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.
curl -O https://raw.githubusercontent.com/ScientiaCapital/unsloth-mcp-server/main/.claude/commands/build.mdgit clone --depth 1 https://github.com/ScientiaCapital/unsloth-mcp-serverWrote 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/scientiacapital/unsloth-mcp-server/build)<a href="https://agentmods.dev/commands/scientiacapital/unsloth-mcp-server/build"><img src="https://agentmods.dev/badge/commands/scientiacapital/unsloth-mcp-server/build.svg" alt="Measured on agentmods" 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 | $0.00014 | $0.01278 |
| Opus 5 | $0.00007 | $0.00639 |
| Sonnet 5 | $0.00003 | $0.00256 |
| Haiku 4.5 | $0.00001 | $0.00128 |
Grade A, and why
build 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 7d 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 — run /begin first."` Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/build — Feature Build Workflow v2
You are executing Tim's Build workflow for feature: $ARGUMENTS
Dynamic Context
Project context:
! cat .claude/PROJECT_CONTEXT.md 2>/dev/null || echo "No PROJECT_CONTEXT.md — run /begin first."
Current sprint plan (if exists):
! grep -A 20 "Sprint Plan" .claude/TASK.md 2>/dev/null || echo "No sprint plan found."
Active worktrees:
! git worktree list 2>/dev/null
Cost state:
! jq '.' ~/.claude/daily-cost.json 2>/dev/null || echo '{"spent": 0, "budget_monthly": 100}'
Existing contracts:
! ls .claude/contracts/ 2>/dev/null || echo "No contracts directory yet."
Instructions
Phase 1: Contract + Team Setup (~5 min)
- Load
.claude/PROJECT_CONTEXT.md— confirm build targets match approved sprint plan - Check for feature contract at
.claude/contracts/$1.ts(or.claude/contracts/$1.py)- If exists → load and confirm scope
- If missing → create it now with interface definitions, input/output types, error contracts
- No builder touches code without a contract
- Decompose work into independent tasks
- Route each task through agent-capability-matrix (use skills on-demand, don't preload)
- Present assignment map:
## Build Assignment — $ARGUMENTS
| Task | Agent | Skill | Worktree | Model | Est Cost |
| ---- | ----- | ----- | -------- | ----- | -------- |
Contract: .claude/contracts/$1.ts
GATE: Wait for user approval before spawning any agents or writing code.
Phase 2: Execute (~variable)
Builders — each receives a task with:
- Task description (< 50 words)
- Contract file path
- Scope boundary (what this agent owns / does NOT touch)
- Verification checklist
Builders run tests inline. Commit only when checklist is green. Push branch — never merge to main directly.
Use conventional commits: feat:, fix:, test:, refactor:, docs:
Observers — run at commit boundaries (point-in-time, not persistent):
- Code Quality Observer: audit
git diffacross builder work - Architecture Observer: check for contract drift, scope creep, duplicate logic
- Devil's Advocate: at each gate, challenge both teams per §Roles
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.
- 7d ago First seen · 151 lines · 14 tokens per session scan A d396c252d88e
build is a command published in the GitHub repository ScientiaCapital/unsloth-mcp-server (2 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 14 tokens to every session and 1,278 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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.