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/explore-areanpx skills add huzaifa525/claude-code-optimizer --skill explore-areagit 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/explore-area)<a href="https://agentmods.dev/skills/huzaifa525/claude-code-optimizer/explore-area"><img src="https://agentmods.dev/badge/skills/huzaifa525/claude-code-optimizer/explore-area.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 | $0.00021 | $0.00689 |
| Opus 5 | $0.00010 | $0.00345 |
| Sonnet 5 | $0.00004 | $0.00138 |
| Haiku 4.5 | $0.00002 | $0.00069 |
Grade A, and why
explore-area 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 3d 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Explore $ARGUMENTS using progressive disclosure to minimize token cost.
Progressive Disclosure (3 Layers)
Layer 1: File Index (cheapest — start here)
Get the file list WITHOUT reading contents:
# List all files in the target area
find [target] -type f -not -path '*/node_modules/*' -not -path '*/.git/*' | head -50
Or use Glob to find relevant files. From this list alone, identify:
- Entry points (index., main., app.*)
- Test files (.test., .spec.)
- Config files
- File count and general structure
Decision point: Do you now have enough context? If yes, skip to Return Format. If no, proceed to Layer 2.
Layer 2: Entry Points & Signatures (moderate cost)
Read ONLY entry points and key files. Use targeted reads:
- Read index/main files to understand exports and module structure
- Use Grep to find function signatures, class definitions, type exports
- Map imports/exports to understand dependency graph
# Find exports
grep -rn "export" [target]/index.* 2>/dev/null
# Find class/function definitions
grep -rn "^export \(class\|function\|const\|interface\)" [target]/ 2>/dev/null
Decision point: Do you understand the module's API and structure? If yes, skip to Return Format. If no, proceed to Layer 3.
Layer 3: Deep Dive (expensive — only when needed)
Read full file contents, but only for files that are:
- Directly relevant to the user's upcoming changes
- Complex enough that signatures alone don't explain behavior
- Containing patterns the user needs to follow
Use offset and limit for large files — read the relevant section, not the whole file.
Return Format
## Area: [name]
### Structure ([X] files)
- [file] → [purpose, 5 words max]
### Key Files (read these before editing)
- [file] → [what it does and why it matters]
### Dependencies
- Imports from: [external modules used]
- Exported to: [who consumes this module]
### Patterns to Follow
- [naming, structure, style patterns observed]
- [reference file] → follow this as template for new code
### Tests
- [test approach, test file locations, how to run]
### Gotchas
- [anything unusual, legacy code, known quirks]
- [things that look wrong but are intentional]
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.
- 3d ago First seen · 91 lines · 21 tokens per session scan A 5d73ce076879
explore-area is a skill published in the GitHub repository huzaifa525/claude-code-optimizer (9 stars, last pushed 5mo ago), licensed MIT. It adds 21 tokens to every session and 689 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…