zotero-code-execution CLAUDE.md

A set of development rules for the zotero-code-execution project, including where skill files belong and what to check before committing changes.

In plain words
What is it for?
Maintaining the project's skill files, updating its README when behavior changes, checking versions, and preparing changes for review and later commit.
Why use it?
It prevents edits in the wrong location and makes project changes easier to review by requiring related documentation updates and user review before commits.

Instructions file

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 instructions/kerim/zotero-code-execution/claude-md
Clone the repo
git clone --depth 1 https://github.com/kerim/zotero-code-execution
Per session 286 This file is loaded in full into every session.
When invoked 286 The same file — it is already loaded in full.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00286 $0.00286
Opus 5 $0.00143 $0.00143
Sonnet 5 $0.00057 $0.00057
Haiku 4.5 $0.00029 $0.00029

Measured 3d ago against content hash 850817c70975, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

zotero-code-execution CLAUDE.md 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 3d 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.

CLAUDE.md · 33 lines

What it actually says

Development Instructions for zotero-code-execution

Skill Development Workflow

This project follows the standardized skill workflow. The skill files are in the skill/ subfolder, which is symlinked to ~/.claude/skills/zotero-mcp-code/.

Important Rules

  1. Only edit files in the skill/ folder - Never edit ~/.claude/skills/ directly (it's a symlink to this folder)
  2. Update README.md if functionality changes
  3. Ask user to review changes before committing
  4. Commit and push after user approval (if remote exists)

File Structure

zotero-code-execution/
├── skill/                    # Symlinked to ~/.claude/skills/zotero-mcp-code/
│   └── SKILL.md              # The actual skill definition
├── *.py                      # Python library and scripts
├── README.md                 # GitHub install instructions
└── CLAUDE.md                 # This file - workflow instructions

Before Committing

  • Changes are in skill/ folder only
  • README.md updated if needed
  • User has reviewed changes
  • Version number updated (if applicable)
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. 3d ago First seen · 33 lines · 286 tokens per session scan A 850817c70975

Subscribe to this mod's changes

zotero-code-execution CLAUDE.md is an instructions file published in the GitHub repository kerim/zotero-code-execution (59 stars, last pushed 7mo ago), licensed MIT. It adds 286 tokens to every session, about $0.0014 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.