Commerce Prompt Caching
anthropics/commerce-agents
The reference agents' cache-stable request assembly, covering the static system and per-request context split, the fixed tool list, the rolling conversation breakpoint, which config fields are…
Anthropic API prompt caching: TTL, breakpoints, stacking, invalidation, hit rate.
Install Prompt Caching Patterns
$ npx skills add softspark/ai-toolkit --skill prompt-caching-patterns -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install softspark/ai-toolkit prompt-caching-patterns --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/softspark/ai-toolkit.git skills-src && mkdir -p .claude/skills && cp -r skills-src/app/skills/prompt-caching-patterns .claude/skills/prompt-caching-patterns && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "prompt-caching-patterns" agent skill from https://github.com/softspark/ai-toolkit/tree/main/app/skills/prompt-caching-patterns into .claude/skills/prompt-caching-patterns/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prompt-caching-patterns", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/softspark/ai-toolkit/tree/main/app/skills/prompt-caching-patternsType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add softspark/ai-toolkit --skill prompt-caching-patterns -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install softspark/ai-toolkit prompt-caching-patterns --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/softspark/ai-toolkit.git skills-src && mkdir -p .agents/skills && cp -r skills-src/app/skills/prompt-caching-patterns .agents/skills/prompt-caching-patterns && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "prompt-caching-patterns" agent skill from https://github.com/softspark/ai-toolkit/tree/main/app/skills/prompt-caching-patterns into .agents/skills/prompt-caching-patterns/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prompt-caching-patterns", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add softspark/ai-toolkit --skill prompt-caching-patterns -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install softspark/ai-toolkit prompt-caching-patterns --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/softspark/ai-toolkit.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/app/skills/prompt-caching-patterns .cursor/skills/prompt-caching-patterns && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "prompt-caching-patterns" agent skill from https://github.com/softspark/ai-toolkit/tree/main/app/skills/prompt-caching-patterns into .cursor/skills/prompt-caching-patterns/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prompt-caching-patterns", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/softspark/ai-toolkit.git --path app/skills/prompt-caching-patterns--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add softspark/ai-toolkit --skill prompt-caching-patterns -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install softspark/ai-toolkit prompt-caching-patterns --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/softspark/ai-toolkit.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/app/skills/prompt-caching-patterns .gemini/skills/prompt-caching-patterns && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "prompt-caching-patterns" agent skill from https://github.com/softspark/ai-toolkit/tree/main/app/skills/prompt-caching-patterns into .gemini/skills/prompt-caching-patterns/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prompt-caching-patterns", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install softspark/ai-toolkit prompt-caching-patternsInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add softspark/ai-toolkit --skill prompt-caching-patterns -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/softspark/ai-toolkit.git skills-src && mkdir -p .github/skills && cp -r skills-src/app/skills/prompt-caching-patterns .github/skills/prompt-caching-patterns && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "prompt-caching-patterns" agent skill from https://github.com/softspark/ai-toolkit/tree/main/app/skills/prompt-caching-patterns into .github/skills/prompt-caching-patterns/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prompt-caching-patterns", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add softspark/ai-toolkit --skill prompt-caching-patterns -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install softspark/ai-toolkit prompt-caching-patterns --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/softspark/ai-toolkit.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/app/skills/prompt-caching-patterns .opencode/skills/prompt-caching-patterns && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "prompt-caching-patterns" agent skill from https://github.com/softspark/ai-toolkit/tree/main/app/skills/prompt-caching-patterns into .opencode/skills/prompt-caching-patterns/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prompt-caching-patterns", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
prompt-caching-patterns- GitHub stars
- 179
- Token cost
- ~1.1k tokens
- SKILL.md length
- 414 words
- Files
- 1
- Skills in repo
- 112
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Anthropic API prompt caching: TTL, breakpoints, stacking, invalidation, hit rate.
- Tasks that involve LLM cost and token optimization
- SKILL.md covers Dated cache reference…, Prefix design, Explicit caching example and Invalidation, plus 3 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
- Tasks that involve Responsive design
What it does
Prompt Caching Patterns is an agent skill from softspark/ai-toolkit. Anthropic API prompt caching: TTL, breakpoints, stacking, invalidation, hit rate. Triggers: prompt caching, cachecontrol, cache breakpoint, cache TTL, hit rate.
Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in AI & LLM Engineering, covering LLM cost and token optimization and Responsive design. It works with Anthropic API. The repository describes itself as: Professional-grade AI coding toolkit: 94 skills, 44 agents, multi-platform (Claude, Cursor, Windsurf, Copilot, Gemini, Cline, Roo Code, Aider, Augment, Antigravity, Codex CLI… The licence is Apache-2.0.
When your agent uses it
- Tasks that involve LLM cost and token optimization
- Tasks that involve Responsive design
Example prompts
- “/prompt-caching-patterns”
Requirements
- Python 3
- Pre-approved tools (allowed-tools): Read
What it can do on your machine
Read from SKILL.md and the folder at commit d64db2b. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves these tools, so the agent can use them without asking each time:
Read
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are python).
