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.
npx agentmods add instructions/go-ports/echovault/agents-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/instructions/go-ports/echovault/agents-md)<a href="https://agentmods.dev/instructions/go-ports/echovault/agents-md"><img src="https://agentmods.dev/badge/instructions/go-ports/echovault/agents-md.svg" alt="Measured on agentmods" 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 | $0.04651 | $0.04651 |
| Opus 5 | $0.02325 | $0.02325 |
| Sonnet 5 | $0.00930 | $0.00930 |
| Haiku 4.5 | $0.00465 | $0.00465 |
Grade A, and why
echovault AGENTS.md 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.
How it starts
The opening of the file, as written. The whole thing — 590 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides guidance to AI coding agents when working with code in this repository.
Project Overview
EchoVault is a local memory system for coding agents. It persists decisions, bugs, patterns, and context across sessions in a SQLite database (with FTS5 full-text search and sqlite-vec vector embeddings) and exposes them through a CLI binary (memory) and an MCP (Model Context Protocol) stdio server.
Build & Development Commands
All builds, tests, and linting MUST be run through the Makefile. Do NOT run go build, go test, golangci-lint, or other tools directly — always use the corresponding make target.
# Build for current platform (optimised)
make build
# Build without cross-compile flags (fastest local build)
make build-native
# Run all tests (CGO_CFLAGS set automatically for FTS5)
make test
# Run a single test (exception: no make target, use go test directly)
CGO_CFLAGS="-DSQLITE_ENABLE_FTS5" go test -run TestName ./path/to/package
# Run all linters (nolintguard, qtlint, golangci-lint) — must pass before commit
make lint
# Run linters with auto-fix
make lint-fix
# Install/tidy dependencies
make deps
# Clean build artifacts
make clean
# See all available targets
make help
CGO Requirements
This project requires CGO throughout — CGO_ENABLED=1 is always set by the Makefile. Two C-backed SQLite extensions are in use:
github.com/mattn/go-sqlite3— SQLite driver compiled via CGOgithub.com/asg017/sqlite-vec-go-bindings— vector similarity search extension via CGO
When running tests directly (not via make test), always set:
CGO_CFLAGS="-DSQLITE_ENABLE_FTS5" go test ./...
Omitting CGO_CFLAGS="-DSQLITE_ENABLE_FTS5" causes "no such module: fts5" errors at runtime.
Code Style (golangci-lint)
The following rules are enforced by .golangci.yml. Code MUST comply to pass CI.
Import Organization (gci formatter)
Imports must be organized in three groups, separated by blank lines:
- Standard library
- Third-party packages
- Local packages (
github.com/go-ports/echovault/...)
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.
- 4d ago First seen · 590 lines · 4,651 tokens per session scan A 94975ab844ff
echovault AGENTS.md is an instructions file published in the GitHub repository go-ports/echovault (4 stars, last pushed 11d ago), licensed MIT. It adds 4,651 tokens to every session, about $0.0233 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.
Other instructions, from other repositories
aeon CLAUDE.md
Instructions for aeonfun/aeon, covering aeon, how aeon works, strategy, voice and soul file hierarchy (read in this order).
cognirepo CLAUDE.md
Claude Code instructions for ashlesh-t/cognirepo, covering claude.md, key rules, session start sequence (run in this order), behavioral confirmation rule and personas (cognirepo-402, cognirepo-403).
wayland-core copilot-instructions.md
Copilot instructions for FerroxLabs/wayland-core, covering ijfw rules, output discipline, memory routing, context discipline and cross-audit.
mcp-structured-memory CLAUDE.md
Claude Code instructions for nmeierpolys/mcp-structured-memory, a project described as: Structured Memory MCP Server.
inkwell-memory CLAUDE.md
Instructions for veronchenko/inkwell-memory, covering claude.md — inkwellmemory, layout, multi-tenant mode (inkwellmultitenant=1), conventions and testing.
RNR-Enhanced-Cognee AGENTS.md
AGENTS.md instructions for vincentspereira/RNR-Enhanced-Cognee, covering rnr enhanced cognee implementation for codex, critical requirements, 1. ascii-only output (no unicode encoding), 2. dynamic categories (no hardcoded categories) and 3. standard memory mcp interface.