A workflow for adding material such as product documents, articles, studies, or company processes to an organised knowledge system. It chooses a destination, summarises the important points, records their source, and notes when they should be used again.

Use it to process incoming documents and research, decide where they belong, extract the essentials, preserve their provenance, and record future uses.

It prevents useful information from remaining only in a chat and being lost when the session ends. It also separates durable knowledge from active project or process material.

absorb — Skill for Claude Code by pe-menezes/pm-chief-of-staff

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 pe-menezes/pm-chief-of-staff --skill absorb

Clone the repo

git clone --depth 1 https://github.com/pe-menezes/pm-chief-of-staff

Made for: Claude Code.

Or install pm-chief-of-staff, the plugin that ships this one along with the rest of its 12 skills, 1 agent, 4 hooks.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/pe-menezes/pm-chief-of-staff/absorb/github.svg)](https://agentmods.dev/skills/pe-menezes/pm-chief-of-staff/absorb)

Your own site

<a href="https://agentmods.dev/skills/pe-menezes/pm-chief-of-staff/absorb"><img src="https://agentmods.dev/badge/skills/pe-menezes/pm-chief-of-staff/absorb/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/pe-menezes/pm-chief-of-staff/absorb"><img src="https://agentmods.dev/badge/skills/pe-menezes/pm-chief-of-staff/absorb.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 897 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 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.

Model	Per session	Once invoked
Fable 5.1	$0.00000	$0.00897
Opus 5.5	$0.00000	$0.00359
Sonnet 5.5	$0.00000	$0.00179
Haiku 4.5	$0.00000	$0.00090

Measured 6d ago against content hash b8c0f27641ff, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 6d 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.

seeds/absorb/SKILL.md · 40 lines

How it starts

The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Absorb material

pm-chief-of-staff seed. This file is YOURS: ask the agent to change the routing or the summary format and it edits this skill on the spot.

Writing: write to the person and in their files in the language this folder's instruction file defines (the AGENTS.md; in a folder without AGENTS.md, the CLAUDE.md); without one, in the language the person writes in, and fallback questions go in their language too. Follow that file's writing canon. Without it: no em dash (use a comma, parentheses or a colon), short dense sentences, 1 line per item.

The value lies in giving the material a destination, distilling what the system does not know yet and leaving in writing when it comes back. Material that stays only in the chat evaporates when the session closes.

Step 1: understand the material

At most 1 question, and only if it cannot be inferred: what it is and what it is for.

Step 2: route by nature

Living project doc (spec, plan, analysis of what is in progress): the project folder in projects/.
Durable knowledge (product, market, article, study): reference/{topic}.md.
Company operating process, by its trigger: the trigger is a file type ("every note of X follows this format"), it becomes .claude/rules/{topic}.md with paths: frontmatter; the trigger is a ritual a planted skill covers (prep a conversation, close the week), the rule goes into the owning skill; the same step applies in 2 or more skills, it becomes a module in .claude/skills/_shared/{name}.md that each of them tells the agent to read (declare at its top who loads it); no clear trigger, reference/ with the trigger written in the file.
About a key person: their hub in people/, in the right section: dated fact with source in "Facts", signal in "Recent signals" (1 dated line), a reading that changes the previous one in "Current reading" (marking the previous one with "superseded on YYYY-MM-DD by {what superseded it}").

Step 3: distill the delta

Read the full file on GitHub · 40 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.

6d ago First seen · 40 lines · 0 tokens per session scan A b8c0f27641ff

Subscribe to this mod's changes

absorb is a skill published in the GitHub repository pe-menezes/pm-chief-of-staff (5 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 897 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 2026-10-31.

Claude Code Documents Memory and context chief-of-staff claude-code-plugin codex product-management second-brain

absorb next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
absorbpe-menezes/pm-chief-of-staff	Skill	5	3d ago	MIT	A	0	Claude Code
migrateguhcostan/claude-mega-brain	Skill	127	3mo ago	MIT	A	147	Claude Code
initguhcostan/claude-mega-brain	Skill	127	3mo ago	MIT	A	89	Claude Code
pageswenlan-app/wenlan	Skill	93	yesterday	Apache-2.0	A	105	Claude Code, Codex
doc-digestegorfedorov/claude-context-optimizer	Skill	130	10d ago	MIT	A	75	Claude Code
gemini-synctonydzi/second-brain-starter-kit	Skill	14	2d ago	MIT	A	0	Claude Code
wicked-garden-mem-ingestmikeparcewski/wicked-garden	Skill	9	today	MIT	A	129	Claude Code