absorb

absorb is a command for Claude Code from robotaitai/project-bedrock. It costs 0 tokens per session (355 once invoked), scanned A, original, MIT.

A command that reads a file or folder and stores confirmed project knowledge in the project's vault. The vault is a set of files used as durable project notes and history.

In plain words
What is it for?
Use it to absorb architecture notes, decisions, history, and API or component documentation into the appropriate project records.
Why use it?
It turns useful information from existing documents into organized project memory instead of leaving it buried in source files.

Command for Claude Code

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 commands/robotaitai/project-bedrock/absorb
Clone the repo
git clone --depth 1 https://github.com/robotaitai/project-bedrock

Made for: Claude Code.

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 absorb

README.md
[![agentmods](https://agentmods.dev/badge/commands/robotaitai/project-bedrock/absorb.svg)](https://agentmods.dev/commands/robotaitai/project-bedrock/absorb)
Your own site
<a href="https://agentmods.dev/commands/robotaitai/project-bedrock/absorb"><img src="https://agentmods.dev/badge/commands/robotaitai/project-bedrock/absorb.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 355 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 $0.00355
Opus 5 $0.00000 $0.00178
Sonnet 5 $0.00000 $0.00071
Haiku 4.5 $0.00000 $0.00036

Measured 4d ago against content hash 3e69e298f45d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

absorb 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 4d 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.

.claude/commands/absorb.md · 35 lines

What it actually says

Absorb knowledge from a file or folder into the project vault.

Target: use whatever path the user specified after /absorb. If no path was given, ask: "Which file or folder should I absorb?"

Steps:

  1. Identify the target

    • If a file: read it
    • If a folder: list all .md files inside it and read each one
  2. For each file, determine what kind of knowledge it contains and route accordingly:

    • Architecture / design notes → find or create ./bedrock/Memory/<topic>.md
    • Decisions / ADRs → append structured entries to ./bedrock/Memory/decisions.md
    • Changelog / history entries → append events to ./bedrock/History/events.ndjson
    • API / component docs → find or create the relevant Memory branch note
    • Mix of the above → split and route each part to the right place
  3. For each Memory branch you write to:

    • Update the Current State section with confirmed facts extracted from the file
    • Add a dated entry to Recent Changes: YYYY-MM-DD -- absorbed from <source>
    • Do NOT copy the file verbatim — extract only stable, confirmed facts
    • Skip speculative, transitional, or session-only content
  4. If durable project context changed, update ./bedrock/Memory/PROJECT.md

  5. If current priorities changed, update ./bedrock/Work/NOW.md

  6. Run in terminal: bedrock sync --project .

  7. Summarize:

    • Which files were read
    • Which Memory branches were updated or created
    • Which decisions were added
    • What was skipped and why
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. 4d ago First seen · 35 lines · 0 tokens per session scan A 3e69e298f45d

Subscribe to this mod's changes

absorb is a command published in the GitHub repository robotaitai/project-bedrock (45 stars, last pushed 14d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 355 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 2026-08-30.