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/boparaiamrit/skills-by-amritWrote 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/boparaiamrit/skills-by-amrit/discuss)<a href="https://agentmods.dev/commands/boparaiamrit/skills-by-amrit/discuss"><img src="https://agentmods.dev/badge/commands/boparaiamrit/skills-by-amrit/discuss/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/boparaiamrit/skills-by-amrit/discuss"><img src="https://agentmods.dev/badge/commands/boparaiamrit/skills-by-amrit/discuss.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 | $0.00019 | $0.01947 |
| Opus 5 | $0.00010 | $0.00974 |
| Sonnet 5 | $0.00004 | $0.00389 |
| Haiku 4.5 | $0.00002 | $0.00195 |
Grade A, and why
discuss 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 11d 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 — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/discuss — Pre-Planning Decision Capture
Lock in the user's preferences before writing a plan. Prevents the #1 cause of rework: wrong assumptions about what the user wants.
Why This Exists
Without this, the planning cycle looks like:
- User says "add auth"
- Agent plans OAuth2
- User says "I wanted magic links"
- Agent replans from scratch — wasting 50% of the context window
With /discuss, decisions are locked BEFORE planning:
- User says "add auth"
- Agent presents 5 multiple-choice questions with recommendations
- User answers in one line:
1A 2B 3C 4A 5A - Agent locks decisions and plans exactly what was requested — zero rework
When to Use
- Before creating any implementation plan
- Before starting a new feature or non-trivial change
- When requirements are ambiguous or have multiple valid approaches
- When the user's preference matters (UI layout, library choice, architecture)
When NOT to Use
- Bug fixes with clear reproduction
- Configuration changes
- Tasks where there's only one sensible approach
- User explicitly says "just do it, I trust your judgment"
The Protocol
Step 1: Understand the Scope
Read the user's request and identify the decision points — places where multiple valid approaches exist. Group them by category.
Step 2: Present Multiple-Choice Questions
Present each question as a lettered multiple-choice with your recommendation highlighted. Always include a "Custom" option.
Format (MANDATORY):
---
## 📋 Discussion: [Feature Name]
I've identified [N] decisions we need to lock before planning. Here are your options:
---
### Q1: [Decision Category] 🏗️
| | Option | What It Means |
|:---:|:---|:---|
| **A** | [Option A name] | [1-line impact/trade-off] |
| **B** | [Option B name] | [1-line impact/trade-off] |
| **C** | [Option C name] | [1-line impact/trade-off] |
| **D** | ✏️ Custom | Describe your preference |
> 🏆 **Recommended: A** — [Why this is the best default]
---
### Q2: [Decision Category] 🔒
| | Option | What It Means |
|:---:|:---|:---|
| **A** | [Option A name] | [1-line impact/trade-off] |
| **B** | [Option B name] | [1-line impact/trade-off] |
| **C** | ✏️ Custom | Describe your preference |
> 🏆 **Recommended: B** — [Why this is the best default]
---
### Q3: [Decision Category] 🎨
| | Option | What It Means |
|:---:|:---|:---|
| **A** | [Option A name] | [1-line impact/trade-off] |
| **B** | [Option B name] | [1-line impact/trade-off] |
| **C** | ✏️ Custom | Describe your preference |
> 🏆 **Recommended: A** — [Why this is the best default]
---
### ⚡ Quick Answer
Answer all questions in one line. Use the letter for your choice, or quotes for custom answers.
> **All recommended:** `1A 2B 3A`
>
> **Example custom:** `1A 2B 3:"infinite scroll with cursor pagination"`
**Your answer:**
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.
- 11d ago First seen · 259 lines · 19 tokens per session scan A b27bb3fc8f32
discuss is a command published in the GitHub repository boparaiamrit/skills-by-amrit (5 stars, last pushed 5mo ago), licensed MIT. It adds 19 tokens to every session and 1,947 once invoked, about $0.0001 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 commands, from other repositories
minutes-ideas
Surface recent voice memos and ideas captured from any device. Use when the user asks "what ideas did I have?", "what were my recent memos?", "what did I record while walking?", or wants to recall a captured thought.
learn
Force claude-smart to extract learnings from this session now.
memory-store
Store an insight, decision, or pattern to memory.
cc-memory
Configure persistent memory that survives across sessions using a layered approach: split rule files for always-loaded context, auto-memory for organic learning, and optional MCP-backed long-term memory for large codebases.
analyze-context
USE WHEN you want to analyze project context before starting work on a task. Calls context + recall, then synthesizes goals, decisions, gotchas, and relevant memories into a pre-task brief.
music-suno-prompt
Grounded Suno prompt synthesis from local knowledge corpus + persona canon + label canon. No vibes-prompting.