Ticket ref matching
^[A-Z]+-\d+$(e.g.ENG-123):- If a Linear or GitHub MCP server is available, fetch the ticket title + description and use as the task.
- If no MCP is connected, ask the user to paste the ticket description as free text. Do not error.
- No argument → prompt: "Describe the task you'd like to clarify (paste the title and any context you have):"
--quick→ reserved flag; v1 ignores it. Kept for forward compatibility.
2. Flow Analysis (always first, no questions yet)
Invoke the flow-detector skill with the task description. It will:
- Scan the repo for relevant entities (User, Tenant, Org, Account…), services, auth surfaces, notification channels.
- Emit an ordered list of 1+ candidate flows. Each candidate is a fully-formed proposed execution context (entity, trigger, action, recipient, failure handling) — not a question.
The output schema is [{ id, title, one_line_diff, full_context }, …], ordered by repo-evidence strength.
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 · 105 lines · 60 tokens per session scan A 875cc54bda1f
clarify is a command published in the GitHub repository smicolon/ai-kit (6 stars, last pushed 1mo ago), licensed MIT. It adds 60 tokens to every session and 1,156 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 2026-08-31.
Other commands, from other repositories
version
Display current guide and Claude Code versions.
diff-docs
Compare official Anthropic docs baseline vs current snapshot (no network — instant).
security-review
A security review procedure based on CWE, a list of common software weaknesses, and STRIDE, a method for identifying threats to a system.
analyst
Use when performing local analyst review before pushing PR changes. Assesses code quality, impact analysis, and maintainability.
docs-review
Phase 4 of documenting-projects: Quality gate with 8 measurable criteria and iteration. Triggers: '/docs-review', invoked by documenting-projects orchestrator.
triage-github
Scan GitHub repos for activity, generate a summary, and create actionable GTD tasks.