claude-code-system-prompts is a repository that records the system prompts, tool descriptions, agent prompts, and utility prompts used by Claude Code. It serves people who want to inspect how Claude Code structures its built-in agents and tools across releases. The catalogue instruction provides access to material documenting that workflow.
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.
npx skills add Piebald-AI/claude-code-system-prompts --skill tool-description-invokegit clone --depth 1 https://github.com/Piebald-AI/claude-code-system-promptsWrote 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/skills/piebald-ai/claude-code-system-prompts/tool-description-invoke)<a href="https://agentmods.dev/skills/piebald-ai/claude-code-system-prompts/tool-description-invoke"><img src="https://agentmods.dev/badge/skills/piebald-ai/claude-code-system-prompts/tool-description-invoke.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 | $0.00035 | $0.00373 |
| Opus 5 | $0.00017 | $0.00187 |
| Sonnet 5 | $0.00007 | $0.00075 |
| Haiku 4.5 | $0.00003 | $0.00037 |
Grade A, and why
Tool Description: Invoke skill 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 3d 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.
What it actually says
Invoke a skill.
A skill is a packaged set of instructions the user or project has set up for a particular kind of task (deploy steps, a review checklist, a repo-specific workflow). Available skills appear in a system-reminder listing with one-line descriptions. When the task at hand is one a listed skill covers, call this tool first — the skill's instructions load into the turn for you to follow in place of your default approach; some skills instead run in a subagent and return the finished result. A skill that runs in the background returns only the agent's name — its result arrives later as a task notification, so don't wait on it or invoke it again in the meantime. Users may also ask for one by name (/<name>, or "slash command"); that's a request to invoke it.
skill: exact name from the listing, no leading slash. Plugin skills useplugin:skill. Directory-scoped skills are listed with a path prefix (apps/web:deploy); when both scoped and unscoped variants of a name exist, pick the one whose directory contains the files you're working on (most specific wins; unscoped otherwise).args: optional arguments to pass through.
Only names from the listing (or that the user typed explicitly) are valid. Built-in CLI commands (/help, /clear, …) aren't skills. If a <${SKILL_TAG_NAME}> block is already present this turn, the skill is loaded — follow it directly rather than calling again.
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.
- 3d ago First seen · 16 lines · 35 tokens per session scan A 7bc210fe31b4
Tool Description: Invoke skill is a skill published in the GitHub repository Piebald-AI/claude-code-system-prompts (12,609 stars, last pushed 2d ago), licensed MIT. It adds 35 tokens to every session and 373 once invoked, about $0.0002 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 2026-09-05.
Other skills, from other repositories
cached-system-instructions
How to structure hierarchical, immutable system instructions to maximize KV-cache hits on Anthropic and OpenAI, slashing Time-to-First-Token (TTFT) by 80% and input costs by 90%.
avoid-duplicate-system-messages
How to consolidate fragmented system instructions into a single static cacheable header, maximizing Anthropic and OpenAI prompt cache hit rates and cutting input token costs by 90%.
compressed-system-prompts
How to refactor wordy, repetitive system prompts into high-density imperative token structures, cutting baseline system prompt costs by 70% while improving instruction adherence.
agentic-token-efficiency-master-rule
The definitive operational architecture governing zero-waste token utilization, surgical context management, and latency minimization for autonomous AI coding agents.
agent-system-prompt-architect
Use when designing, reviewing, revising, or templating deployable system prompts for agent projects, especially prompts needing clear roles, task boundaries, tool-use rules, evidence handling, output formats, safety behavior, or compact runtime-ready structure.
deep-learning-expert
Use this skill when user needs to design deep learning models, perform training optimization, interpret papers, or solve engineering practice issues. Trigger keywords: deep learning, neural networks, model training, overfitting, gradient vanishing, PyTorch, TensorFlow, pretrained models, fine-tuning, model deployment…