ai-science-toolkit: Instructions file for Claude Code

CLAUDE.md

ai-science-toolkit CLAUDE.md is an instructions file for Claude Code from dgilford/ai-science-toolkit. It costs 14,736 tokens per session, scanned F, original, MIT.

A project guide for Claude Code, an AI coding assistant, in a workspace that develops reusable skills. It explains how skills are installed, what several skills do, and how review agents and agent files work.

In plain words
What is it for?
It helps create or update repositories, record work, hand work to another AI session, and find the right skill for a task.
Why use it?
It gives Claude Code a shared reference for using the workspace's skills and following its project conventions.

Instructions file for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

This is dgilford/ai-science-toolkit's own configuration. It tells Claude Code how to work on ai-science-toolkit itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ai-science-toolkit configures →

Runs only inside a plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else, and the catalogue could not identify which plugin ships it.

Reuse

Borrowing it

Nothing to install: this file belongs to dgilford/ai-science-toolkit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/dgilford/ai-science-toolkit/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/dgilford/ai-science-toolkit

Made for: Claude Code.

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 ai-science-toolkit CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/dgilford/ai-science-toolkit/claude-md.svg)](https://agentmods.dev/instructions/dgilford/ai-science-toolkit/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/dgilford/ai-science-toolkit/claude-md"><img src="https://agentmods.dev/badge/instructions/dgilford/ai-science-toolkit/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 14,736 This file is loaded in full into every session.
When invoked 14,736 The same file — it is already loaded in full.
Security scan F 4 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 $0.14736 $0.14736
Opus 5 $0.07368 $0.07368
Sonnet 5 $0.02947 $0.02947
Haiku 4.5 $0.01474 $0.01474

Measured 7d ago against content hash 4e583377c657, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade F, and why

ai-science-toolkit CLAUDE.md scanned grade F with 4 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 7d 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl -sL "https://zenodo.org/api/records/<CONCEPT_ID>" | python3 -c \

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

| `lit-review` | `/lit-review` | Search and synthesize scientific literature from Zotero, arxiv, bioRxiv, Google Scholar, and Consensus. Zotero write support needs `ZOTERO_*` env vars in `~/.claude/settings.json`. |

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

**Shell lint (`scripts/lint-shell.sh`).** ShellCheck `-S warning` over every tracked `*.sh`, discovered with `git ls-files` so a new script is covered as soon as it's committed. It is the **single source of truth**: both

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -sL "https://zenodo.org/api/records/<CONCEPT_ID>" | python3 -c \
CLAUDE.md · 252 lines

How it starts

The opening of the file, as written. The whole thing — 252 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Purpose

This directory is a workspace for developing and iterating on global Claude Code skills. Skills are installed at ~/.claude/skills/<name>/SKILL.md and are available across all projects.

Installed skills

The canonical "when to reach for each" catalog is skills/pathfinder/SKILL.md (/pathfinder); this table is the short index. The external tab-setup skill is excluded here — see Boot hooks and Syncing below.

Skill Trigger Purpose
repo-init /repo-init Scaffold a new repo (or retrofit an existing one) with a standard structure via a short intake grill: research mode by default, --package for a distributable library. Never overwrites; --dry-run previews.
handoff /handoff Create or update a durable project handoff (.ai/HANDOFF.md) for the next AI agent/session.
worklog /worklog Log a work entry to the Notion Work Journal + remote server cache + local .ai/ mirror — the capture core invoked by /handoff and whenever you ask to log something.
pickup /pickup Pick up work from repo-local handoff state — the read side of the handoff pair.
evolve-claude-md /evolve-claude-md Update CLAUDE.md — or the canonical AGENTS.md it redirects to — with durable knowledge from the current session.
grill-me /grill-me Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Thin launcher for the model-invokable grilling core. By Matt Pocock.
grilling /grilling Grill the user relentlessly about a plan or design, one decision at a time, until shared understanding — the model-invokable core behind /grill-me. Adapted from Matt Pocock.
lit-review /lit-review Search and synthesize scientific literature from Zotero, arxiv, bioRxiv, Google Scholar, and Consensus. Zotero write support needs ZOTERO_* env vars in ~/.claude/settings.json.
overbaked /overbaked Audit a document, plan, or code for over-engineering, verbosity, and scope creep.
slack-message /slack-message Draft an internal Slack message grounded in current project context and recent workflow.
create-alert /create-alert Author a scheduled Slack alert: grill a "tell me when X happens" ask into a testable trigger, dry-run it live, and — after you sign off on the synthesized spec — create a claude.ai cloud routine that messages Slack when it fires.
write-new-skill /write-new-skill Create new Claude Code skills with proper structure and progressive disclosure.
unstale /unstale Detect and repair staleness residue in Python library code and notebooks — dead imports, dead code, resolved TODOs, stale comments/docstrings, and HANDOFF blockers; --auto applies HIGH-confidence fixes.
figure-review /figure-review Audit a scientific figure for publication-readiness: colormaps, uncertainty, axes, caption, and claim support; panel-aware, and raises likely-deliberate choices as by-design?; --style adds CC house style.
spot-ai /spot-ai Audit a document, paragraph, or sentence for AI-isms: gray-list style tells (lane 1) and substance weaknesses — hollow claims, fabricated specifics, missing hedges (lane 2). Severity + confidence per finding, fix suggested or missing substance named; per-repo .ai/graylist.md can add, exempt, or re-tune thresholds. Flags only — never rewrites.
reviewer-2 /reviewer-2 Adopt a critical-reviewer stance to stress-test a claim, result, or manuscript section: baseline, counterfactual, alternatives, uncertainty consistency.
pathfinder /pathfinder Router: a navigable map of every skill and subagent and when to reach for each; resolves the reviewer-2-vs-panel review decision.
ai-review /ai-review Comprehensive senior-engineer repo review; orchestrates a parallel fan-out that delegates to code-review/security-review/unstale/overbaked/reviewer-2 and adds gap-hunting, grounded ideation, and prioritized synthesis. Report-only by default; --fix opts into HIGH-confidence unstale repairs.
commit-batch /commit-batch Batch the working tree into logical, single-concern commits, then commit and push if asked. Thin launcher for the model-invokable commit-batching core.
commit-batching /commit-batching Batch a dirty working tree into logical, single-concern commits (survey → group → stage by path → commit → push if asked) — the model-invokable core behind /commit-batch.

Read the full file on GitHub · 252 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. 7d ago First seen · 252 lines · 14,736 tokens per session scan F 4e583377c657

Subscribe to this mod's changes

ai-science-toolkit CLAUDE.md is an instructions file published in the GitHub repository dgilford/ai-science-toolkit (62 stars, last pushed 18d ago), licensed MIT. It adds 14,736 tokens to every session, about $0.0737 per session on Opus 5. A static security scan graded it F with 4 findings (downloads and executes remote code, reads agent configuration directories, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other instructions, from other repositories

vibetags com-example-config-AsyncTestConfig.instructions.md

Instructions for PIsberg/vibetags, covering copilot instructions for asynctestconfig and immutable type.

PIsberg/vibetags · 82 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens