raw-memory

raw-memory is a skill for Claude Code from Aicoo-Team/AICOO-Skills. It costs 154 tokens per session (1,677 once invoked), scanned A, original, MIT.

An automatic session recorder for Claude Code and Codex. When a session ends, it redacts secrets, encrypts and signs the record on the device, then uploads it as an immutable Aicoo note.

In plain words
What is it for?
Use it to enable, verify, and manage automatic capture of coding-agent sessions. Node.js 18 or newer and Gitleaks must be installed; browser authorization is used instead of an API key.
Why use it?
It removes the need to save and upload completed sessions manually while preventing upload when redaction, encryption, or signing cannot finish safely. It uses installed end-of-session hooks, not scheduled jobs.

Skill for Claude Code

Written for Claude Code: SessionEnd hook event. Also seen: mentions Claude Code; mentions Codex.

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

Good fit Use it to enable, verify, and manage automatic capture of coding-agent sessions. Node.js 18 or newer and Gitleaks must be installed; browser authorization is used instead of an API key.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/aicoo-team/aicoo-skills/raw-memory"><img src="https://agentmods.dev/badge/skills/aicoo-team/aicoo-skills/raw-memory.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 154 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,677 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 6 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium MCP Rug Pull · line 36
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 72
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 90
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 91
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 92
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 113
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
How audits are shown
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 $0.00154 $0.01677
Opus 5 $0.00077 $0.00839
Sonnet 5 $0.00031 $0.00335
Haiku 4.5 $0.00015 $0.00168

Measured 11d ago against content hash de6a29405c7c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

raw-memory scanned grade A with 1 finding 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 11d 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.

Makes network callslowCapability

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

curl -s "https://www.aicoo.io/api/v1/raw-memory/devices" \
skills/raw-memory/SKILL.md · 124 lines

How it starts

The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Raw Memory — automatic session capture

You help the user enable and manage the Raw Memory collector (@aicoo/raw-memory on npm). Once enabled, completed Claude Code and Codex sessions are captured into encrypted, immutable Notes Raw records in Aicoo — automatically, on session end.

Explain the model to the user in one or two lines when relevant:

  • A one-time enable authorizes the device and installs SessionEnd hooks for Claude Code and Codex.
  • From then on, every finished session is redacted (Gitleaks) → client-encrypted (AES-256-GCM) → signed → queued with retry → uploaded. No manual steps.
  • Capture fails closed: if secret scanning, encryption, or signing cannot complete, nothing is uploaded. An occasional missing session is the protection working, not a bug.
  • This skill is not a sync loop. Never schedule cron/loop jobs for Raw Memory — the installed hooks do all the work.

Prerequisites

node --version                      # need >= 18
gitleaks version 2>/dev/null || echo "MISSING gitleaks — brew install gitleaks (macOS)"

No API key is required: enable uses browser authorization. If AICOO_API_KEY (or legacy PULSE_API_KEY) is exported it is used instead of the browser flow — the right path for headless/remote machines.

Step 1: Enable

npx @aicoo/raw-memory enable

Optional flags: --name "<device name>" (default: hostname), --base-url <url> or AICOO_BASE_URL env (default https://www.aicoo.io/).

What happens, and what you must do:

  1. Browser authorization (when no API key env var is set): the CLI prints Open this URL to authorize Raw Memory: followed by a URL on stderr, and tries to auto-open the browser. Relay that URL to the user as a clickable link — the auto-open can fail. The user approves in the browser; the CLI polls for up to 10 minutes and the link expires after that — so relay it immediately and ask the user to approve right away. Do NOT send the user to register elsewhere or hunt for an API key.
  2. On success the CLI prints one line of JSON on stdout:

Read the full file on GitHub · 124 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. 11d ago First seen · 124 lines · 154 tokens per session scan A de6a29405c7c

Subscribe to this mod's changes

raw-memory is a skill published in the GitHub repository Aicoo-Team/AICOO-Skills (35 stars, last pushed 1mo ago), licensed MIT. It adds 154 tokens to every session and 1,677 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 1 finding (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