Manage costs effectively changedcosts
Nearest release: v2.1.322, published 14 hours before upstream edited the page. Shown because the two are within 24 hours of each other. Nothing here says the release caused the edit.
Upstream edited this page at 10 Nov 2026 16:08 UTC, give or take a minute or two: the time comes from Anthropic’s own sitemap rather than from a commit. This site recorded the change at 10 Nov 2026 16:37 UTC.
Upstream edited
Recorded here
Lines+6added
Lines−6removed
From line
288
where the diff opens
First seen
14 Aug 2026
this site's first read of the page
Recorded edits52to this page, all time
The whole hunk
from line 288, old and new numbered
/
from line 288
288288
289289Custom [hooks](https://code.claude.com/docs/en/hooks.md) can preprocess data before Claude sees it. Instead of Claude reading a 10,000-line log file to find errors, a hook can grep for `ERROR` and return only matching lines, reducing context from tens of thousands of tokens to hundreds.
290290
291A [skill](https://code.claude.com/docs/en/skills.md) can give Claude domain knowledge so it doesn't have to explore. For example, a "codebase-overview" skill could describe your project's architecture, key directories, and naming conventions. When Claude invokes the skill, it gets this context immediately instead of spending tokens reading multiple files to understand the structure.
291This PreToolUse hook trims test output to its last 100 lines:
292292
293For example, this PreToolUse hook filters test output to show only failures:
294
295293> [tab] settings.json
296294>
297295> Add this to your [settings.json](https://code.claude.com/docs/en/settings.md#where-settings-live) to run the hook before every Bash command:
from line 314
316314
317315> [tab] filter-test-output.sh
318316>
319> The hook calls this script. Create the folder with `mkdir -p ~/.claude/hooks`, save the script below as `~/.claude/hooks/filter-test-output.sh`, and make it executable with `chmod +x ~/.claude/hooks/filter-test-output.sh`. It checks if the command is a test runner and modifies it to show only failures:
317> The hook calls this script. Create the folder with `mkdir -p ~/.claude/hooks`, save the script below as `~/.claude/hooks/filter-test-output.sh`, and make it executable with `chmod +x ~/.claude/hooks/filter-test-output.sh`. It checks if the command is a test runner and, if so, keeps only the last 100 lines of its output:
320318>
321319> ```bash theme={null}
322320> #!/bin/bash
from line 321
323321> input=$(cat)
324322> cmd=$(echo "$input" | jq -r '.tool_input.command')
325323>
326> # If running tests, filter to show only failures
324> # If running tests, keep only the last 100 lines
327325> pattern='^(npm test|pytest|go test)( [^;&|<>`$#\\[:cntrl:]]*)?$'
328326> if [[ "$cmd" =~ $pattern ]]; then
329> filtered_cmd="$cmd 2>&1 | grep -A 5 -E '(FAIL|ERROR|error:)' | head -100"
327> filtered_cmd="$cmd 2>&1 | tail -n 100"
330328> echo "$input" | jq --arg filtered "$filtered_cmd" \
331329> '{hookSpecificOutput: {hookEventName: "PreToolUse", updatedInput: (.tool_input + {command: $filtered})}}'
332330> else
from line 333
335333> ```
336334
337335To verify the setup, run `/hooks` and check that the hook appears under PreToolUse. You can also start Claude Code with `claude --debug-file ./claude-debug.txt` and ask Claude to run `npm test`. When the hook rewrites the command, that log file contains a `modified tool input keys` line listing `command` and the other Bash input fields.
336
337A [skill](https://code.claude.com/docs/en/skills.md) can give Claude domain knowledge so it doesn't have to explore. For example, a "codebase-overview" skill could describe your project's architecture, key directories, and naming conventions. When Claude invokes the skill, it gets this context immediately instead of spending tokens reading multiple files to understand the structure.
338338
339339### Move instructions from CLAUDE.md to skills
340340
No line in this hunk matches that.