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.
git clone --depth 1 https://github.com/ZIB-IOL/The-Agentic-ResearcherWrote 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/commands/zib-iol/the-agentic-researcher/update_base)<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>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 5.1 | $0.00014 | $0.00277 |
| Opus 5 | $0.00007 | $0.00138 |
| Sonnet 5 | $0.00003 | $0.00055 |
| Haiku 4.5 | $0.00001 | $0.00028 |
Grade A, and why
update_base scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
You need to update the project's instruction file with the latest base template while keeping the project-specific content intact.
Steps
- Read the latest base template from
/claude-home/.claude/INSTRUCTIONS.md.template - Detect which instruction file exists in the workspace (check
CLAUDE.md,GEMINI.md,AGENTS.mdin order). Use the first one found as$INSTRUCTION_FILE. - Read the current project file at
/workspace/$INSTRUCTION_FILE - Extract from the current file: everything starting from
## 8. Project Instructions(inclusive) to the end of the file. This is the project-specific content that must be preserved exactly as-is. - Combine: take the template content up to (but NOT including)
## 8. Project Instructions, then append the extracted project-specific content from step 4. - Write the combined result to
/workspace/$INSTRUCTION_FILE - Show the user a brief summary of what changed (e.g., "Updated base sections 0-7 from template, preserved your Project Instructions")
- Commit with message:
chore: update instruction file base template
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.
- 8d ago First seen · 17 lines · 14 tokens per session scan A 74448ec6954e
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.
Other commands, from other repositories
skill-refresh
You are running inside a headless Claude Code session in the neo4j-skills repository. Goal: scan Neo4j release notes and deprecation pages, then update any SKILL.md and references/ files that are stale, outdated, or missing new features. Open no PRs or commits — output only file edits. The workflow will handle git and…
session-stop
Stop recording and save this agent session to the project ledger.
wtfp:resume-writing
Restore the latest portable handoff and route the researcher to the next safe action.
wtfp:discuss-section
Capture the researcher's intended purpose, essential content, voice, and boundaries before planning.
wtfp:new-paper
Interview the researcher and initialize a portable WTF-P project.
wtfp:verify-work
Test a drafted section against each plan requirement and record evidence one check at a time.