shipit: Skill for Claude Code

.claude/skills/prompt-architecture/SKILL.md

prompt-architecture is a skill for Claude Code from nikzlabs/shipit. It costs 75 tokens per session (914 once invoked), scanned A, original, Apache-2.0.

A set of rules for storing and assembling the text instructions given to language-model agents. It keeps prompt text in Markdown files and the code that combines it in TypeScript.

In plain words
What is it for?
Use it when editing agent instructions, voice-cleanup prompts, session naming, or other model-facing text. It covers prompt composition and tests for prompt assembly and caching.
Why use it?
Keeping instructions mixed into program code makes them harder to review, test, and safely update. These rules also describe how to load prompts consistently and detect missing files early.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

This is nikzlabs/shipit's own configuration. It tells Claude Code how to work on shipit 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 shipit configures →

Reuse

Borrowing it

Nothing to install: this file belongs to nikzlabs/shipit. 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/nikzlabs/shipit/main/.claude/skills/prompt-architecture/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/nikzlabs/shipit

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 prompt-architecture

README.md
[![agentmods](https://agentmods.dev/badge/skills/nikzlabs/shipit/prompt-architecture/github.svg)](https://agentmods.dev/skills/nikzlabs/shipit/prompt-architecture)
Your own site
<a href="https://agentmods.dev/skills/nikzlabs/shipit/prompt-architecture"><img src="https://agentmods.dev/badge/skills/nikzlabs/shipit/prompt-architecture/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.

agentmods 80×15 button for prompt-architecture

Your own site · 80×15
<a href="https://agentmods.dev/skills/nikzlabs/shipit/prompt-architecture"><img src="https://agentmods.dev/badge/skills/nikzlabs/shipit/prompt-architecture.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 914 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00075 $0.00914
Opus 5 $0.00037 $0.00457
Sonnet 5 $0.00015 $0.00183
Haiku 4.5 $0.00007 $0.00091

Measured 10d ago against content hash f8c48f67e220, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

prompt-architecture 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 10d 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.

.claude/skills/prompt-architecture/SKILL.md · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Prompt architecture

LLM prompts — agent system instructions, voice cleanup, session naming — are content, not logic. Keep the two separated.

Prompt text is data: it lives in .md files

Co-locate the .md with the code that composes it. Prose reviews as prose, diffs cleanly, and needs no backtick or ${} escaping.

Load it with loadPrompt(import.meta.url, "./x.md") (orchestrator/load-prompt.ts), at module top level — once at init, never per call. A missing file then throws at boot rather than mid-turn.

Not a bundler ?raw import: production runs TS via tsx with no bundler, so fs.readFileSync(new URL(...)) is what actually works.

Examples: agents/<id>/system-prompt.md, voice/cleanup-prompt.md, orchestrator/prompts/*.md.

Known exception: session-namer.ts still defines its PROMPT_TEMPLATE inline in TypeScript and substitutes per call. It predates this convention and is not a model to copy — if you touch it, move the text to an .md rather than extending the inline template.

Prompt composition is code

Axis branching and fragment selection stay in TypeScript. In agent-instructions.ts, renderInstructions fills {{TOKEN}} holes in prompts/skeleton.md via fillPromptTokens, which throws on an unfilled token — that's the guard ensuring no literal {{FOO}} ever reaches the model.

There are two axes: agentId (Parallel-sessions wording) and the session mode, which has three values — std, ops (docs/128), and sandbox (docs/211). isOps and isSandbox are mutually exclusive, and ops wins if both are passed. Every (agentId, mode) pair is precomputed, so don't write code or tests that assume a single isOps boolean.

The prompt-cache contract is load-bearing

Every (agentId, mode) variant renders once at module load into PRECOMPUTED_INSTRUCTIONS, a module-level ReadonlyMap (typed as read-only; not runtime-frozen). The per-turn path is a pure lookup, which keeps the CLI string byte-stable so the Anthropic prompt cache stays warm.

Read the full file on GitHub · 52 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. 10d ago First seen · 52 lines · 75 tokens per session scan A f8c48f67e220

Subscribe to this mod's changes

prompt-architecture is a skill published in the GitHub repository nikzlabs/shipit (7 stars, last pushed today), licensed Apache-2.0. It adds 75 tokens to every session and 914 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

nowait-reasoning-optimizer

Implements the NOWAIT technique for efficient reasoning in R1-style LLMs. Use when optimizing inference of reasoning models (QwQ, DeepSeek-R1, Phi4-Reasoning, Qwen3, Kimi-VL, QvQ), reducing chain-of-thought token usage by 27-51% while preserving accuracy. Triggers on "optimize reasoning", "reduce thinking tokens"…

foryourhealth111-pixel/Vibe-Skills · 110 tokens

prompt-lookup

Activates when the user asks about AI prompts, needs prompt templates, wants to search for prompts, or mentions prompts.chat. Use for discovering, retrieving, and improving prompts.

foryourhealth111-pixel/Vibe-Skills · 39 tokens

loom-prompt-engineering

Designs and optimizes prompts for large language models including system prompts, agent signals, and few-shot examples.

cosmix/loom · 28 tokens

ai-orchestration-langchain

LangChain.js patterns for building LLM applications — chat models, LCEL chains, prompt templates, structured output, agents, tools, RAG, streaming, and LangSmith tracing.

agents-inc/skills · 43 tokens

prompt-engineering

Create, update, review, or discuss an LLM prompt — a system prompt, a skill, or an agent. Use when writing or improving a prompt, discussing a skill or agent, diagnosing prompt failures, or when the user says a prompt needs work.

doodledood/manifest-dev · 56 tokens

ai-observability-promptfoo

Testing and evaluation framework for LLM prompts and applications -- promptfooconfig.yaml, assertions, model-graded evals, red teaming, CI/CD integration, custom providers, and comparative evaluation.

agents-inc/skills · 46 tokens