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 agentmods add skills/lacerbi/dotclaude/filesnpx skills add lacerbi/dotclaude --skill filesgit clone --depth 1 https://github.com/lacerbi/dotclaudeWrote 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/lacerbi/dotclaude/files)<a href="https://agentmods.dev/skills/lacerbi/dotclaude/files"><img src="https://agentmods.dev/badge/skills/lacerbi/dotclaude/files.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00009 | $0.00489 |
| Opus 5 | $0.00005 | $0.00244 |
| Sonnet 5 | $0.00002 | $0.00098 |
| Haiku 4.5 | $0.00001 | $0.00049 |
Grade A, and why
files 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.
What it actually says
Task
$ARGUMENTS
Your Task
Identify the essential context files someone needs to read before starting this task — the files that rebuild the broader understanding an agent needs to avoid tunnel vision.
What This Is For
A fresh agent is about to work on this task with a clean context window. It will naturally discover specific implementation files as it works. Your job is different: identify the 3–6 files that provide the surrounding context — the big picture that prevents the agent from being over-focused on the immediate task and making mistakes from ignorance.
What to Include
- The task/plan file if one exists (e.g.,
PLAN-foo.md) - Core project docs: Architecture files, design docs, devlogs, or READMEs that explain why things are the way they are — if they are useful to understand the broader context
- Key conventions or patterns: Files that show how similar work was done, or that establish standards the task must follow
- Critical implicit context: Things that someone familiar with the project would know but a fresh agent won't
What NOT to Include
- Files the agent will find on its own through normal exploration
- Every file tangentially related to the task
- CLAUDE.md/AGENTS.md (loaded automatically)
- Long lists of implementation files — if you're listing more than ~6 files, you're being too granular
Process
- Understand the task scope
- Explore the project for broader context docs (architecture, design, devlogs, guides)
- Select the smallest set of files that gives a fresh agent the big picture
Output Format
Output a short list with brief explanations:
path/to/file - why it matters for context
path/to/other - why it matters for context
Aim for ~6 files (3–6 typical; a few extra are allowed if truly important, e.g., for a fragmented knowledge base). After outputting the list, stop — do not read the files or start working.
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.
- 4d ago First seen · 49 lines · 9 tokens per session scan A fb43a40f83d6
files is a skill published in the GitHub repository lacerbi/dotclaude (2 stars, last pushed 5d ago), licensed MIT. It adds 9 tokens to every session and 489 once invoked, about $0.0000 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.
Other skills, from other repositories
hyperpod-node-debugger
Diagnose and remediate per-node issues on a HyperPod cluster (EKS or Slurm) — a specific node is unhealthy, unresponsive, stuck, or needs replacing. Covers on-node EFA, GPU / accelerator hardware (XID, ECC, NVLink, row-remap, DCGM), Slurm node down/drained, disk and memory pressure, per-node lifecycle-script failures…
brain-page
Operating manual for reading and writing a project's brain — every read and write goes through the bundled zero-dependency brain CLI; never hand-edit brain files. Read it before creating or modifying any page or root page.
brain-bootstrap
Seed a freshly-scaffolded brain with real project knowledge — on an existing (brownfield) project read the code, docs, and git log to draft the six root pages and capture key historical decisions; on a near-empty (greenfield) project interview the user. Every write goes through the brain CLI. Run it after brain-setup.
brain-ingest
The process for digesting a conversation, document, or research result, classifying it, and writing it down as brain content (a root-page update or a new/updated page) through the brain CLI.
immune
Hybrid adaptive memory: Cheatsheet (positive patterns pre-generation) and Immune (negative patterns post-generation) with Hot/Cold tiered auto-learning. Triggers on: "scan for errors", "immune scan", "check output quality", "antibody scan". NOT for PR review (use pr-review) or repo audits (use repo-sentinel).
brain-setup
Bootstrap the Open Project Brain Standard into the current project — prefer brain init (ensure BRAIN.md, scaffold empty brain brainRoot-aware, default-wire CLAUDE.md + AGENTS.md). Optionally install a pre-commit hook and a Claude Code SessionStart hook.