build-memory

build-memory is a skill for Claude Code from Aicoo-Team/AICOO-Skills. It costs 104 tokens per session (1,418 once invoked), scanned B, original, MIT.

A skill for building an Aicoo agent’s long-term memory from selected files, documentation, repository history, or existing agent memory. It organizes this knowledge into files describing the owner, agent style, sharing rules, and lasting facts.

In plain words
What is it for?
Use it to create or refresh agent memory from a chosen local folder, repository, documents, or other supported context sources.
Why use it?
It turns real project and personal context into structured information the agent can use later, instead of leaving the agent with only generic instructions.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions CLAUDE.md; mentions AGENTS.md.

Part of the Aicoo Agent Skills plugin — 21 skills shipped together

Good fit Use it to create or refresh agent memory from a chosen local folder, repository, documents, or other supported context sources.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/aicoo-team/aicoo-skills/build-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.

Any agent
npx skills add Aicoo-Team/AICOO-Skills --skill build-memory
Clone the repo
git clone --depth 1 https://github.com/Aicoo-Team/AICOO-Skills

Made for: Claude Code.

Or install Aicoo Agent Skills, the plugin that ships this one along with the rest of its 21 skills.

Wrote 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.

agentmods badge for build-memory

README.md
[![agentmods](https://agentmods.dev/badge/skills/aicoo-team/aicoo-skills/build-memory/github.svg)](https://agentmods.dev/skills/aicoo-team/aicoo-skills/build-memory)
Your own site
<a href="https://agentmods.dev/skills/aicoo-team/aicoo-skills/build-memory"><img src="https://agentmods.dev/badge/skills/aicoo-team/aicoo-skills/build-memory/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for build-memory

Your own site · 80×15
<a href="https://agentmods.dev/skills/aicoo-team/aicoo-skills/build-memory"><img src="https://agentmods.dev/badge/skills/aicoo-team/aicoo-skills/build-memory.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 104 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,418 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00104 $0.01418
Opus 5 $0.00052 $0.00709
Sonnet 5 $0.00021 $0.00284
Haiku 4.5 $0.00010 $0.00142

Measured 10d ago against content hash 958110c610cf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade B, and why

build-memory scanned grade B with 2 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 10d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

cat CLAUDE.md AGENTS.md .claude/*.md 2>/dev/null | head -200

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s -X POST "https://www.aicoo.io/api/v1/accumulate" \
skills/build-memory/SKILL.md · 129 lines

How it starts

The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Build Memory — Turn Local Context Into Agent Memory

Your agent's memory is notes under /Memory. /Memory/Self/ holds the identity files that shape how the agent thinks and what it knows:

  • USER.md — who the owner is (role, stack, current work, expertise, goals)
  • COO.md — the agent's voice and operating style
  • POLICY.md — boundaries (what to share, what never to share)
  • MEMORY.md — long-term facts, projects, preferences, learned patterns

Building memory = reading the user's real context, synthesizing it, and writing these files. This is more powerful than a generic importer because you (the agent) can read the actual repo, git history, and docs and reason about what matters.

Requires being signed in — see the onboarding skill. Resolve the token first with the pack's scripts/aicoo-auth.sh (auto-refreshes): export AICOO_API_KEY="$(bash /path/to/aicoo-skills/scripts/aicoo-auth.sh)".


1. Ask where to build from

Don't guess the source — ask, then use what they pick:

"Where should I build your memory from? I can use: • this folder / repo (I'll read the code, docs, and git history) • a different local folder — tell me the path • Notion or Google Docs — I'll point you to the importer • just tell me about yourself — we skip files"

  • Local folder / repo / git → you (the agent) read it directly (step 2).
  • Notion / Google Docs → these connect through the web importer, which the skill can't call with an API token. Point the user to https://www.aicoo.io/import-workspace (Connect Notion / Google Drive → select docs → it extracts memory + generates USER.md/COO.md). Then come back and continue from step 4 to verify.
  • Just tell me → ask 3–4 questions (role, what they build, stack, how they want the agent to behave) and synthesize from that.

2. Scan the chosen local source

Pull the strongest available signals; adapt to what exists (use the folder the user named, or the current one):

cat README.md package.json pyproject.toml Cargo.toml 2>/dev/null | head -200
git log --oneline -30 2>/dev/null
git shortlog -sn 2>/dev/null | head
ls docs/ notes/ 2>/dev/null
cat CLAUDE.md AGENTS.md .claude/*.md 2>/dev/null | head -200

Read the full file on GitHub · 129 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. 10d ago First seen · 129 lines · 104 tokens per session scan B 958110c610cf

Subscribe to this mod's changes

build-memory is a skill published in the GitHub repository Aicoo-Team/AICOO-Skills (35 stars, last pushed 1mo ago), licensed MIT. It adds 104 tokens to every session and 1,418 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories