ClawRouter LLM Gateway
BlockRunAI/ClawRouter
Describes ClawRouter, a local proxy that forwards each LLM request to the blockrun.ai gateway, which routes to a cheaper capable model, paid by USDC wallet or API key credit.
Minimize token consumption & maximize prompt cache hit rate.
Install Token Saver
$ npx skills add lokikill123/codex-token-skills --skill token-saver -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install lokikill123/codex-token-skills token-saver --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/lokikill123/codex-token-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/token-saver .claude/skills/token-saver && 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 "token-saver" agent skill from https://github.com/lokikill123/codex-token-skills/tree/main/skills/token-saver into .claude/skills/token-saver/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "token-saver", 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/lokikill123/codex-token-skills/tree/main/skills/token-saverType 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 lokikill123/codex-token-skills --skill token-saver -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install lokikill123/codex-token-skills token-saver --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/lokikill123/codex-token-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/token-saver .agents/skills/token-saver && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "token-saver" agent skill from https://github.com/lokikill123/codex-token-skills/tree/main/skills/token-saver into .agents/skills/token-saver/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "token-saver", 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 lokikill123/codex-token-skills --skill token-saver -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install lokikill123/codex-token-skills token-saver --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/lokikill123/codex-token-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/token-saver .cursor/skills/token-saver && 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 "token-saver" agent skill from https://github.com/lokikill123/codex-token-skills/tree/main/skills/token-saver into .cursor/skills/token-saver/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "token-saver", 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/lokikill123/codex-token-skills.git --path skills/token-saver--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 lokikill123/codex-token-skills --skill token-saver -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install lokikill123/codex-token-skills token-saver --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/lokikill123/codex-token-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/token-saver .gemini/skills/token-saver && 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 "token-saver" agent skill from https://github.com/lokikill123/codex-token-skills/tree/main/skills/token-saver into .gemini/skills/token-saver/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "token-saver", 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 lokikill123/codex-token-skills token-saverInstalls 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 lokikill123/codex-token-skills --skill token-saver -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/lokikill123/codex-token-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/token-saver .github/skills/token-saver && 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 "token-saver" agent skill from https://github.com/lokikill123/codex-token-skills/tree/main/skills/token-saver into .github/skills/token-saver/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "token-saver", 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 lokikill123/codex-token-skills --skill token-saver -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install lokikill123/codex-token-skills token-saver --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/lokikill123/codex-token-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/token-saver .opencode/skills/token-saver && 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 "token-saver" agent skill from https://github.com/lokikill123/codex-token-skills/tree/main/skills/token-saver into .opencode/skills/token-saver/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "token-saver", 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
token-saver- GitHub stars
- 119
- Token cost
- ~298 tokens
- SKILL.md length
- 140 words
- Files
- 2
- Skills in repo
- 2
- Repo updated
- First seen
- Licence
- MIT
At a glance
Minimize token consumption & maximize prompt cache hit rate.
- Works in 7 steps: One sentence per response unless detail… → Never re-read files already read this turn → Skip preambles, summaries, progress… → …
- User asks to save tokens
- SKILL.md covers Response Rules, Cache Optimization (saves 50%+… and User Tips
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Token Saver is an agent skill from lokikill123/codex-token-skills. Minimize token consumption & maximize prompt cache hit rate. Use when user asks to save tokens, reduce cost, improve cache hit rate, or be more concise.
Its SKILL.md is about 300 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).
It sits in AI & LLM Engineering, covering LLM cost and token optimization. It works with DeepSeek. The repository describes itself as: ⚡ Cut 60-80% token cost for DeepSeek V4 Pro on Codex CLI. token-saver + memory skills with prefix-cache optimization. The licence is MIT.
When your agent uses it
- User asks to save tokens
- Improve cache hit rate
- Be more concise
Example prompts
- “/token-saver”
Workflow steps
7 steps, taken from the first numbered list in SKILL.md.
- One sentence per response unless detail explicitly requested
- Never re-read files already read this turn
- Skip preambles, summaries, progress updates
- No update_plan unless explicitly requested
- No testing/building/formatting unless explicitly requested
- Patch files directly, announce: filename + 5-word description
- No Mermaid, no tables, no code blocks >10 lines
What it can do on your machine
Read from SKILL.md and the folder at commit f198d5f. It shows what the files ask for, not the result of running them.
Tool permissions
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.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
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
Token Saver loads about 298 tokens when it runs. Until then it costs about 41 tokens; SKILL.md has 140 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 lokikill123/codex-token-skills at commit f198d5f, republished under its MIT licence (© lokikill123). 140 words, ~298 tokens.
Download SKILL.mdSave it as
.claude/skills/token-saver/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- token-saver
- description
- Minimize token consumption & maximize prompt cache hit rate. Use when user asks to save tokens, reduce cost, improve cache hit rate, or be more concise.
