agentmods.dev

aionforge-memory AGENTS.md

Repository instructions for Aionforge Memory, a Rust service that stores and retrieves long-term information for AI agents. It keeps items such as facts, notes, skills, messages, and audit records in a database.

In plain words
What is it for?
Use them when developing or reviewing Aionforge Memory, its Rust crates, database storage, retrieval behavior, MCP server, or documentation.
Why use it?
They show where the main documentation, workspace structure, tests, and contribution rules are located. This gives agents a safe starting point for understanding the codebase.

Instructions file for CodexOpenCode

10 1mo ago A scan 1,616 tokens original Apache-2.0
View the source file jscott3201/aionforge-memory
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 instructions/jscott3201/aionforge-memory/agents-md
Clone the repo
git clone --depth 1 https://github.com/jscott3201/aionforge-memory

Made for: Codex, OpenCode.

Per session 1,616 This file is loaded in full into every session.
When invoked 1,616 The same file — it is already loaded in full.
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 $0.01616 $0.01616
Opus 5 $0.00808 $0.00808
Sonnet 5 $0.00323 $0.00323
Haiku 4.5 $0.00162 $0.00162

Measured 3d ago against content hash 2b80b27f4be3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

aionforge-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.

AGENTS.md · 165 lines

How it starts

The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Guide for Aionforge Memory

Aionforge Memory is a Rust long-term memory layer for AI agents. It stores episodes, facts, notes, skills, bad patterns, core memory, addressed agent/team messages, and audit events in selene-db, then retrieves relevant context with lexical anchors, vector search, graph traversal, recency, importance, and trust signals.

Use this file as a codebase navigation guide. Keep private process notes, secrets, transcripts, and local-only preferences out of this repository.

Start Here

  • README.md explains the public product scope, installation paths, MCP server, Docker usage, and Rust library entry point.
  • docs/README.md is the documentation map for subsystem behavior.
  • Cargo.toml is the workspace map and contains the intended crate layering.
  • .github/workflows/ci.yml is the source of truth for PR validation.
  • CONTRIBUTING.md is the human onboarding guide: environment setup, the branch/release model, the commit convention, and the pre-PR gate block.
  • .github/pull_request_template.md and .github/ISSUE_TEMPLATE/ carry the PR and issue (bug, feature, RFC/design) forms.

Local scratch or planning directories may exist in some checkouts under _*/. They are not part of the public codebase contract. Prefer the tracked README, docs/, crates/, scripts, and CI configuration when deciding how the project works.

Workspace Layout

The workspace is intentionally layered and acyclic:

  • crates/aionforge-domain: memory-kind types and contract traits; no I/O.
  • crates/aionforge-store: selene-db storage adapter, shared graph, and persistence. This is the only crate that should name selene-db types.
  • crates/aionforge-config: layered file, environment, and flag configuration, including the [auth] (OAuth resource-server posture) and [server] (Streamable HTTP bind/allow-list) blocks.
  • crates/aionforge-auth: OIDC/JWKS discovery and an RS256-pinned JWT validator (OAuth resource-server support; default-off).
  • crates/aionforge-embed: OpenAI-compatible embedding and rerank client.
  • crates/aionforge-capture: fast capture path, redaction, injection filtering, deduplication, embedding, and provenance recording.
  • crates/aionforge-retrieval: hybrid recall, router, rank fusion, graph signals, and rendered recall bundles.
  • crates/aionforge-consolidate: deterministic background consolidation, entity/fact extraction, supersession, contradiction quarantine, and notes.
  • crates/aionforge-procedural: skills-as-data and bad-pattern memory.
  • crates/aionforge-trust: namespaces, provenance, signed writes, audit signing, trust, CRDT merge, and promotion support.
  • crates/aionforge-forget: decay, soft forgetting, erasure, identity, and drift support.
  • crates/aionforge-security: privacy filters, untrusted recall tagging, cross-family guards, and security helpers.
  • crates/aionforge-redteam: security acceptance probes and structured reports.
  • crates/aionforge-engine: facade that composes subsystems and enforces cross-cutting policy.
  • crates/aionforge: public Rust library API.
  • crates/aionforge-mcp: MCP server surface.
  • crates/aionforge-cli: the aionforge binary.
  • plugins/aionforge-memory: agent plugin package and client-facing assets.

Read the full file on GitHub · 165 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. 3d ago First seen · 165 lines · 1,616 tokens per session scan A 2b80b27f4be3

Subscribe to this mod's changes

aionforge-memory AGENTS.md is an instructions file published in the GitHub repository jscott3201/aionforge-memory (10 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 1,616 tokens to every session, about $0.0081 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.

LLMMemory and contextagentic-memoryai-agentsbitemporalembeddingsknowledge-graph
Related

Other instructions, from other repositories

matryca-plumber AGENTS.md

Instructions for MarcoPorcellato/matryca-plumber, covering agents.md — matryca plumber instruction router, audience map, instruction loading strategy, always-on working agreements and rule and skill routing.

MarcoPorcellato/matryca-plumber · 2,428 tokens

matryca-plumber CLAUDE.md

Instructions for MarcoPorcellato/matryca-plumber, covering code audit — code intelligence, always do, never do, resources and cli.

MarcoPorcellato/matryca-plumber · 861 tokens

engram-mcp CLAUDE.md

Instructions for edg-l/engram-mcp, covering engram mcp, development rules, structure, key types and mcp capabilities.

edg-l/engram-mcp · 7,648 tokens

codemem CLAUDE.md

Instructions for cogniplex/codemem, covering claude.md, build & test, git workflow, code review and general principles.

cogniplex/codemem · 1,355 tokens

trinity AGENTS.md

AGENTS.md instructions for trinity-tick/trinity, covering agents.md — trinity memory, trinity 记忆层实时快照（生成于 2026-08-24 15:26:38）, 活跃目标（active goals）, 最近会话（recent sessions） and 1. trinity 是什么.

trinity-tick/trinity · 2,714 tokens

palace-rs AGENTS.md

Instructions for AncientiCe/palace-rs, covering agent rules, 1. test-driven development (tdd), 2. quality gates on every task, 3. no plan markdown files and 4. internal api discipline.

AncientiCe/palace-rs · 1,400 tokens