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/davidmosiah/delx-memory/agents-mdgit clone --depth 1 https://github.com/davidmosiah/delx-memoryWrote 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/davidmosiah/delx-memory/agents-md)<a href="https://agentmods.dev/instructions/davidmosiah/delx-memory/agents-md"><img src="https://agentmods.dev/badge/instructions/davidmosiah/delx-memory/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 | $0.00416 | $0.00416 |
| Opus 5 | $0.00208 | $0.00208 |
| Sonnet 5 | $0.00083 | $0.00083 |
| Haiku 4.5 | $0.00042 | $0.00042 |
Grade A, and why
delx-memory 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 3d 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.
What it actually says
Agent Development Notes
Scope
This repo is a local-first persistent memory MCP server. It stores small key/value entries in SQLite for AI agents to share across sessions and across tools.
Commands
- Install:
npm ci - Typecheck:
npm run typecheck - Build:
npm run build - Fast smoke:
npm run smoke - Full gate:
npm test
Rules
- Never commit a
.sqlitefile, a.env, or any real user memory contents. - Keep the secret-detector patterns conservative on the KEY side (false positives are fine — users can pick a different key name) and high-specificity on the VALUE side (false positives there would block legitimate notes containing words like "token", "refresh", "secret").
- Every mutating tool must require
explicit_user_intent: true. Do not add a tool that mutates without it. - Tools that mutate must preserve idempotence where reasonable (e.g.
memory_forgetreturnsexisted: falserather than throwing on missing key). - Keep the per-value cap at 64 KB. This is a tripwire against blob-storage misuse.
- Tests must use ephemeral tmpdirs (
mkdtempSync) and clean up. Never let a test write to~/.delx-memory/. - No telemetry. No outbound network calls anywhere in the package except over the HTTP transport when the user opts in.
Agent-readiness checklist
Before publishing a new version:
npm testcleannpm pack --dry-run— confirm onlydist/, docs,examples/,server.json,llms.txtare packagedgit log -p | grep -iE 'token|secret|api_key'— confirm no real credentials slipped in- Bump
versioninpackage.json,server.json, andsrc/constants.tstogether - Update
CHANGELOG.md
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.
- 3d ago First seen · 34 lines · 416 tokens per session scan A d91cd0f112d2
delx-memory AGENTS.md is an instructions file published in the GitHub repository davidmosiah/delx-memory (1 stars, last pushed 5d ago), licensed MIT. It adds 416 tokens to every session, about $0.0021 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
personal-model AGENTS.md
Instructions for Intuition-Lab/personal-model, covering agents.md, runtime boundary, commands, pipeline and documentation map.
plur CLAUDE.md
Instructions for plur-ai/plur, covering claude.md, what is plur, development, package dependency and version bumps.
personal-model CLAUDE.md
Instructions for Intuition-Lab/personal-model: Read and follow AGENTS.md. It is the single agent orientation for this repository: Runtime boundary, commands, architecture, invariants, current documentation, privacy rules, and DCO workflow.
neurostack CLAUDE.md
Instructions for raphasouthall/neurostack, covering neurostack - claude code guide, quick reference, installation, mcp server (recommended for claude code) and openai-compatible api.
Vault-Agent-Memory AGENTS.md
Instructions for zycaskevin/Vault-Agent-Memory, covering agent instructions for vault agent memory, common install architecture, second decision: optional features, first decision: database scope and safe agent workflow.
codex-image-context-runtime AGENTS.md
Instructions for shixinnt/codex-image-context-runtime, covering agents.md, public boundary, runtime contract and changes.