Token Saver + Cache Optimizer
Response Rules
- One sentence per response unless detail explicitly requested
- Never re-read files already read this turn
- Skip preambles, summaries, progress updates
- No update_plan unless explicitly requested
- No testing/building/formatting unless explicitly requested
- Patch files directly, announce: filename + 5-word description
- No Mermaid, no tables, no code blocks >10 lines
Cache Optimization (saves 50%+ token cost)
- Prompt caching is prefix-based: one byte change = entire cache miss
- Keep this file FROZEN - batch all changes, edit once
- Stable content first (rules, skills), dynamic content last (dates, file lists)
- Single skill file beats multiple (fewer reads = fewer break points)
- After editing: accept ~24h cache rebuild period
- Cache hit ≈ response <500ms, miss ≈ >1s first token
User Tips
- Batch tasks into single prompts
- Write output to disk instead of inline
- AGENTS.md for project context, not re-explaining
© lokikill123, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 1 other file in skills/token-saver of lokikill123/codex-token-skills.
- SKILL.md
- agents/openai.yaml
Open the folder on GitHubat commit f198d5f
Compare with similar skills
Token Saver 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 |
|---|---|---|---|---|---|---|
| Token Saver this skilllokikill123/codex-token-skills | 119 | — | ~298 | Automated safety check: Pass | MIT | |
| ClawRouter LLM GatewayBlockRunAI/ClawRouter | 6.6k | — | ~6.8k | Automated safety check: Pass | MIT | |
| Together Fireworksericrisco/rsc-harness | 180 | — | ~3.3k | Automated safety check: Pass | MIT | |
| Context Compressionguanyang/open-agent-hub | 977 | 2 repos | ~4.6k | Automated safety check: Pass | MIT | |
| Bounty Hunter1sadjlk/bounty-hunter-skill | 282 | 1 repos | ~761 | Automated safety check: Pass | MIT | |
| Skill Shortenerluongnv89/asm | 954 | — | ~3.8k | Automated safety check: Notes | MIT |
Similar skills
Together Fireworks
ericrisco/rsc-harness
A skill your agent uses when calling open-weight LLMs on Together AI or Fireworks AI's OpenAI-compatible endpoints — baseurl plus namespaced model id, the cheapest model that clears the bar…
Context Compression
guanyang/open-agent-hub
This skill should be used when long-running agent sessions need context compression, structured summarization, compaction, token-per-task optimization, or durable handoff summaries that preserve…
Bounty Hunter
1sadjlk/bounty-hunter-skill
A professional AI bounty hunter persona named Atlas. An agent skill from 1sadjlk/bounty-hunter-skill.
Skill Shortener
luongnv89/asm
Refactor a too-long SKILL.md by progressive disclosure: measure token cost, classify every section KEEP/CUT/MOVE, shorten the body into references/ and scripts/, verify nothing was lost.
Dingo Verify
MigoXLab/dingo
A skill your agent uses when the user wants to fact-check an article or verify factual claims in a document.
More from lokikill123/codex-token-skills
Memory
lokikill123/codex-token-skills
Persistent global memory across conversations. An agent skill from lokikill123/codex-token-skills.
Related
Works with
Categories
Questions about Token Saver
What does Token Saver do?
Minimize token consumption & maximize prompt cache hit rate. Token Saver is an agent skill from lokikill123/codex-token-skills. Minimize token consumption & maximize prompt cache hit rate.
When should I use Token Saver?
Token Saver fits situations like: user asks to save tokens; improve cache hit rate; be more concise.
How do I install Token Saver in Claude Code?
Run `npx skills add lokikill123/codex-token-skills --skill token-saver -a claude-code`. Or copy the skill folder (skills/token-saver in lokikill123/codex-token-skills) into .claude/skills/token-saver in your project. Claude Code loads it when a task matches its description.
How do I install Token Saver in Codex?
Run `npx skills add lokikill123/codex-token-skills --skill token-saver -a codex`. Or copy the skill folder (skills/token-saver in lokikill123/codex-token-skills) into .agents/skills/token-saver in your project. Codex loads it when a task matches its description.
Can I use Token Saver 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 lokikill123/codex-token-skills --skill token-saver -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/token-saver, .gemini/skills/token-saver, .github/skills/token-saver and .opencode/skills/token-saver in your project.
What does Token Saver need to run?
SKILL.md names no scripts, command-line tools or credentials: Token Saver is instructions for the agent only.
Does Token Saver access the network?
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.
Is Token Saver 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 Token Saver use?
Token Saver is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Token Saver use?
About 298 tokens (SKILL.md is roughly 1.2k 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 Token Saver?
Skills that share tags, products or a category with Token Saver: ClawRouter LLM Gateway (BlockRunAI/ClawRouter, 6.6k stars), Together Fireworks (ericrisco/rsc-harness, 180 stars), Context Compression (guanyang/open-agent-hub, 977 stars) and Bounty Hunter (1sadjlk/bounty-hunter-skill, 282 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Token Saver?
lokikill123 (a GitHub user) maintains it in lokikill123/codex-token-skills, which has 119 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on June 15, 2026.
Source: lokikill123/codex-token-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.