Prompt Caching
davila7/claude-code-templates
Caching strategies for LLM prompts including Anthropic prompt caching, response caching, and CAG (Cache Augmented Generation) Use when: prompt caching, cache prompt, response cache, cag, cache…
Show this session's prompt-cache state, the cold-comeback price, and the cache writes paid so far
$ npx skills add karanb192/claude-code-hooks --skill status -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install karanb192/claude-code-hooks status --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/karanb192/claude-code-hooks.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/cache-tax/skills/status .claude/skills/status && 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 "status" agent skill from https://github.com/karanb192/claude-code-hooks/tree/main/plugins/cache-tax/skills/status into .claude/skills/status/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "status", 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/karanb192/claude-code-hooks/tree/main/plugins/cache-tax/skills/statusType 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 karanb192/claude-code-hooks --skill status -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install karanb192/claude-code-hooks status --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/karanb192/claude-code-hooks.git skills-src && mkdir -p .agents/skills && cp -r skills-src/plugins/cache-tax/skills/status .agents/skills/status && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "status" agent skill from https://github.com/karanb192/claude-code-hooks/tree/main/plugins/cache-tax/skills/status into .agents/skills/status/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "status", 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 karanb192/claude-code-hooks --skill status -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install karanb192/claude-code-hooks status --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/karanb192/claude-code-hooks.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/plugins/cache-tax/skills/status .cursor/skills/status && 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 "status" agent skill from https://github.com/karanb192/claude-code-hooks/tree/main/plugins/cache-tax/skills/status into .cursor/skills/status/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "status", 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/karanb192/claude-code-hooks.git --path plugins/cache-tax/skills/status--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 karanb192/claude-code-hooks --skill status -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install karanb192/claude-code-hooks status --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/karanb192/claude-code-hooks.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/plugins/cache-tax/skills/status .gemini/skills/status && 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 "status" agent skill from https://github.com/karanb192/claude-code-hooks/tree/main/plugins/cache-tax/skills/status into .gemini/skills/status/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "status", 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 karanb192/claude-code-hooks statusInstalls 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 karanb192/claude-code-hooks --skill status -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/karanb192/claude-code-hooks.git skills-src && mkdir -p .github/skills && cp -r skills-src/plugins/cache-tax/skills/status .github/skills/status && 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 "status" agent skill from https://github.com/karanb192/claude-code-hooks/tree/main/plugins/cache-tax/skills/status into .github/skills/status/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "status", 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 karanb192/claude-code-hooks --skill status -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install karanb192/claude-code-hooks status --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/karanb192/claude-code-hooks.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/plugins/cache-tax/skills/status .opencode/skills/status && 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 "status" agent skill from https://github.com/karanb192/claude-code-hooks/tree/main/plugins/cache-tax/skills/status into .opencode/skills/status/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "status", 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.
statusShow this session's prompt-cache state, the cold-comeback price, and the cache writes paid so far
Status is an agent skill from karanb192/claude-code-hooks. Show this session's prompt-cache state, the cold-comeback price, and the cache writes paid so far
Its SKILL.md is about 210 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
The repository describes itself as: 🪝 Claude Code hooks + an installable plugin marketplace: safety, cost, observability, productivity. The licence is MIT.
Read from SKILL.md and the folder at commit 3c9c90a. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Shell commands in SKILL.md call:
nodeFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Status loads about 212 tokens when it runs. Until then it costs about 26 tokens; SKILL.md has 106 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.
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.
The full file from karanb192/claude-code-hooks at commit 3c9c90a, republished under its MIT licence (© karanb192). 106 words, ~212 tokens.
.claude/skills/status/SKILL.md (or your agent's skills folder).!node "${CLAUDE_SKILL_DIR}/../../cache-tax.js" --render 2>/dev/null || node "${CLAUDE_PLUGIN_ROOT}/cache-tax.js" --render
The card above is this session's prompt-cache state from its own transcript: which cache tier the main conversation is on, whether the cache is warm or has lapsed, how many tokens the next message re-writes if it is cold and what that costs at list price, and the session's cache writes, reads and full re-writes so far.
State what the next message will cost in one sentence. If the cache is cold and the context is large, say whether /clear plus a short handoff note is the cheaper move. Keep it short; do not re-run any commands.
