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.
npx skills add damusix/atomic-claude --skill atomic-wikigit clone --depth 1 https://github.com/damusix/atomic-claudeWrote 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.
[](https://agentmods.dev/skills/damusix/atomic-claude/atomic-wiki)<a href="https://agentmods.dev/skills/damusix/atomic-claude/atomic-wiki"><img src="https://agentmods.dev/badge/skills/damusix/atomic-claude/atomic-wiki/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.
<a href="https://agentmods.dev/skills/damusix/atomic-claude/atomic-wiki"><img src="https://agentmods.dev/badge/skills/damusix/atomic-claude/atomic-wiki.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00204 | $0.01895 |
| Opus 5.5 | $0.00082 | $0.00758 |
| Sonnet 5.5 | $0.00041 | $0.00379 |
| Haiku 4.5 | $0.00020 | $0.00189 |
Grade A, and why
atomic-wiki 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auto-fires on:
- "I want a place for my notes / research / tickets / raw dumps"
- "create a space for [notes|tickets|research]" — any capture-intent phrase
- "add a bucket", "add this to my wiki", "wiki this"
- "set up a karpathy wiki", "karpathy realm", "set up a wiki for my projects"
- "what does my wiki know about X"
- "is my wiki stale"
Conversational entry point for wiki and capture-bucket operations. Code writes structure; the model writes meaning. Degrades gracefully when atomic binary is absent.
Realm resolution
Read the <wikis> block in ~/.claude/CLAUDE.md (outside <atomic>, CLI-managed). Each entry is a path to a registered wiki's index.md. The realm root is the directory containing wiki/index.md.
- cwd under a realm root → that realm is active. Bucket operations target it.
- No registered realm + setup intent →
atomic wiki scan --root <path>bootstraps. Ask which folder is the realm root if ambiguous. atomicbinary absent → say so; point at/refresh-wikianddocs/reference/realm-wiki.md. Do not hand-build the structure.
Pipeline routing
When a full inference run is needed (refresh, summarize, synthesize), detect scope and load the matching reference:
- Read
<wiki-type>from the active wiki index (docs/wiki/index.mdfor repo scope,wiki/index.mdfor realm scope). - Repo scope (
<wiki-type>repo</wiki-type>) — the full per-repo pipeline lives at~/.claude/skills/atomic-wiki/references/repo.md(installed location). A full refresh is triggered via/refresh-wiki, which dispatchesatomic-wiki-inferrerto execute it. - Realm scope (
<wiki-type>realm</wiki-type>) — the wiki-output and bucket-synthesis pipelines live at~/.claude/skills/atomic-wiki/references/realm.md(installed location). A full refresh is triggered via/refresh-wiki [root], which orchestrates scan/stale/offer and dispatchesatomic-wiki-inferrerfor each inference step.
The pipeline text lives only in the reference files (installed at ~/.claude/skills/atomic-wiki/references/) — not here, and not duplicated in the agent's system prompt. When an agentic inference run is needed, the agent resolves $HOME via Bash and reads the appropriate reference file at its absolute path, then executes it.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 106 lines · 204 tokens per session scan A b83eca6fc17e
atomic-wiki is a skill published in the GitHub repository damusix/atomic-claude (114 stars, last pushed today), licensed MIT. It adds 204 tokens to every session and 1,895 once invoked, about $0.0008 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
context-mode
Use context-mode tools (ctxexecute, ctxexecutefile) instead of Bash/cat when processing large outputs. Triggers: "analyze logs", "summarize output", "process data", "parse JSON", "filter results", "extract errors", "check build output", "analyze dependencies", "process API response", "large file analysis", "page…
memory-management
A project-memory manager that stores information in HOT, WARM, and COLD tiers. These tiers keep frequently needed context close at hand while archiving older information for later retrieval.
vc:context-engineering
Check context limits, optimize token usage, and debug context failures. Use when asking about rate limits, usage warnings, memory systems, or context-aware agent design.
ctx-purge
Purge the context-mode knowledge base. Permanently deletes all indexed content and resets session stats. This is destructive and cannot be undone. Trigger: /context-mode:ctx-purge.
next
Produce a clean handoff to a fresh Claude Code window. Use when the current conversation is too long (>400K tokens, hallucinations, lost context, or the user wants to close the window). "/next" produces a handoff, "/next list" shows all pending, "/next remove X" deletes one.
agenticx-memory-architect
Guide for setting up and using the AgenticX memory system including Mem0 integration, long-term memory, context management, and memory-enhanced agents. Use when the user wants to add memory to agents, persist conversation history, build memory-aware workflows, or integrate with Mem0 for long-term recall.