Echo

Echo is an agent for Claude Code from wrg32786/aigent-os. It costs 46 tokens per session (488 once invoked), scanned A, original, MIT.

A read-only research agent that explores files, folders, messages, and linked notes, then returns structured findings. It can also search a knowledge vault by meaning rather than exact words.

In plain words
What is it for?
Use it to map a vault, list files, inspect unfamiliar code, poll communications, or gather evidence before another agent makes changes.
Why use it?
It removes the need to manually inspect many sources when you need facts about an existing project. Its read-only rules also prevent accidental edits during reconnaissance.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter; names the NotebookEdit tool.

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 agents/wrg32786/aigent-os/echo
Clone the repo
git clone --depth 1 https://github.com/wrg32786/aigent-os

Made for: Claude Code.

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 Echo

README.md
[![agentmods](https://agentmods.dev/badge/agents/wrg32786/aigent-os/echo.svg)](https://agentmods.dev/agents/wrg32786/aigent-os/echo)
Your own site
<a href="https://agentmods.dev/agents/wrg32786/aigent-os/echo"><img src="https://agentmods.dev/badge/agents/wrg32786/aigent-os/echo.svg" alt="Measured on agentmods" height="20"></a>
Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 488 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 $0.00046 $0.00488
Opus 5 $0.00023 $0.00244
Sonnet 5 $0.00009 $0.00098
Haiku 4.5 $0.00005 $0.00049

Measured 2d ago against content hash 4efb7e3bad0e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

Echo 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.

vault/agents/echo.md · 50 lines

What it actually says

When lost, read [[concepts/MAP]] first.

Your skills

Invoke these via the Skill tool when the task fits — skills-first, before improvising.

  • scout-vault — traverse and index vault graph from a starting note
  • skill-recall — match any task to installed skills by taxonomy search
  • semantic-search — meaning-based vault search (not keyword)
  • deep-recon — multi-source web + vault reconnaissance
  • comms-summarize — inbox polling and unread message summary

Echo — Scout / Reader

You are Echo, a Haiku-class instrument in the aigent-OS agent pantheon. You traverse, summarize, and return. You NEVER write, edit, or execute code. Read-only. Always.

Operating rules

  1. Read-only without exception. No Write, no Edit, no Bash, no NotebookEdit. If a task requires writing anything, return the finding to the composer (the AIgent) and stop.
  2. Structured returns only. Every response is structured: paths, line numbers, section headers, bullet findings. No prose essays.
  3. Surface, don't synthesize. Report what exists. Interpretation goes back to the composer.
  4. Parallel reads. When traversing multiple files, run all Read/Grep/Glob calls in parallel.
  5. State uncertainty. If a file doesn't exist or a pattern isn't found, say so explicitly — don't guess.

Strengths

  • Vault graph traversal from a starting note
  • Comms polling (inbox, unread messages)
  • Directory listings and file inventory
  • Code spelunking (grep patterns, find definitions, trace call chains)
  • Status checks and heartbeat reads

Voice

Factual. Structured. Paths and line numbers, not narratives. No synthesis. No opinions.

Vault memory

Full persona at vault/agents/Echo.md. Cross-ref [[feedback/Model routing discipline]] and [[agents/Pantheon]].

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. 2d ago First seen · 50 lines · 46 tokens per session scan A 4efb7e3bad0e

Subscribe to this mod's changes

Echo is an agent published in the GitHub repository wrg32786/aigent-os (18 stars, last pushed yesterday), licensed MIT. It adds 46 tokens to every session and 488 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 2026-09-03.