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
platform.claude.com
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Prompt Caching Patterns loads about 1.1k tokens when it runs. Until then it costs about 46 tokens; SKILL.md has 414 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from softspark/ai-toolkit at commit d64db2b, republished under its Apache-2.0 licence (© softspark). 414 words, ~1,133 tokens.
Download SKILL.mdSave it as
.claude/skills/prompt-caching-patterns/SKILL.md (or your agent's skills folder).- name
- prompt-caching-patterns
- description
- Anthropic API prompt caching: TTL, breakpoints, stacking, invalidation, hit rate. Triggers: prompt caching, cache_control, cache breakpoint, cache TTL, hit rate.
- allowed-tools
- Read
- effort
- medium
- user-invocable
- false
Prompt Caching Patterns
Cache repeated prefixes when reuse offsets write costs. Cache eligibility and pricing depend on the model and platform; a short system prompt is not cached merely because it repeats.
Dated cache reference (2026-09-23)
| Model | Minimum eligible prefix | Cache read / base input price |
|---|---|---|
| Claude Opus 5.5 | 512 tokens | 5% |
| Claude Fable 5.1 | 512 tokens | 2.5% |
| Claude Sonnet 5 | 1024 tokens | 10% |
| Claude Haiku 4.5 | 4096 tokens | 10% |
For the Claude API, a five-minute write costs 1.25 times base input and a one-hour write costs 2 times base input. Recheck current pricing before budgeting; provider-specific billing and model availability can differ.
Prefix design
Cache order is tools → system → messages, regardless of the order of request
keys. An explicit breakpoint includes the marked block and everything before it.
Keep dynamic material after the stable prefix.
[ tool definitions ] breakpoint 1
[ reusable system instructions ] breakpoint 2
[ reference documents ] breakpoint 3
[ stable conversation prefix ] breakpoint 4
[ current variable content ]There are at most four breakpoints. Top-level automatic cache_control moves a
breakpoint to the last eligible block and consumes one slot. Explicit markers
give control over a static prefix.
Explicit caching example
The caller supplies the approved model, text and output limit. Marking a prefix below its model's minimum silently produces no cache entry.
def cached_answer(client, model, policy, document, question, max_tokens):
return client.messages.create(
model=model,
max_tokens=max_tokens,
system=[{
"type": "text",
"text": policy,
"cache_control": {"type": "ephemeral"},
}],
messages=[{
"role": "user",
"content": [
{"type": "text", "text": document,
"cache_control": {"type": "ephemeral"}},
{"type": "text", "text": question},
],
}],
)Use {"type": "ephemeral", "ttl": "1h"} for an approved one-hour write. When mixing
TTLs, put longer-lived breakpoints before shorter-lived ones. Do not send paid
heartbeat requests simply to keep an unused prefix warm.
Show full SKILL.md (193 more words)Show less
Invalidation
Changing tools invalidates subsequent system and message prefixes; changing the system invalidates subsequent messages. Top-level effort changes invalidate message cache blocks and can affect earlier blocks depending on the model. Supported per-message effort updates preserve earlier prefixes. Changing the model is not a promise of cross-model cache reuse.
A static string passed as system alone does not enable caching: configure
cache_control at the request or content-block level. Keep tool definitions,
document serialization and stable instructions deterministic.
Measuring reuse
Include writes when calculating the fraction of input served from cache.
def cache_read_fraction(usage):
read = usage.cache_read_input_tokens or 0
written = usage.cache_creation_input_tokens or 0
uncached = usage.input_tokens or 0
total = read + written + uncached
return read / total if total else 0.0Record write/read counts and actual costs across cold and warm requests. Choose a target from observed reuse; a single universal hit-rate threshold is misleading. Both cache counters remaining zero can indicate an ineligible prefix.
When not to cache
Skip cache writes when no prefix will be reused before expiry or when measured cost exceeds uncached requests. Do not pad prompts with irrelevant content merely to reach a minimum. A one-hour TTL may fit intermittent reuse better than five minutes, within the approved cost policy.
Sources and related skills
Reviewed 2026-09-23:
Use model-routing-patterns for route evaluation and llm-ops-engineer for
application operations.
© softspark, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in app/skills/prompt-caching-patterns of softspark/ai-toolkit.
