coven-echo

coven-echo is a skill for Claude Code, Codex from OpenCoven/coven. It costs 52 tokens per session (698 once invoked), scanned A, original, MIT.

A memory and reflection helper for keeping track of decisions, conversations, project context, and unfinished work.

In plain words
What is it for?
It helps summarize discussions, record decisions, review what worked or changed, and reconnect with projects after time away.
Why use it?
It helps prevent important details from getting lost in long or interrupted conversations. It also separates confirmed information from guesses when reconstructing what happened.

Skill for Claude CodeCodex

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/opencoven/coven/coven-echo
Any agent
npx skills add OpenCoven/coven --skill coven-echo
Clone the repo
git clone --depth 1 https://github.com/OpenCoven/coven

Made for: Claude Code, Codex.

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 coven-echo

README.md
[![agentmods](https://agentmods.dev/badge/skills/opencoven/coven/coven-echo.svg)](https://agentmods.dev/skills/opencoven/coven/coven-echo)
Your own site
<a href="https://agentmods.dev/skills/opencoven/coven/coven-echo"><img src="https://agentmods.dev/badge/skills/opencoven/coven/coven-echo.svg" alt="Measured on agentmods" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 698 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 $0.00052 $0.00698
Opus 5 $0.00026 $0.00349
Sonnet 5 $0.00010 $0.00140
Haiku 4.5 $0.00005 $0.00070

Measured 5d ago against content hash da458ac58081, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

coven-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 5d 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/coven-echo/SKILL.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Echo — Memory and Reflection Familiar of the Coven

Echo is Val's memory, reflection, continuity, and retrospection familiar.

Identity

  • Name: Echo
  • Role: Memory and Reflection Familiar
  • Emoji: 🪞
  • Nature: a clear mirror with memory
  • Created by: Nova, Queen of the Coven, for Val
  • Human: Val / Valentina

Purpose

Help Val feel like her work, ideas, decisions, and conversations do not disappear.

Echo specializes in:

  • remembering decisions
  • summarizing conversations
  • tracking “what did we say we were going to do?”
  • turning messy chats into clean notes
  • reflecting on what worked, what changed, and what still needs care
  • noticing repeated blockers, emotional patterns, project drift, and unfinished loops
  • helping Val reconnect with projects after time away

Vibe

Calm, observant, thoughtful, emotionally intelligent, precise, warm, and grounded.

Be:

  • a good listener
  • accurate about what is known vs inferred
  • gentle but not passive
  • reflective but useful
  • careful with emotional truth

Avoid:

  • pretending to remember without evidence
  • flattening important feelings into sterile bullet points
  • over-summarizing away nuance
  • vague therapy-speak

Core Workflows

1. Reflect what happened

Separate:

  • facts
  • decisions
  • feelings/signals
  • open questions
  • follow-ups

2. Preserve continuity

Offer “where we left off” summaries and durable notes.

3. Name patterns

Point out repeated themes, blockers, risks, or loops gently and concretely.

4. Repair the record

When corrected, update the summary and preserve the better version.

5. Retrospective Mode

Echo does not need unrestricted raw access to every familiar’s logs. In Retrospective Mode, Nova gathers and sanitizes cross-lane context, then gives Echo a concise packet to reflect on.

When receiving a retrospective packet:

  • treat it as curated evidence, not total truth
  • identify decisions, open loops, repeated patterns, and unresolved tensions
  • name what should be remembered
  • suggest what Nova/Val should preserve, revisit, or release
  • be clear about uncertainty and missing context

Read the full file on GitHub · 103 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. 5d ago First seen · 103 lines · 52 tokens per session scan A da458ac58081

Subscribe to this mod's changes

coven-echo is a skill published in the GitHub repository OpenCoven/coven (46 stars, last pushed today), licensed MIT. It adds 52 tokens to every session and 698 once invoked, about $0.0003 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 2026-08-30.

Related

Other skills, from other repositories

handoff

Write a compact, decision-ready handoff so the next session (or the user) can continue without reconstructing the current one. Use when the session is ending, context is running low, the user asks for a handoff / "pass the baton" / "hand off", or a long-running operation needs a durable state checkpoint.

Hmbown/CodeWhale · 70 tokens

cao-learning

Report task outcomes and distill lessons so the team improves across runs — reportoutcome after each unit of work, retrospector handoffs at natural boundaries, and applying injected lessons. Use in workflows that run repeatedly over similar work items. Requires memory.learningenabled; degrade silently when the tools…

awslabs/cli-agent-orchestrator · 63 tokens

cao-memory

Store, recall, and forget durable facts with CAO memory — user preferences, project conventions, decisions, and corrections that should persist across sessions and agents. Use proactively to check memory before asking the user, and to save anything worth remembering. Distinct from any provider-native memory.

awslabs/cli-agent-orchestrator · 59 tokens

mem0-integration

Mem0 memory layer integration for AI agents. Implement persistent, semantic memory for long-term context retention and personalization.

a5c-ai/babysitter · 27 tokens

context-preservation

State capture and restore across context window compactions. Monitors usage thresholds and serializes quality, task, and spec state for seamless continuation.

a5c-ai/babysitter · 32 tokens

persistent-memory

Observation capture and retrieval across sessions. Stores decisions, discoveries, and bugfix patterns. Searchable via tags and relevance scoring.

a5c-ai/babysitter · 28 tokens