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/arkaaiadmin/agentic-memory/agents-mdgit clone --depth 1 https://github.com/ArkaAiAdmin/Agentic-MemoryWhat 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 | $0.05809 | $0.05809 |
| Opus 5 | $0.02905 | $0.02905 |
| Sonnet 5 | $0.01162 | $0.01162 |
| Haiku 4.5 | $0.00581 | $0.00581 |
Grade A, and why
Agentic-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 yesterday.
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 — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — agentic-memory (Maintainer Edition)
You maintain the agentic-memory codebase. All commands run from the repo root.
If you are an agent using the system (not maintaining it): read AGENT_CONTRACT.md (5 rules) + docs/AGENT_QUICKSTART.md. Stop there.
System at a Glance
Live counts (schema version, tool surface, cron/hooks, test files, LOC) live in
docs/_meta.json (machine-enforced by verify_doc_meta.py). Architecture:
docs/architecture.md. MCP tool surface: docs/MCP_SURFACE.md. For agents
using the system: AGENT_QUICKSTART.md.
Session Protocol
| # | When | Action |
|---|---|---|
| 1 | Every session start | agentic-memory_memory_session_start(query="<subsystem>") — anchors a real DB-backed session (writes .current_session.json with the authoritative id) and returns the briefing. The harness hook does this automatically when wired; the verb is the fallback and is self-sufficient. |
| 2 | Before any task | agentic-memory_memory_search(query="<topic>") |
| 3 | After bug/decision fix | agentic-memory_memory_save(category="lessons" or "decisions") |
| 4 | After test/index/cron op | agentic-memory_memory_advanced(operation="auto_save_status") — only when cron is down or immediate results are needed (Rule 21) |
| 5 | Before ending session | agentic-memory_memory_save(category="sessions"), then memory_session_end(summary=...). No session handle needed — end falls back to the state file, then to the most recent active session for this agent; with nothing active it returns a structured no-op instead of erroring. |
Minimum every session: #1 + #5. Save context-rich projects notes (importance=4) at milestones — useful weeks later, not log lines.
Session persistence requires [session_memory] enabled = true (on since 2026-08-22). Skill extraction vetoes eval/test residue ids (skill_extractor.is_junk_memory_id) and strips YAML frontmatter; sweep with scripts/purge_junk_skills.py if junk ever returns.
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.
- yesterday First seen · 221 lines · 5,809 tokens per session scan A 0b67ed884c1d
Agentic-Memory AGENTS.md is an instructions file published in the GitHub repository ArkaAiAdmin/Agentic-Memory (0 stars, last pushed yesterday), licensed Apache-2.0. It adds 5,809 tokens to every session, about $0.0290 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
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
buildNext
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
Instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
Instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.