update_base

update_base is a command for Claude Code from ZIB-IOL/The-Agentic-Researcher. It costs 14 tokens per session (277 once invoked), scanned A, original, MIT.

A command that refreshes a project's instruction file from a shared base template while retaining the project's own instructions. It checks common instruction-file names and updates the first one it finds.

In plain words
What is it for?
It is for updating CLAUDE.md, GEMINI.md, or AGENTS.md with newer shared instructions, preserving the project section, showing a summary, and committing the change.
Why use it?
It removes the need to manually copy new standard instructions while protecting project-specific guidance from being overwritten.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md). Also seen: mentions CLAUDE.md; mentions AGENTS.md; mentions Gemini CLI.

Good fit It is for updating CLAUDE.md, GEMINI.md, or AGENTS.md with newer shared instructions, preserving the project section, showing a summary, and committing the change.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/zib-iol/the-agentic-researcher/update_base
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.

Clone the repo
git clone --depth 1 https://github.com/ZIB-IOL/The-Agentic-Researcher

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 update_base

README.md
[![agentmods](https://agentmods.dev/badge/commands/zib-iol/the-agentic-researcher/update_base.svg)](https://agentmods.dev/commands/zib-iol/the-agentic-researcher/update_base)
Your own site
<a href="https://agentmods.dev/commands/zib-iol/the-agentic-researcher/update_base"><img src="https://agentmods.dev/badge/commands/zib-iol/the-agentic-researcher/update_base.svg" alt="Measured on agentmods" height="20"></a>
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 277 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 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 $0.00014 $0.00277
Opus 5 $0.00007 $0.00138
Sonnet 5 $0.00003 $0.00055
Haiku 4.5 $0.00001 $0.00028

Measured 8d ago against content hash 74448ec6954e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

update_base 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 8d 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.

commands/update_base.md · 17 lines

What it actually says

You need to update the project's instruction file with the latest base template while keeping the project-specific content intact.

Steps

  1. Read the latest base template from /claude-home/.claude/INSTRUCTIONS.md.template
  2. Detect which instruction file exists in the workspace (check CLAUDE.md, GEMINI.md, AGENTS.md in order). Use the first one found as $INSTRUCTION_FILE.
  3. Read the current project file at /workspace/$INSTRUCTION_FILE
  4. Extract from the current file: everything starting from ## 8. Project Instructions (inclusive) to the end of the file. This is the project-specific content that must be preserved exactly as-is.
  5. Combine: take the template content up to (but NOT including) ## 8. Project Instructions, then append the extracted project-specific content from step 4.
  6. Write the combined result to /workspace/$INSTRUCTION_FILE
  7. Show the user a brief summary of what changed (e.g., "Updated base sections 0-7 from template, preserved your Project Instructions")
  8. Commit with message: chore: update instruction file base template
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. 8d ago First seen · 17 lines · 14 tokens per session scan A 74448ec6954e

Subscribe to this mod's changes

update_base is a command published in the GitHub repository ZIB-IOL/The-Agentic-Researcher (93 stars, last pushed 2mo ago), licensed MIT. It adds 14 tokens to every session and 277 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.