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 agentmods add skills/huzaifa525/claude-code-optimizer/optimize-tokensnpx skills add huzaifa525/claude-code-optimizer --skill optimize-tokensgit clone --depth 1 https://github.com/huzaifa525/claude-code-optimizerWrote 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/huzaifa525/claude-code-optimizer/optimize-tokens)<a href="https://agentmods.dev/skills/huzaifa525/claude-code-optimizer/optimize-tokens"><img src="https://agentmods.dev/badge/skills/huzaifa525/claude-code-optimizer/optimize-tokens.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 | $0.00025 | $0.00477 |
| Opus 5 | $0.00013 | $0.00238 |
| Sonnet 5 | $0.00005 | $0.00095 |
| Haiku 4.5 | $0.00003 | $0.00048 |
Grade A, and why
optimize-tokens 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 5d 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
Search for the latest token optimization strategies and analyze this project's setup.
Steps
1. Web Research
Search for the latest tips:
- "Claude Code token optimization 2026"
- "Claude Code reduce token usage"
- "Claude Code cost saving tips"
- "Claude Code .claudeignore best practices"
Summarize the top 5-10 NEW tips found online.
2. Analyze Current Project
Check CLAUDE.md:
- Does it exist? How many lines?
- Is it under 200 lines?
- Does it have entry points, flow diagrams, decisions?
Check .claudeignore:
- Does it exist?
- Does it cover: node_modules, dist, lock files, binary assets?
Check .claude/rules/:
- Are rules path-scoped?
- Are there rules loading unnecessarily?
Check .claude/skills/:
- Are exploration skills using
context: fork? - Are side-effect skills using
disable-model-invocation: true?
Check MCP servers:
- How many tool definitions are loaded?
- Any unused servers?
Check settings:
- Is MAX_THINKING_TOKENS capped?
- What model is being used?
3. Output Report
## Token Optimization Report
### Current Setup Score: [X/10]
### What's Good
- [things already optimized]
### Quick Wins (do now)
| Action | Estimated Savings | Effort |
|--------|------------------|--------|
| [action] | [X%] | [Low/Med/High] |
### Latest Tips from Web
- [tip 1 — source]
- [tip 2 — source]
- [tip 3 — source]
### Recommended Changes
1. [specific change with file path]
2. [specific change with file path]
3. [specific change with file path]
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.
- 5d ago First seen · 75 lines · 25 tokens per session scan A e1e78c82e699
optimize-tokens is a skill published in the GitHub repository huzaifa525/claude-code-optimizer (9 stars, last pushed 5mo ago), licensed MIT. It adds 25 tokens to every session and 477 once invoked, about $0.0001 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.
Other skills, from other repositories
om-auto-publish-pr
Publish pkg.pr.new package previews for a same-repository Open Mercato PR by dispatching the Package Previews GitHub Actions workflow with gh. Use when a maintainer asks to publish, republish, or trigger a PR package preview. Does not publish npm snapshots.
codex-skin-pack-installer
Install Codex themes and Codex skin packs with npx skills. Use this skill when a user wants Codex to find, download, validate, apply, switch, remix, or restore Codex desktop themes such as caishen-readable, caishen-lite, mythic-guardian-noir, global-founder-bright, export-night, or caishen-max. It stages verified…
om-code-review
Open Mercato repo-local extension of the shared om-code-review skill (installed from open-mercato/skills into .agents/skills/). Adds the Docker-vs-local gate runner detection, the template parity gate, Open Mercato layer classification, and the repo's severity taxonomy on top of the shared workflow.
om-build-workflow
Build or extend standalone business workflows, activities, event triggers, durable user tasks, compensation, output paths, idempotency, and live progress. Use for "add workflow", "custom activity", "CALLAPI", "approval task", "workflow progress", or "zbuduj workflow".
memstack-automation-n8n-workflow-builder
Use this skill when the user says 'n8n workflow', 'build a workflow', 'automation workflow', 'connect services', or needs visual workflow design with node mapping, data transformations, and error handling for n8n. Do NOT use for standalone webhook endpoints or cron jobs.
styleseed
Route a StyleSeed request to exactly one first workflow after resolving the current artifact boundary. Use when the user asks generally for StyleSeed help rather than invoking one specific ss- skill.