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 skills add yash-gadodia/claude-init --skill clarifygit clone --depth 1 https://github.com/yash-gadodia/claude-initWrote 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/skills/yash-gadodia/claude-init/clarify)<a href="https://agentmods.dev/skills/yash-gadodia/claude-init/clarify"><img src="https://agentmods.dev/badge/skills/yash-gadodia/claude-init/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/skills/yash-gadodia/claude-init/clarify"><img src="https://agentmods.dev/badge/skills/yash-gadodia/claude-init/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 | $0.00042 | $0.00985 |
| Opus 5 | $0.00021 | $0.00492 |
| Sonnet 5 | $0.00008 | $0.00197 |
| Haiku 4.5 | $0.00004 | $0.00098 |
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 9d 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Clarify: Idea → Design → Spec
Transform vague requirements into implementation-ready specifications through structured dialogue.
When This Triggers
Automatically when:
- The request is ambiguous or has multiple valid interpretations
- The request spans multiple subsystems or involves architecture decisions
- You'd have to guess at important details to start implementing
Skip when: the request is clear and specific enough to plan directly.
Process
1. Explore Context
Before asking a single question, check the codebase:
- Read ARCHITECTURE.md for system context
- Find related code — are there existing patterns for this type of feature?
- Check recent commits — is there related work in progress?
Don't ask things you can answer by reading.
2. Clarify Intent (max 3 questions)
Ask questions one at a time. Prefer multiple choice.
Good: "Should this work for unauthenticated users too, or only logged-in? (a) logged-in only (b) both (c) only unauthenticated" Bad: "What tech stack should we use?" (you can see the codebase) Bad: Asking 5 questions at once
Focus on: purpose, constraints, success criteria. Not implementation details — that comes in planning.
3. Propose Approaches
For non-trivial work, propose 2-3 approaches:
- Lead with your recommendation and why
- Show trade-offs (complexity, time, risk, flexibility)
- YAGNI ruthlessly — remove unnecessary features from all options
4. Write the Spec
# Spec: [Feature Name]
## Problem
<1-2 sentences: what pain point this solves>
## Solution
<The chosen approach, 2-3 sentences>
## Acceptance Criteria
- [ ] Given [context], when [action], then [result]
- [ ] Edge case: [scenario] → [expected behavior]
- [ ] Error case: [failure mode] → [expected handling]
## Assumptions
<What we assumed that wasn't explicit in the request>
## Technical Notes
- Extends: [existing code/patterns to build on]
- Changes: [what needs to be modified]
- New: [what needs to be created]
## Out of Scope
<What this explicitly does NOT include>
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.
- 9d ago First seen · 116 lines · 42 tokens per session scan A 65f74ce59acf
clarify is a skill published in the GitHub repository yash-gadodia/claude-init (5 stars, last pushed 2d ago), licensed MIT. It adds 42 tokens to every session and 985 once invoked, about $0.0002 per session on Opus 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 skills, from other repositories
code-review
You are a senior code reviewer. You receive diffs via stdin.
mainframe
Use when Pi writes, reviews, or executes bash; use MAINFRAME tools, AWM, and guarded function execution when available.
mainframe
Discover MAINFRAME read-only shell helpers and route durable agent authority through its control plane when available.
skit
Run, inspect, and manage entries in the user's skit library — their personal hub, manager, and launcher for scripts in many languages (Python, shell, JS/TS, and more), executables, command templates, and AI-agent prompts, with typed parameter forms, saved presets, and per-entry launch policy. Use when the user asks to…
setup
Use when setting up a project, adding linting, formatting, git hooks, or type checking. Detects the language and installs that ecosystem's lint/format/hooks toolchain (JS/TS, Python, Go, Rust).
deps
Use when hardening a dependency supply chain, pinning versions, adding registry/security flags, or setting up Renovate. Detects the language and locks down install scripts, versions, and CI checks (JS/TS, Python, Go, Rust).