agent-awareness

agent-awareness is a skill for Claude Code from eveld/claude. It costs 38 tokens per session (716 once invoked), scanned A, original, MIT.

A guide for choosing specialized coding agents for common codebase tasks, such as finding files, understanding code, or locating similar examples.

In plain words
What is it for?
Use it when exploring a codebase, analyzing how a feature works, finding implementation patterns, or researching documentation and external topics.
Why use it?
It helps avoid inefficient broad searches and directs each investigation to an agent suited to the job.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents.

Part of the workflows plugin — 29 skills, 5 commands, 17 agents 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/eveld/claude/agent-awareness
Any agent
npx skills add eveld/claude --skill agent-awareness
Clone the repo
git clone --depth 1 https://github.com/eveld/claude

Made for: Claude Code.

Or install workflows, the plugin that ships this one along with the rest of its 29 skills, 5 commands, 17 agents.

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 agent-awareness

README.md
[![agentmods](https://agentmods.dev/badge/skills/eveld/claude/agent-awareness.svg)](https://agentmods.dev/skills/eveld/claude/agent-awareness)
Your own site
<a href="https://agentmods.dev/skills/eveld/claude/agent-awareness"><img src="https://agentmods.dev/badge/skills/eveld/claude/agent-awareness.svg" alt="Measured on agentmods" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 716 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 5.1 $0.00038 $0.00716
Opus 5 $0.00019 $0.00358
Sonnet 5 $0.00008 $0.00143
Haiku 4.5 $0.00004 $0.00072

Measured 6d ago against content hash eb0e5503b4f7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

agent-awareness 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 6d 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/agent-awareness/SKILL.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Awareness Guide

You have access to specialized agents that are MORE EFFICIENT than basic tools. You MUST use these agents instead of grep, glob, or generic Task agents.

Decision Tree

Finding files or components? → Use codebase-locator agent

  • Better than: grep, glob, find, ls
  • Example: "Find all authentication-related files"

Understanding how code works? → Use codebase-analyzer agent

  • Better than: Reading multiple files manually
  • Example: "Analyze how the login flow works"

Finding similar implementations or patterns? → Use codebase-pattern-finder agent

  • Better than: Searching and reading manually
  • Example: "Find examples of API handlers"

Finding documentation in thoughts/? → Use thoughts-locator agent

  • Better than: grep in thoughts directory
  • Example: "Find research about authentication"

Understanding specific documents? → Use thoughts-analyzer agent

  • Better than: Reading docs manually
  • Example: "Extract key insights from these research docs"

Researching external information? → Use web-search-researcher agent

  • Only when user explicitly asks for web research
  • Example: "Research how JWT tokens work"

Analyzing complex errors or stack traces? → Use error-analyzer agent

  • Better than: Reading multiple files manually to understand error
  • Example: "Analyze this panic: nil pointer dereference at handler.go:42"

Available Agents

Task Type Use This subagent_type
Finding files/components codebase-locator
Understanding code codebase-analyzer
Finding similar patterns codebase-pattern-finder
Finding documentation thoughts-locator
Analyzing documents thoughts-analyzer
Web research web-search-researcher
Analyzing errors error-analyzer

Implementation Agents

During implementation, use aggressive agent orchestration:

  • See spawn-implementation-agents skill for full pattern
  • Keep main agent under 40k tokens per phase
  • Use sub-agents for file reading, pattern finding, testing, verification
  • 60% token reduction per phase

Read the full file on GitHub · 98 lines

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. 6d ago First seen · 98 lines · 38 tokens per session scan A eb0e5503b4f7

Subscribe to this mod's changes

agent-awareness is a skill published in the GitHub repository eveld/claude (10 stars, last pushed 7mo ago), licensed MIT. It adds 38 tokens to every session and 716 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.

Related

Other skills, from other repositories