Borrowing it
Nothing to install: this file belongs to go-ports/echovault. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/go-ports/echovault/main/.claude/skills/local-memory/SKILL.mdgit clone --depth 1 https://github.com/go-ports/echovaultWrote 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.
[](https://agentmods.dev/skills/go-ports/echovault/local-memory)<a href="https://agentmods.dev/skills/go-ports/echovault/local-memory"><img src="https://agentmods.dev/badge/skills/go-ports/echovault/local-memory/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<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="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00030 | $0.00943 |
| Opus 5.5 | $0.00012 | $0.00377 |
| Sonnet 5.5 | $0.00006 | $0.00189 |
| Haiku 4.5 | $0.00003 | $0.00094 |
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 2mo 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.
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
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.
- 2mo ago First seen · 133 lines · 30 tokens per session scan A 3ae351baa42c
echovault is a skill published in the GitHub repository go-ports/echovault (4 stars, last pushed 4d ago), licensed MIT. It adds 30 tokens to every session and 943 once invoked, about $0.0001 per session on Opus 5.5. 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.
echovault compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| echovaultgo-ports/echovault | Skill | 4 | 4d ago | MIT | A | 30 | Claude Code |
| knowledge-ingestopenclaw/openclaw | Skill | 394k | yesterday | MIT | A | 80 | Claude Code, Codex |
| mem0-oss-to-platformmem0ai/mem0 | Skill | 68k | 2d ago | Apache-2.0 | A | 217 | Claude Code, Codex |
| forgetasgeirtj/system_prompts_leaks | Skill | 71k | 2d ago | CC0-1.0 | A | 74 | Claude Code, Codex |
| Cortexdanielmiessler/LifeOS | Skill | 20k | yesterday | MIT | A | 184 | Claude Code |
| memoryopensquilla/opensquilla | Skill | 7.1k | 6d ago | Apache-2.0 | A | 44 | Claude Code, Codex |
| ha-data-storesshiwenwen/hope-agent | Skill | 1.9k | yesterday | MIT | A | 115 | Claude Code, Codex |