ashlr-codex-efficient-tools

ashlr-codex-efficient-tools is a skill for Claude Code, Codex from ashlrai/ashlr-plugin. It costs 40 tokens per session (206 once invoked), scanned A, original, MIT.

A workflow guide for using Ashlr tools to explore projects and run commands with less context. Ashlr is a tool set for compact file searches, reads, directory maps, shell commands, and usage statistics.

In plain words
What is it for?
Use it to orient yourself in a project, search and read files, run tests or type checks, inspect token savings, and review project structure.
Why use it?
It helps avoid repeated scans and overly long command output when working in a codebase.

Skill for Claude CodeCodex

Part of the ashlr plugin — 11 skills, 36 commands, 5 agents, 7 hooks, 1 MCP server shipped together

Install

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.

agentmods
npx agentmods add skills/ashlrai/ashlr-plugin/ashlr-codex-efficient-tools
Any agent
npx skills add ashlrai/ashlr-plugin --skill ashlr-codex-efficient-tools
Clone the repo
git clone --depth 1 https://github.com/ashlrai/ashlr-plugin

Made for: Claude Code, Codex.

Or install ashlr, the plugin that ships this one along with the rest of its 11 skills, 36 commands, 5 agents, 7 hooks, 1 MCP server.

Wrote 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.

agentmods badge for ashlr-codex-efficient-tools

README.md
[![agentmods](https://agentmods.dev/badge/skills/ashlrai/ashlr-plugin/ashlr-codex-efficient-tools.svg)](https://agentmods.dev/skills/ashlrai/ashlr-plugin/ashlr-codex-efficient-tools)
Your own site
<a href="https://agentmods.dev/skills/ashlrai/ashlr-plugin/ashlr-codex-efficient-tools"><img src="https://agentmods.dev/badge/skills/ashlrai/ashlr-plugin/ashlr-codex-efficient-tools.svg" alt="Measured on agentmods" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 206 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00040 $0.00206
Opus 5 $0.00020 $0.00103
Sonnet 5 $0.00008 $0.00041
Haiku 4.5 $0.00004 $0.00021

Measured 4d ago against content hash 584d9bafc295, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ashlr-codex-efficient-tools 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 4d 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.

skills/ashlr-codex-efficient-tools/SKILL.md · 18 lines

What it actually says

Ashlr Codex Efficient Tools

Use Ashlr MCP tools for high-volume context work:

  • Use ashlr__orient once before broad exploration when a genome exists.
  • Use ashlr__grep for search instead of repeated native scans.
  • Use ashlr__tree for compact directory maps.
  • Use ashlr__read for large files or files where only head/tail plus structure is needed.
  • Use ashlr__bash for verbose commands such as tests, typechecks, git log, and package installs.
  • Use ashlr__savings or ashlr stats --json to inspect token/cost savings.

Keep native tools for tiny files, exact patch application, or commands where raw output is short and important.

Changes

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.

  1. 4d ago First seen · 18 lines · 40 tokens per session scan A 584d9bafc295

Subscribe to this mod's changes

ashlr-codex-efficient-tools is a skill published in the GitHub repository ashlrai/ashlr-plugin (3 stars, last pushed 4d ago), licensed MIT. It adds 40 tokens to every session and 206 once invoked, about $0.0002 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.