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/kioie/memex/agents-mdgit clone --depth 1 https://github.com/kioie/memexWhat 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 | $0.02112 | $0.02112 |
| Opus 5 | $0.01056 | $0.01056 |
| Sonnet 5 | $0.00422 | $0.00422 |
| Haiku 4.5 | $0.00211 | $0.00211 |
Grade A, and why
memex 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 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.
How it starts
The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent instructions (memex)
Guidance for AI coding agents working in this repository.
Commands
- Test all (CI / quick):
make testorgo test -race -short ./... - Test full scale:
make test-fullorgo test -race ./memex ./cmd/memex - Test integration:
make test-integration(MCP stdio subprocess;-tags=integration) - Test HTTP deploy:
make test-http(examples/http-deploy) - Run HTTP locally:
make run-http(Smithery deploy template) - Benchmarks:
go test -bench=. -benchmem ./memex - Test package:
go test -race -v ./memex - Test single:
go test -run TestName ./memex -v - Coverage:
make coverage/make coverage-check(≥75% onmemex/) - Sonar coverage:
make coverage-sonar/make coverage-sonar-check(≥80% onmemex/, used by SonarQube CI) - Lint:
make lint(requires golangci-lint) - Vulnerabilities:
make vulncheck(requires govulncheck) - Build CLI:
make build→bin/memex - Install:
make installorgo install ./cmd/memex - Run MCP server:
go run ./cmd/memex serve(stdio; for local MCP clients) - Doctor:
memex doctor— store path, schema version, memory counts, hybrid flag
Layout
memex/— importable library (github.com/kioie/memex/memex): SQLite store + MCP tool registrationcmd/memex/— CLI (memex serve,memex doctor)docs/— user-facing guides (Getting started, For AI agents)examples/— Cursor MCP configs, scoping cookbook, HTTP deployserver.json— MCP Registry metadatadocs/DISCOVERY.md,docs/SMITHERY.md— publishing guidesintegration/— MCP stdio subprocess tests (//go:build integration)
MCP layer
| Concern | Where | Notes |
|---|---|---|
| Store / FTS | memex/store.go |
No MCP imports |
| Hybrid / entities | memex/store_hybrid.go, store_entities.go, store_embed.go |
RRF fusion; MEMEX_HYBRID=1 |
| Tool handlers | memex/server.go |
tinymcp.RegisterTool, tinymcp.TextResult |
| MCP prompts | memex/prompts.go |
memory_guide, session_start, remember_fact |
| Stdio serve | cmd/memex/main.go |
server.Start() from tinymcp |
| In-memory tests | mcp_roundtrip_test.go |
server.RawServer().Connect(...) |
| Subprocess tests | integration/mcp_stdio_test.go |
Full CLI + stdio path |
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.
- 2d ago First seen · 137 lines · 2,112 tokens per session scan A 965f1e67a788
memex AGENTS.md is an instructions file published in the GitHub repository kioie/memex (1 stars, last pushed 9d ago), licensed MIT. It adds 2,112 tokens to every session, about $0.0106 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
pad CLAUDE.md
Instructions for PerpetualSoftware/pad, covering pad — development guide, what this is, architecture, build & install and quick iteration loop.
sverklo CLAUDE.md
Instructions for sverklo/sverklo, covering sverklo development, using sverklo tools, project structure and build & test.
brain-os AGENTS.md
Instructions for brainOS-HQ/brain-os, covering agents.md, context, the hard rule, tool routing (in order) and mutation safety.
brain-os copilot-instructions.md
Instructions for brainOS-HQ/brain-os, covering github copilot instructions, read this first, critical rules (also in agents.md) and known bugs (v0.4.1 fixes pending).
brain-os CLAUDE.md
Instructions for brainOS-HQ/brain-os, covering claude.md, agent instructions, build / dev, publish flow and project memory.
code-insights CLAUDE.md
Instructions for melagiri/code-insights, covering claude.md — code insights, project overview, development philosophy (critical), configuration hierarchy and documentation index.