lw-capture

lw-capture is a skill for Claude Code from matteoroversi/lookward. It costs 65 tokens per session (844 once invoked), scanned A, original, MIT.

A recording step for saving signals such as chat sessions, pasted text, or connector data into a knowledge system's source folder. Each capture is immutable, meaning it is preserved and not edited later.

In plain words
What is it for?
It helps capture Claude Code sessions, pasted content, and data pulled from connectors. It records the source only; creating or combining knowledge entries is handled elsewhere.
Why use it?
It gives incoming information a permanent record with its origin and time. It prevents raw evidence from being confused with edited knowledge or summaries.

Skill for Claude Code

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

Part of the lookward plugin — 5 skills shipped together

Good fit It helps capture Claude Code sessions, pasted content, and data pulled from connectors. It records the source only; creating or combining knowledge entries is handled elsewhere.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/matteoroversi/lookward/lw-capture
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 matteoroversi/lookward --skill lw-capture
Clone the repo
git clone --depth 1 https://github.com/matteoroversi/lookward

Made for: Claude Code.

Or install lookward, the plugin that ships this one along with the rest of its 5 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 lw-capture

README.md
[![agentmods](https://agentmods.dev/badge/skills/matteoroversi/lookward/lw-capture/github.svg)](https://agentmods.dev/skills/matteoroversi/lookward/lw-capture)
Your own site
<a href="https://agentmods.dev/skills/matteoroversi/lookward/lw-capture"><img src="https://agentmods.dev/badge/skills/matteoroversi/lookward/lw-capture/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 lw-capture

Your own site · 80×15
<a href="https://agentmods.dev/skills/matteoroversi/lookward/lw-capture"><img src="https://agentmods.dev/badge/skills/matteoroversi/lookward/lw-capture.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 844 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00065 $0.00844
Opus 5 $0.00032 $0.00422
Sonnet 5 $0.00013 $0.00169
Haiku 4.5 $0.00006 $0.00084

Measured 11d ago against content hash 6ee7e6d78154, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

lw-capture 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 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.

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.

skills/lw-capture/SKILL.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

lw-capture

Append a signal to the world model's sources/immutable, append-only, provenance-stamped. This skill is the record primitive of the living loop — mostly invisible: the connectors (forged by lw-forge) and the surface automations (the Claude Code hook, the claude.ai routine) call it; you rarely invoke it by hand. When you do invoke it directly — /lw-capture with a paste or a file — it writes one immutable digest capture to sources/ and stops there. It does not create or edit knowledge nodes and does not consolidate — that is lw-enrich (propose-don't-apply). Loads ontology/contract.md.

What it writes — a capture (a source node)

One markdown file per signal, under sources/<channel>/…, with frontmatter:

---
id: <stable id — derived from the source's native id, so re-runs don't duplicate>
type: source
title: <human label for the signal>
timestamp: <when the signal happened, ISO 8601>
resource: <link or native id of the original — the system of record>
lookward:
 world_model: <wm name>
 purpose: "raw capture of a <source kind>"
 face: self
 visibility: private # default private (Rule 3)
 provenance: connector # connector | upload | reflection | session
 confidence: high
 capture:
 surface: <claude.ai | claude-code | …>
 source_kind: <session-transcript | message | file | …>
 source_id: <native id>
 pull_run: <ISO date of this capture run>
---
# Faithful digest of the signal — topics, decisions, artifacts produced, open items,
# entities mentioned. Every claim traceable to `resource`. Nothing invented (citation invariant).

Rules (from the contract)

  • Append-only & immutable. Never edit or overwrite a prior capture. Re-running is idempotent: if a capture for this source_id already exists, skip it.
  • Faithful, not invented. The digest reflects only what the signal contains; it cites the source. No consolidation, no interpretation into nodes.
  • Default private. visibility: private unless the user has set otherwise.
  • Provenance always. Stamp surface, source kind, source id, and pull-run.

Read the full file on GitHub · 54 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 · 54 lines · 65 tokens per session scan A 6ee7e6d78154

Subscribe to this mod's changes

lw-capture is a skill published in the GitHub repository matteoroversi/lookward (7 stars, last pushed 2mo ago), licensed MIT. It adds 65 tokens to every session and 844 once invoked, about $0.0003 per session on Opus 5. 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

media-ingest

Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.

garrytan/gbrain · 52 tokens

mem0-oss-to-platform

Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…

mem0ai/mem0 · 273 tokens

Cortex

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…

danielmiessler/LifeOS · 196 tokens

memory

Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.

opensquilla/opensquilla · 44 tokens

ha-data-stores

Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…

shiwenwen/hope-agent · 115 tokens

shellm

Reference for the shellm system — recursive LLM shell, identity management, memory, skills, trajectory, and all CLI tools. Use when working on shellm itself, debugging agent behavior, or understanding how the pieces fit together.

laude-institute/headlong · 49 tokens