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/setupnpx skills add huzaifa525/claude-code-optimizer --skill setupgit clone --depth 1 https://github.com/huzaifa525/claude-code-optimizerWhat 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 | $0.00026 | $0.01151 |
| Opus 5 | $0.00013 | $0.00575 |
| Sonnet 5 | $0.00005 | $0.00230 |
| Haiku 4.5 | $0.00003 | $0.00115 |
Grade A, and why
setup 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Set up Claude Code optimization for this project. Analyze the codebase and generate project-specific files.
Steps
1. Detect Project Stack
Read these files (skip if not found):
package.json→ Node.js/JS/TS projectpyproject.tomlorrequirements.txt→ Pythongo.mod→ GoCargo.toml→ RustGemfile→ Rubypom.xmlorbuild.gradle→ Javadocker-compose.yml→ Docker setupturbo.jsonorpnpm-workspace.yaml→ Monorepo
2. Find Entry Points
# Look for main/index files
Glob("**/index.{ts,js,tsx,jsx,py}")
Glob("**/main.{ts,js,py,go,rs}")
Glob("**/app.{ts,js,py}")
Glob("**/server.{ts,js}")
3. Find Route/API Registration
Grep("router|app\.(get|post|put|delete|use)|@(Get|Post|Controller)|urlpatterns|HandleFunc")
4. Detect Test Framework
Glob("**/*.test.*")
Glob("**/*.spec.*")
Glob("**/tests/**")
Glob("**/__tests__/**")
5. Detect Config Files
Glob("**/.eslintrc*")
Glob("**/.prettierrc*")
Glob("**/tsconfig.json")
Glob("**/ruff.toml")
Glob("**/.editorconfig")
6. Check Git Info
git log --oneline -5
git branch --show-current
7. Generate CLAUDE.md
Write CLAUDE.md to the project root with:
# Project: [detected name or $ARGUMENTS]
## Commands
- Build: [detected from package.json scripts or Makefile]
- Test: [detected test command]
- Lint: [detected lint command]
- Dev: [detected dev command]
## Entry Points
- [detected entry files with descriptions]
## Request Flow
[detected from framework: e.g., Client → Express → Middleware → Route → Controller → Service → DB]
## Data Flow
[detected from ORM/database setup]
## Key Decisions
- [fill in — prompt user to complete this section]
## Things That Look Wrong But Aren't
- [fill in — prompt user to complete this section]
## Conventions
- [detected from linter config, existing code patterns]
- [detected test conventions]
## Code Annotations
- Search `@claude-entry` for system entry points
- Search `@claude-pattern` for examples to follow
- Search `@claude-warning` for files not to modify
## Workflow
- New feature → /plan first, then /smart-edit to implement
- Bug fix → /debug-error or /fix-issue [number]
- Before editing unfamiliar code → /explore-area [dir]
- After all changes → /review then /commit
- Ready to merge → /create-pr
- New developer → /onboard
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.
- 2d ago First seen · 160 lines · 26 tokens per session scan A 6f5010cb4ac0
setup is a skill published in the GitHub repository huzaifa525/claude-code-optimizer (9 stars, last pushed 5mo ago), licensed MIT. It adds 26 tokens to every session and 1,151 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
throughline
Use when the user asks to use Throughline from Codex, continue or restore Throughline memory, export read-only handoff context for a local launcher, prepare a new Codex thread handoff, summarize a captured Codex session, or check whether the Throughline Codex Stop hook captured the current session. Hide long…
critical-review
Use when you want structured feedback on a plan or document before implementation.
save
Save all session progress to status tracking files. Use when you want to checkpoint work mid-session or before ending.
code-review
Use when you want a thorough code review of files, changes, or the entire project before shipping.
implement-batch
Use when you want to implement the next batch of a plan. Handles module implementation, testing, and validation.
audit-orchestrator
Universal Pre-Scan → Analysis → Optimization → Report orchestrator for ANY project type — web apps (Astro/SvelteKit/Next), infrastructure/homelab repos, CLI tools, libraries, backend services, monorepos, data/ML projects, docs. Self-detects project type and runs the matching analysis track. Session state lives in…