© karanb192, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in plugins/cache-tax/skills/status of karanb192/claude-code-hooks.
Open the folder on GitHubat commit 3c9c90a
Status 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 |
|---|---|---|---|---|---|---|
| Status this skillkaranb192/claude-code-hooks | 533 | — | ~212 | Automated safety check: Pass | MIT | |
| Prompt Cachingdavila7/claude-code-templates | 32k | 6 repos | ~452 | Automated safety check: Pass | MIT | |
| Turborepo Cachingwshobson/agents | 40k | 9 repos | ~2k | Automated safety check: Notes | MIT | |
| OmniRoute LLM Cachediegosouzapw/OmniRoute | 74k | 1 repos | ~529 | Automated safety check: Pass | MIT | |
| Cachingzebbern/claude-code-guide | 4.7k | — | ~1.5k | Automated safety check: Pass | MIT | |
| Content-Hash File Cache Patternaffaan-m/ECC | 275k | 5 repos | ~1.4k | Automated safety check: Pass | MIT |
davila7/claude-code-templates
Caching strategies for LLM prompts including Anthropic prompt caching, response caching, and CAG (Cache Augmented Generation) Use when: prompt caching, cache prompt, response cache, cag, cache…
wshobson/agents
Configures Turborepo pipelines and local or remote caching for monorepo builds, including Vercel remote cache, a self-hosted cache and cache-miss debugging.
diegosouzapw/OmniRoute
Documents OmniRoute's cache endpoints for reading cache statistics and clearing entries, statistics or the reasoning cache, with notes on TTL and similarity settings.
zebbern/claude-code-guide
Caching strategies — invalidation, TTL guidelines, cache keys, cache layers, and when not to cache.
affaan-m/ECC
Caches slow file processing results in Python keyed by a SHA-256 hash of the file content, so renames still hit the cache and edits invalidate it automatically.
thedaviddias/Front-End-Checklist
A skill your agent uses when auditing slow page loads, heavy assets, or rendering delays related to Enable browser caching.
karanb192/claude-code-hooks
Show the wanted-poster bounty board: this repo's TODO/FIXME/HACK debt priced as aging XP bounties
karanb192/claude-code-hooks
List this repo's recorded dead ends: approaches already tried and abandoned, with reasons and cost
karanb192/claude-code-hooks
Show this repo's context-cost leaderboard: the files that pulled the most tokens into context
karanb192/claude-code-hooks
Preview the provenance receipt (prompts, est. An agent skill from karanb192/claude-code-hooks.
karanb192/claude-code-hooks
Show your personal model-quality trend card (failure rate, edit churn, tokens/task by model version)
karanb192/claude-code-hooks
Show the CLAUDE.md compliance scorecard: which rules Claude actually follows vs ignores
Show this session's prompt-cache state, the cold-comeback price, and the cache writes paid so far. Status is an agent skill from karanb192/claude-code-hooks.
Run `npx skills add karanb192/claude-code-hooks --skill status -a claude-code`. Or copy the skill folder (plugins/cache-tax/skills/status in karanb192/claude-code-hooks) into .claude/skills/status in your project. Claude Code loads it when a task matches its description.
Run `npx skills add karanb192/claude-code-hooks --skill status -a codex`. Or copy the skill folder (plugins/cache-tax/skills/status in karanb192/claude-code-hooks) into .agents/skills/status in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add karanb192/claude-code-hooks --skill status -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/status, .gemini/skills/status, .github/skills/status and .opencode/skills/status in your project.
Going by SKILL.md and its folder, Status needs the command-line tools its instructions call (node).
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
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.
Status is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 212 tokens (SKILL.md is roughly 848 characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Status: Prompt Caching (davila7/claude-code-templates, 32k stars), Turborepo Caching (wshobson/agents, 40k stars), OmniRoute LLM Cache (diegosouzapw/OmniRoute, 74k stars) and Caching (zebbern/claude-code-guide, 4.7k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
karanb192 (a GitHub user) maintains it in karanb192/claude-code-hooks, which has 533 GitHub stars. The repository holds 8 skills in this directory. The repository was last updated on October 4, 2026.
Source: karanb192/claude-code-hooks on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.