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/statsclaw/statsclaw/statsclaw-protocolnpx skills add statsclaw/statsclaw --skill statsclaw-protocolgit clone --depth 1 https://github.com/statsclaw/statsclawWhat 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 | $0.00017 | $0.12795 |
| Opus 5 | $0.00009 | $0.06398 |
| Sonnet 5 | $0.00003 | $0.02559 |
| Haiku 4.5 | $0.00002 | $0.01280 |
Grade A, and why
statsclaw-protocol 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.
How it starts
The opening of the file, as written. The whole thing — 623 lines — stays where its author put it; the contents beside it link to each section on GitHub.
StatsClaw — Agent Teams Framework for Claude Code
StatsClaw is a reusable workflow framework for building, validating, documenting, reviewing, and externalizing code changes with Claude Code across multiple languages. The repository contains the framework only: orchestration rules, agent definitions, templates, profiles, and docs.
StatsClaw does not version user runtime state. All request state, project contexts, generated specs, shared task lists, mailboxes, locks, and run artifacts live inside the workspace repository under .repos/workspace/<repo-name>/. The workspace repo is a user-specified GitHub repository (e.g., [username]/workspace) that serves as both the runtime state directory and the permanent log archive. There is no separate .statsclaw/ directory.
This keeps target repos clean (code + ARCHITECTURE.md + essential user-facing docs only). Exception: ARCHITECTURE.md is written to the target repo root so users and contributors can see the system architecture directly. See skills/workspace-sync/SKILL.md for details.
Simple Prompt Interface
Users should never need to learn StatsClaw terminology. A simple sentence is enough to trigger the full workflow. Leader parses natural language (any language) and routes to the correct skill or workflow automatically.
Example Prompts That Just Work
| User types | What happens |
|---|---|
"patrol fect issues on cfe" |
Scans open issues in xuyiqing/fect, fixes bugs on cfe branch, pushes PRs, replies to issues |
"fix fect issue #42" |
Runs full workflow to fix issue #42 in fect, pushes fix, comments on the issue |
"check fect issues and auto-fix" |
Same as patrol — scans, triages, fixes, pushes, replies |
"monitor fect issues every 30min" |
Recurring patrol with 30-minute interval |
"fix the failing tests in fect" |
Standard fix workflow on fect repo |
"ship it" |
Push current changes and create PR |
"simulate the finite-sample properties" |
Runs Monte Carlo simulation study (workflow 11 or 12) |
"run Monte Carlo for the new estimator" |
Implements estimator + runs simulation (workflow 11) |
"enable brain" |
Enables Brain mode — agents read shared knowledge, noteworthy discoveries are offered for contribution |
"turn off brain" |
Disables Brain mode — isolated mode, no shared knowledge |
/contribute |
Summarizes lessons learned during the session, extracts reusable knowledge, and submits to the shared brain (with user consent) |
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 · 623 lines · 17 tokens per session scan A dce293420912
statsclaw-protocol is a skill published in the GitHub repository statsclaw/statsclaw (91 stars, last pushed 1mo ago), licensed MIT. It adds 17 tokens to every session and 12,795 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 2026-08-30.
Other skills, from other repositories
audit-reproducibility
Enforce the replication-protocol.md rule by cross-checking numeric claims in a manuscript against the actual R / Stata / Python outputs. Report PASS/FAIL per claim against tolerance thresholds. Use before submission and before releasing a replication package.
diagnose
Root-cause a failing or wrong empirical result with a disciplined reproduce → minimise → hypothesise → instrument → fix loop, instead of guessing-and-poking. Use when the user says "why is my regression wrong", "this number changed", "my script errors out", "the result won't reproduce", "debug this", "this estimate…
capture-environment
Snapshot the computational environment for a replication package — detects the analysis stack (R / Stata / Python) and emits the right lockfiles (renv.lock + sessionInfo.txt, requirements.txt / environment.yml / uv.lock, Stata version + ado package list), records seeds and RNG kind, optionally writes a pinning…
checkpoint
Save a structured state snapshot before stopping or handing off. Captures the active plan, recent decisions, file pointers (with line numbers), open questions, and the next 1–3 actions into a checkpoint file under qualityreports/checkpoints/. Optionally proposes [LEARN] entries to add to MEMORY.md. Use when user says…
coauthor-brief
Generate a co-author / collaborator handoff brief for a multi-author, multi-machine project — summarizing what changed since the last brief (git delta), the current state of each artifact (manuscript, analysis, slides), open questions, how to reproduce locally, and any restricted-data access steps. Use when user says…
data-management-plan
Draft a funder-compliant Data Management Plan (NSF DMP, NIH DMS Policy 2023, ERC, Horizon Europe) by composing the confidential-data and environment-capture primitives. Sections cover data description, formats/metadata, storage/backup, access/sharing, preservation/archiving, and roles. Use when user says "data…