echovault

echovault is a skill for Claude Code, Codex from go-ports/echovault. It costs 30 tokens per session (943 once invoked), scanned A, original, MIT.

A local memory system for coding agents that carries useful context between sessions.

In plain words
What is it for?
Keeping project knowledge across coding sessions, including previous decisions, problems, and learned information.
Why use it?
It prevents the agent from losing past decisions, bugs, and project context when a session ends. It requires retrieving memories at the start and saving them before the end.

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/go-ports/echovault/local-memory
Any agent
npx skills add go-ports/echovault --skill local-memory
Clone the repo
git clone --depth 1 https://github.com/go-ports/echovault

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 echovault

README.md
[![agentmods](https://agentmods.dev/badge/skills/go-ports/echovault/local-memory.svg)](https://agentmods.dev/skills/go-ports/echovault/local-memory)
Your own site
<a href="https://agentmods.dev/skills/go-ports/echovault/local-memory"><img src="https://agentmods.dev/badge/skills/go-ports/echovault/local-memory.svg" alt="Measured on agentmods" height="20"></a>
Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 943 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 $0.00030 $0.00943
Opus 5 $0.00015 $0.00472
Sonnet 5 $0.00006 $0.00189
Haiku 4.5 $0.00003 $0.00094

Measured 4d ago against content hash 3ae351baa42c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

echovault 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.

.claude/skills/local-memory/SKILL.md · 133 lines

How it starts

The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.

EchoVault — Agent Memory System

You have persistent memory across sessions. USE IT.

IMPORTANT: Prefer the EchoVault MCP tools (memory_context / memory_search / memory_save / memory_replace / memory_delete) over invoking the memory CLI.

Session start — MANDATORY

Before doing ANY work, retrieve context from previous sessions by calling the MCP tool memory_context.

project is required.

{
  "project": "<project-name>",
  "limit": 10
}

If the user's request relates to a specific topic, also call memory_search.

{
  "query": "<relevant terms>",
  "project": "<project-name>",
  "limit": 5
}

If you discover an existing memory is wrong or outdated, prefer memory_replace (overwrite) over memory_save (dedup/merge).

Do not skip this step. Prior sessions may contain decisions, bugs, and context that directly affect your current task.

Session end — MANDATORY

Before ending your response to ANY task that involved making changes, debugging, deciding, or learning something, you MUST call the MCP tool memory_save. This is not optional. If you did meaningful work, save it.

title, what, and project are required.

{
  "project": "<project-name>",
  "title": "Short descriptive title (max 60 chars)",
  "what": "1-2 sentences: what happened / what was decided",
  "why": "Reasoning behind it (optional)",
  "impact": "What changed as a result (optional)",
  "tags": ["tag1", "tag2"],
  "category": "<category>",
  "related_files": ["path/to/file1", "path/to/file2"],
  "details": "Full context for a future agent with zero context. Prefer: Context, Options considered, Decision, Tradeoffs, Follow-up."
}

Categories: decision, bug, pattern, learning, context.

What to save

You MUST save when any of these happen:

  • You made an architectural or design decision
  • You fixed a bug (include root cause and solution)
  • You discovered a non-obvious pattern or gotcha
  • You set up infrastructure, tooling, or configuration
  • You chose one approach over alternatives
  • You learned something about the codebase that isn't in the code
  • The user corrected you or clarified a requirement

Read the full file on GitHub · 133 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. 4d ago First seen · 133 lines · 30 tokens per session scan A 3ae351baa42c

Subscribe to this mod's changes

echovault is a skill published in the GitHub repository go-ports/echovault (4 stars, last pushed 11d ago), licensed MIT. It adds 30 tokens to every session and 943 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

media-ingest

Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.

garrytan/gbrain · 52 tokens

mem0-oss-to-platform

Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…

mem0ai/mem0 · 273 tokens

Cortex

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…

danielmiessler/LifeOS · 196 tokens

agent-memory

../../../engineering/agent-memory/skills/agent-memory/SKILL.md.

alirezarezvani/claude-skills · 0 tokens

memory

Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.

opensquilla/opensquilla · 44 tokens

ha-data-stores

Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…

shiwenwen/hope-agent · 115 tokens