A cross-project store for recording lessons from coding sessions and keeping a curated playbook of reusable patterns. It stores the user's data locally, with optional syncing to private GitHub repositories.

Use it to capture insights, search past notes, promote reusable lessons into the playbook, and manage that playbook.

Useful knowledge can be lost between projects or sessions. This separates raw session notes from general lessons that are worth carrying into new projects.

nucleus — Skill by machbuilds

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 skills/machbuilds/atom/nucleus

Any agent

npx skills add machbuilds/atom --skill nucleus

Clone the repo

git clone --depth 1 https://github.com/machbuilds/atom

Made for: Claude Code, Codex.

Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 927 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.

Model	Per session	Once invoked
Fable 5	$0.00029	$0.00927
Opus 5	$0.00015	$0.00464
Sonnet 5	$0.00006	$0.00185
Haiku 4.5	$0.00003	$0.00093

Measured 2d ago against content hash dbae53515d84, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

nucleus 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 2d 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.

scaffold/.claude/skills/nucleus/SKILL.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

nucleus skill (Claude wrapper)

Source of truth: see the Tooling > nucleus and Tooling > learnings sections of AGENTS.md in this project. That file holds the canonical instructions every AI tool reads.

This file is the Claude-specific wrapper. Behavior comes from AGENTS.md.

The two layers (don't conflate them)

nucleus — your memory of every session. Raw, project-tagged, low bar to capture. Lives at ~/.atom/nucleus/.
learnings — your playbook of patterns to carry forward. Curated, generalized, high bar. Lives at ~/.atom/learnings/. Auto-copied into every new project you bootstrap from atom.

Both are 100% the user's own data. Nothing leaves their machine without explicit action. They optionally sync to the user's own private GitHub repos.

Quick reference

# Capture during session (low bar)
nucleus add "<insight>" --type <T> --confidence <C> --tags <t1> <t2>
nucleus search "<keyword>" --json --limit 5

# Graduate to playbook (high bar — only when generalizable)
nucleus promote <id>            → writes ~/.atom/learnings/<type>/<key>.md

# Manage your playbook
learnings list
learnings show <key>
learnings sync                  → push/pull to private GitHub

atom --help shows the unified command table.

When this skill activates (Claude-specific)

Capture is not automated — there is no daemon. You actively call nucleus add during the session when one of these triggers fires:

After fixing a non-obvious bug. What was the surprise? Capture.
After a design decision with rationale. Why this approach over the alternative? Capture.
After discovering a generalizable pattern. A snippet, a flag, a workflow that worked. Capture.
At /clear or end-of-task signals (user says "ship it", "we're done", or commits). Sweep recent work, capture anything missed.

The bar is low. If you're unsure whether to capture, capture. Promotion is where refinement happens; nucleus is the journal.

Read the full file on GitHub · 109 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.

2d ago First seen · 109 lines · 29 tokens per session scan A dbae53515d84

Subscribe to this mod's changes

nucleus is a skill published in the GitHub repository machbuilds/atom (2 stars, last pushed 2mo ago), licensed MIT. It adds 29 tokens to every session and 927 once invoked, about $0.0001 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.

Memory and context agentsmd ai-agent ai-tools claude-code cli developer-tools

opencli-sitemap-author

Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.

jackwener/OpenCLI · 67 tokens

golden-rss

Use when testing the rss golden build.

yusufkaraaslan/Skill_Seekers · 12 tokens

omh-buzz

This is a Hermes-native buzz workflow skill.

rlaope/oh-my-hermes · 95 tokens

redteam-api-detail-pack

Domain routing and boundary guidance for authorized API security testing, including BOLA/IDOR, authentication bypass, mass assignment, missing rate limits, and GraphQL issues. Use when a task belongs to the API testing domain and needs scope, evidence, pivot, or exit criteria.

Netw0rkNoob/VulnClaw · 61 tokens

redteam-postex-detail-pack

Domain routing and boundary guidance for authorized post-exploitation testing after initial access, including privilege escalation, persistence, lateral movement, data collection, and cleanup considerations. Use when a task belongs to the post-exploitation domain and needs scope, evidence, pivot, or exit criteria.