[MODEL] Agent briefs/replies refused by the user's own hook: READ-FIRST BLOCK (tool use before reading the page) (26 on one day)

Preflight Checklist

• [x] I have searched existing issues for similar behavior reports
• [x] This report does NOT contain sensitive information (API keys, passwords, etc.)

Type of Behavior Issue

Claude ignored my instructions or configuration

What You Asked Claude to Do

Standing project instructions and a user-written hook set rules for how agents brief, message, stop and report. This report covers one refusal type, READ-FIRST BLOCK (tool use before reading the page). Count for the day: 26; actors: 14 agents; mostly newly started workers.

What Claude Actually Did

Agents made a tool call before reading the user's read-first page in full, or after the page changed. 26 tool calls were refused (Read 9, Bash 7, browser 2, Grep 2, transcript reads 2, create-agent, remote command, get-self, Write). The previous overseer's first call after taking over at 13:22 was one of them.

Expected Behavior

Read the standing page first when the project instructions say to, and re-read it when told it changed.

Files Affected

None. Agent messages and tool calls only.

Permission Mode

Accept Edits was ON (auto-accepting changes)

Can You Reproduce This?

Sometimes (intermittent)

Steps to Reproduce

Not a deterministic repro. The sequence is in the record above; the underlying logs are on the reporter's machine and can be summarised on request.

Claude Model

Sonnet

Relevant Conversation

See "What Claude Actually Did". Quotes are limited to the agents' own tool results and messages.

Impact

Medium - Extra work to undo changes

Claude Code Version

2.1.289 (as recorded in the agent session logs; the claude on PATH reports 2.1.220)

Platform

Other

Additional Context

This is one of 19 refusal types from the same day; the summary ticket links all of them. The hook is user-written and is not part of the product; the behaviour reported is what the agents sent into it.
Single-day record, 2026-10-06, all times US Eastern (Windows 11), a multi-agent session driven through a third-party agent harness; API platform is unverified. Reported as behaviour, not as a claim that Claude Code is defective.