Open the folder on GitHubat commit d64db2b
Compare with similar skills
Prompt Caching Patterns next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Prompt Caching Patterns this skillsoftspark/ai-toolkit | 179 | — | ~1.1k | Automated safety check: Pass | Apache-2.0 | |
| Commerce Prompt Cachinganthropics/commerce-agents | 3.2k | — | ~2k | Automated safety check: Pass | Apache-2.0 | |
| Prompt CachingArchive228/loopkit | 755 | — | ~735 | Automated safety check: Pass | MIT | |
| Token Optimizationcwinvestments/memstack | 423 | — | ~1.4k | Automated safety check: Pass | Proprietary | |
| Claude API In Prototypesasgeirtj/system_prompts_leaks | 69k | — | ~281 | Automated safety check: Pass | CC0-1.0 | |
| Claude APIkid-sid/claude-spellbook | 189 | — | ~2.7k | Automated safety check: Pass | MIT |
Similar skills
- Official
Prompt Caching
Archive228/loopkit
Cache the parts of the prompt that don't change so a long-running loop stops paying full price on every turn.
Token Optimization
cwinvestments/memstack
A skill your agent uses when the user says 'token optimization', 'save tokens', 'context window', 'reduce tokens', 'token stack', or 'TokenStack', or asks about extending context window capacity.
Claude API In Prototypes
asgeirtj/system_prompts_leaks
Call Claude from your HTML artifacts via window.claude.complete
Claude API
kid-sid/claude-spellbook
A skill your agent uses when building or debugging apps that call the Claude API — implementing tool use, streaming, vision, prompt caching, batch processing, extended thinking, or an agentic loop…
Claude API Development
warpdotdev/warp
Guides building, debugging and tuning apps on the Claude API and Anthropic SDK, including prompt caching, and migrating code between Claude model versions.
More from softspark/ai-toolkit
All 112 skills in this repoPrepare Test Env
softspark/ai-toolkit
Prepare or verify a project QA environment with source identity, readiness, browser access, evidence paths and owned cleanup.
A11y Validate
softspark/ai-toolkit
Accessibility validator: WCAG 2.1 AA, EN 301 549, EAA. An agent skill from softspark/ai-toolkit.
Analyze
softspark/ai-toolkit
Analyzes code quality, complexity, patterns across codebase.
Autonomous Dev
softspark/ai-toolkit
Drives a brief, specification, issue or existing PR through implementation, review, tests and QA to a ready PR.
Brand Voice
softspark/ai-toolkit
Direct technical voice for docs, README, user-facing text. An agent skill from softspark/ai-toolkit.
CI
softspark/ai-toolkit
Detect/generate/debug CI pipeline config (GitHub Actions, GitLab CI).
Related
Works with
Categories
Questions about Prompt Caching Patterns
What does Prompt Caching Patterns do?
Anthropic API prompt caching: TTL, breakpoints, stacking, invalidation, hit rate. Prompt Caching Patterns is an agent skill from softspark/ai-toolkit. Anthropic API prompt caching: TTL, breakpoints, stacking, invalidation, hit rate.
When should I use Prompt Caching Patterns?
Prompt Caching Patterns fits situations like: tasks that involve LLM cost and token optimization; tasks that involve Responsive design.
How do I install Prompt Caching Patterns in Claude Code?
Run `npx skills add softspark/ai-toolkit --skill prompt-caching-patterns -a claude-code`. Or copy the skill folder (app/skills/prompt-caching-patterns in softspark/ai-toolkit) into .claude/skills/prompt-caching-patterns in your project. Claude Code loads it when a task matches its description.
How do I install Prompt Caching Patterns in Codex?
Run `npx skills add softspark/ai-toolkit --skill prompt-caching-patterns -a codex`. Or copy the skill folder (app/skills/prompt-caching-patterns in softspark/ai-toolkit) into .agents/skills/prompt-caching-patterns in your project. Codex loads it when a task matches its description.
Can I use Prompt Caching Patterns in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add softspark/ai-toolkit --skill prompt-caching-patterns -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/prompt-caching-patterns, .gemini/skills/prompt-caching-patterns, .github/skills/prompt-caching-patterns and .opencode/skills/prompt-caching-patterns in your project.
What does Prompt Caching Patterns need to run?
SKILL.md names no scripts, command-line tools or credentials: Prompt Caching Patterns is instructions for the agent only. Our summary lists: Python 3. Its frontmatter pre-approves these tools: Read.
Does Prompt Caching Patterns access the network?
SKILL.md names 1 domain. As links in the text: platform.claude.com. This is read from the text; nothing was executed.
Is Prompt Caching Patterns safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Prompt Caching Patterns use?
Prompt Caching Patterns is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Prompt Caching Patterns use?
About 1.1k tokens (SKILL.md is roughly 4.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Prompt Caching Patterns?
Skills that share tags, products or a category with Prompt Caching Patterns: Commerce Prompt Caching (anthropics/commerce-agents, 3.2k stars), Prompt Caching (Archive228/loopkit, 755 stars), Token Optimization (cwinvestments/memstack, 423 stars) and Claude API In Prototypes (asgeirtj/system_prompts_leaks, 69k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Prompt Caching Patterns?
softspark (a GitHub user) maintains it in softspark/ai-toolkit, which has 179 GitHub stars. The repository holds 112 skills in this directory. The repository was last updated on October 7, 2026.
Source: softspark/ai-toolkit on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.