05_tool_heavy_task — Claude Code prompt: file reading and setup
The 05_tool_heavy_task prompt has Claude Code read three files one at a time, then sum up Meridian’s testing strategy in a single paragraph. It also tests whether the agent makes separate tool calls.
MIT ★ 2,744 updated 2026-10-08
.claude/commands/05_tool_heavy_task.mdWhat 05_tool_heavy_task does
The prompt asks Claude Code to use Read on compare-fixture-unit-tests.md, compare-fixture-integration-tests.md, and compare-fixture-release-checks.md, with a separate call for each file. Once all three reads are complete, the agent writes one paragraph describing Meridian’s testing strategy.
The files need to be in Claude Code’s current working directory. If one is missing, the requested sequence cannot be completed as written. The prompt is designed to measure tool-call fan-out, so the text of the final paragraph is not the thing being checked.
What it helps with
- Check whether an agent reads each file with a separate Read call
- Combine details from unit tests, integration tests, and release checks
- Summarize Meridian’s testing strategy in one paragraph
Example prompts for the agent
- Read the three Meridian testing files one by one, then write a single-paragraph summary of the project’s testing strategy.
- Use a separate Read call for
compare-fixture-unit-tests.md,compare-fixture-integration-tests.md, andcompare-fixture-release-checks.md, then reconcile their contents.
How to install 05_tool_heavy_task
Manually: put the files in place
.claude/commands/05_tool_heavy_task.mdHow to use
Paste the text at the start of a chat or into project instructions
Questions about 05_tool_heavy_task
How do I install 05_tool_heavy_task in Claude Code?
Use .claude/commands/05_tool_heavy_task.md as the installation path.
What does 05_tool_heavy_task do?
It directs Claude Code to read three named files with separate Read calls, then summarize Meridian’s testing strategy in one paragraph.
Which files does 05_tool_heavy_task need?
The current working directory must contain compare-fixture-unit-tests.md, compare-fixture-integration-tests.md, and compare-fixture-release-checks.md.
Source text
05_tool_heavy_task.md · MIT
--- name: tool_heavy_task content_shape: agentic-tool-use reference_tokens_per_char: 0.27 description: Force at least three tool calls. No predicate — the value is measuring tool-fanout ratio, not text compliance. --- [session-metrics:compare-suite:v2:prompt=tool_heavy_task] Use your Read tool to read each of these three files in turn (they are in your current working directory), then reconcile what you see across them into a single one-paragraph summary of the Meridian project's testing strategy: 1. `compare-fixture-unit-tests.md` 2. `compare-fixture-integration-tests.md` 3. `compare-fixture-release-checks.md` You must actually invoke the Read tool three separate times — one per file — before writing the summary. Output the summary as one paragraph after the reads are complete. <!-- PREDICATE --> ````python # No predicate — tool fan-out is what we're measuring here, not the # text output. The paired-turn ratio columns (token + cost) carry the # signal; a check() that tested text would give misleading pass/fail. check = None ````
© centminmod · MIT · centminmod/my-claude-code-setup