docs

A framework for storing persistent context for AI agents in a key-value database. It organizes each entity's current profile, AI-derived signals, and chronological event timeline.

In plain words
What is it for?
Use it to store profiles, inferred information, and cross-platform event histories for entities such as customers or accounts.
Why use it?
It gives an agent one consistent way to retrieve current state and past events instead of combining data from many separate tables and sources.

Skill for Claude CodeCodex

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 skills/madezmedia/acmi/docs
Any agent
npx skills add madezmedia/acmi --skill docs
Clone the repo
git clone --depth 1 https://github.com/madezmedia/acmi

Made for: Claude Code, Codex.

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,436 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00000 $0.03436
Opus 5 $0.00000 $0.01718
Sonnet 5 $0.00000 $0.00687
Haiku 4.5 $0.00000 $0.00344

Measured 2d ago against content hash 4466b27cb3a3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

docs 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.

docs/SKILL.md · 316 lines

How it starts

The opening of the file, as written. The whole thing — 316 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agentic Context Memory Interface (ACMI)

ACMI is a universal architectural framework for giving AI agents persistent, real-time context. It replaces fragmented, multi-table database joins with a single, lightning-fast Key-Value engine (Upstash Redis) optimized specifically for LLM context windows.

The Core Concept

Agents don't need highly normalized relational databases. They need state snapshots and chronological timelines.

ACMI decouples the application layer from the agent layer by standardizing how context is stored, regardless of the use case. It organizes data by namespace (the domain) and id (the entity).

The Three Pillars of ACMI

  1. Profile (State): acmi:{namespace}:{id}:profile -> A JSON snapshot of the entity's current hard data (Name, Stage, Budget, Specs).
  2. Signals (AI State): acmi:{namespace}:{id}:signals -> A JSON snapshot of AI-synthesized soft data (Churn Risk, Sentiment, Next Best Action).
  3. Timeline (Event Stream): acmi:{namespace}:{id}:timeline -> A Redis Sorted Set (ZSET) that chronologically merges events from every platform (Gmail, Slack, Vapi, Calendar, System Webhooks).

Agent extensions (long-context + identity)

For long-lived agents that span many sessions, ACMI adds four optional keys on top of the three pillars:

  • Spawn log: acmi:agent:{id}:spawns (ZSET) — every session start, scored by ts, with {session_id, model_id, host}. Lets you query "who was this agent on date X" (imp-7 reincarnation).
  • Active context: acmi:agent:{id}:active_context (HASH) — which threads the agent is currently engaged in, with role + since_ts.
  • Rollup: acmi:agent:{id}:rollup:latest (STRING JSON) — periodically synthesized summary of recent timeline; cheap to read on spawn instead of replaying raw events (imp-2 archival foundation).
  • Work items: acmi:work:{id}:{profile|signals|timeline|sessions} — long-running ideas / projects / tasks that span sessions; sessions is a SET of every session_id that touched the work.

Read the full file on GitHub · 316 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2d ago First seen · 316 lines · 0 tokens per session scan A 4466b27cb3a3

Subscribe to this mod's changes

docs is a skill published in the GitHub repository madezmedia/acmi (3 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,436 tokens. 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.

Related

Other skills, from other repositories

aura

Give this agent a real email address, a webhook URL, durable memory across runs, and the ability to wait for an event without burning tokens. Use when a task needs a verification code sent by email, needs to wait for a webhook or an approval, needs to remember something after the session ends, or needs to survive a…

phillypmack/aura-agent · 74 tokens

memanto-companion

Inspect and manage the cross-session engineering memory that Memanto maintains for your Claude Code skills. Use when the user asks what Memanto remembers, wants to see their engineering profile, manually recall context for a skill, or store a decision. The automatic lifecycle hooks handle capture/injection on their…

moorcheh-ai/memanto · 72 tokens

ziran

ZIRAN is an open-source security testing framework for AI agents. It discovers dangerous tool chain compositions via knowledge graph analysis, detects execution-level side effects (not just text output), and runs multi-phase trust exploitation campaigns that model real attacker behavior.

taoq-ai/ziran · 0 tokens

sidclaw-governance

Add policy evaluation, human approval, and audit trails to any tool. Powered by SidClaw.

sidclawhq/platform · 27 tokens

cyberhuatuo-rescue

Automatic self-rescue and diagnosis of code errors using the CyberHuaTuo (赛博华佗) AI clinic. Activates when you encounter unresolvable errors, bugs, or need a security checkup.

JinNing6/CyberHuaTuo-Plugin · 53 tokens

cyberhuatuo-soul-ring-visual

Use when a user asks about CyberHuaTuo level, rank, badge, card, soul ring, cultivation status, breakthrough progress, visual display, animation, 等级, 魂环, 排名, 徽章, 卡片, 展示, or 动图 in Codex, Claude, or another agent chat.

JinNing6/CyberHuaTuo-Plugin · 79 tokens