unsloth-mcp-server: Command for Claude Code

.claude/commands/end.md

end is a command for Claude Code from ScientiaCapital/unsloth-mcp-server. It costs 20 tokens per session (1,471 once invoked), scanned A, original, Apache-2.0.

A set of instructions for an end-of-day development workflow called /end. It combines observer reports, security checks, project state updates, portfolio information, Git checks, and a handoff.

In plain words
What is it for?
Use it at the end of a workday to review observer findings, inspect Git activity and worktrees, check cost data, and prepare the project for handoff. The workflow defines actions for critical and blocking items.
Why use it?
It gathers unfinished work, quality or architecture warnings, alerts, costs, and repository state into one closing review. Required phases reduce the chance that important issues are silently ignored.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths.

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/end.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 end

README.md
[![agentmods](https://agentmods.dev/badge/commands/scientiacapital/unsloth-mcp-server/end.svg)](https://agentmods.dev/commands/scientiacapital/unsloth-mcp-server/end)
Your own site
<a href="https://agentmods.dev/commands/scientiacapital/unsloth-mcp-server/end"><img src="https://agentmods.dev/badge/commands/scientiacapital/unsloth-mcp-server/end.svg" alt="Measured on agentmods" height="20"></a>
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,471 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00020 $0.01471
Opus 5 $0.00010 $0.00736
Sonnet 5 $0.00004 $0.00294
Haiku 4.5 $0.00002 $0.00147

Measured 6d ago against content hash 93ed939b453e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

end 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."`

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/end.md · 159 lines

How it starts

The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/end — End Day Workflow v2

You are executing Tim's End Day workflow.

Dynamic Context

Project context: ! cat .claude/PROJECT_CONTEXT.md 2>/dev/null || echo "No PROJECT_CONTEXT.md found."

Observer reports: ! echo "=== QUALITY ===" && cat .claude/observers/QUALITY.md 2>/dev/null || echo "No quality report." ! echo "=== ARCH ===" && cat .claude/observers/ARCH.md 2>/dev/null || echo "No arch report." ! echo "=== ALERTS ===" && cat .claude/observers/ALERTS.md 2>/dev/null || echo "No alerts."

Git state: ! git status --short 2>/dev/null | head -10 ! git log --since="today 00:00" --oneline 2>/dev/null

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

Active worktrees: ! git worktree list 2>/dev/null

Instructions

Run all 6 phases in order. No phase is skippable.

Phase 1: Observer Final Report (~3 min)

Pull .claude/observers/QUALITY.md and .claude/observers/ARCH.md.

Disposition every item — nothing silently dropped:

Severity Action
CRITICAL Resolve now OR log to Backlog.md with owner + ETA
BLOCKER Resolve now OR log to Backlog.md with owner + ETA
WARNING Log to Backlog.md, prioritize by impact
RISK Log to Backlog.md, prioritize by impact
INFO Log or discard with justification

Devil's Advocate: verify every flagged item was genuinely addressed, not just acknowledged. Confirm no work today introduced new issues observers missed.

Phase 2: Security Sweep (~2 min)

Check if any new commits exist since the last security gate:

# Count commits since last build security gate
COMMITS_TODAY=$(git log --since="today 00:00" --oneline 2>/dev/null | wc -l | tr -d ' ')
echo "Commits today: $COMMITS_TODAY"

Skip if: no new commits since Build Phase 4 security gate passed (and Build Phase 4 was run today).

Read the full file on GitHub · 159 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 · 159 lines · 20 tokens per session scan A 93ed939b453e

Subscribe to this mod's changes

end is a command published in the GitHub repository ScientiaCapital/unsloth-mcp-server (2 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 20 tokens to every session and 1,471 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.