unsloth-mcp-server: Command for Claude Code

.claude/commands/begin.md

begin is a command for Claude Code from ScientiaCapital/unsloth-mcp-server. It costs 15 tokens per session (1,046 once invoked), scanned A, original, Apache-2.0.

A “Start Day” command workflow that gathers project context, checks Git status, reviews blockers and spending, and can create a stand-up report and sprint plan.

In plain words
What is it for?
Use it to perform a lightweight readiness check or a full daily review with context synchronization, environment health checks, planning, and status reporting.
Why use it?
It brings important project state together at the beginning of work, reducing the chance of overlooking dirty files, missing dependencies, alerts, or unresolved issues.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; mentions subagents; positional $N argument.

This is ScientiaCapital/unsloth-mcp-server's own configuration. It tells Claude Code how to work on unsloth-mcp-server itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything unsloth-mcp-server configures →

Reuse

Borrowing it

Nothing to install: this file belongs to ScientiaCapital/unsloth-mcp-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/ScientiaCapital/unsloth-mcp-server/main/.claude/commands/begin.md
Clone the repo
git clone --depth 1 https://github.com/ScientiaCapital/unsloth-mcp-server

Made for: Claude Code.

Wrote 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.

agentmods badge for begin

README.md
[![agentmods](https://agentmods.dev/badge/commands/scientiacapital/unsloth-mcp-server/begin.svg)](https://agentmods.dev/commands/scientiacapital/unsloth-mcp-server/begin)
Your own site
<a href="https://agentmods.dev/commands/scientiacapital/unsloth-mcp-server/begin"><img src="https://agentmods.dev/badge/commands/scientiacapital/unsloth-mcp-server/begin.svg" alt="Measured on agentmods" height="20"></a>
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,046 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00015 $0.01046
Opus 5 $0.00008 $0.00523
Sonnet 5 $0.00003 $0.00209
Haiku 4.5 $0.00002 $0.00105

Measured 6d ago against content hash bcc764e972da, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

begin scanned grade A with 1 finding 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 6d 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.

Reads agent configuration directorieslowAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

! `cat .claude/PROJECT_CONTEXT.md 2>/dev/null || echo "No PROJECT_CONTEXT.md found — will generate one."`

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

.claude/commands/begin.md · 124 lines

How it starts

The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/begin — Start Day Workflow v2

You are executing Tim's Start Day workflow. Mode: $ARGUMENTS (default: "full" if blank).

Dynamic Context

Current project state: ! cat .claude/PROJECT_CONTEXT.md 2>/dev/null || echo "No PROJECT_CONTEXT.md found — will generate one."

Git state: ! git status --short 2>/dev/null | head -10 ! git log --oneline -5 2>/dev/null

Unresolved blockers: ! cat .claude/observers/ALERTS.md 2>/dev/null || echo "No alerts."

Cost state: ! jq '.' ~/.claude/daily-cost.json 2>/dev/null || echo '{"spent": 0, "budget_monthly": 100}'

Instructions

Mode Detection

If $1 is "light" OR the only planned work today is docs/typos/config/single-file patches:

  • Run Phase 1 only, then report ready status
  • Skip Phases 2-4

If $1 is "full" or blank:

  • Run all 4 phases in order

Phase 1: Context Sync + Environment Health (~3 min)

  1. Read .claude/PROJECT_CONTEXT.md — verify it matches the current project. If missing, auto-generate from git log + package.json/pyproject.toml
  2. Show git state (branch, ahead/behind, dirty files)
  3. Environment health checks:
    • package.json exists but no node_modules? → warn "Run npm install"
    • requirements.txt exists but no .venv? → warn "Run pip install"
    • .env.example exists but no .env? → warn "Copy .env.example → .env"
  4. Cost check: show MTD spend vs $100/mo budget with percentage
  5. Show any unresolved items from .claude/observers/ALERTS.md
    • BLOCKERs must be cleared or moved to Backlog.md with owner + ETA before new feature work

Phase 2: Observer Audit (~5 min) [FULL DAY ONLY]

Run two observer audits as point-in-time checks (NOT persistent daemons):

Code Quality Observer (use haiku model if spawning subagent):

  • Audit git diff HEAD~5..HEAD for: tech debt, test gaps, silent exception handlers, hardcoded values, unused imports
  • Write findings to .claude/observers/QUALITY.md
  • Format: [CRITICAL | WARNING | INFO] — file:line — description — fix

Read the full file on GitHub · 124 lines

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. 6d ago First seen · 124 lines · 15 tokens per session scan A bcc764e972da

Subscribe to this mod's changes

begin is a command published in the GitHub repository ScientiaCapital/unsloth-mcp-server (2 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 15 tokens to every session and 1,046 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.