Hk Local Logs

What it does

When your agent uses it

• Someone mentions a 500 error
• What went wrong
• A service not starting
• Celery task failures

Example prompts

• “check the logs”
• “what went wrong”
• “getting 500”
• “/hk-local-logs”

Requirements

• Python 3
• Pre-approved tools (allowed-tools): Bash, Read, Grep

Workflow steps

4 steps, taken from the step headings in SKILL.md.

1. 1Resolve paths
2. 2Read the log
3. 3Search mode (--search)
4. 4Auto-detect mode (no layer specified)

What it can do on your machine

Read from SKILL.md and the folder at commit 87305cd. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • Bash
  • Read
  • Grep

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • git
  • python
  • python3

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Hk Local Logs loads about 2.1k tokens when it runs. Until then it costs about 131 tokens; SKILL.md has 624 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~131

When it runs · the whole SKILL.md, loaded when a task matches

~2.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

• NotePre-approves every shell command (allowed-tools: Bash)SKILL.md

  allowed-tools: Bash, Read, Grep

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from deepklarity/harness-kit at commit 87305cd, republished under its MIT licence (© deepklarity). 624 words, ~2,113 tokens.

name

hk-local-logs

description

Inspect and debug errors via logs across the harness-kit monorepo. Reads the right log file based on the error layer — backend, frontend, celery, odin CLI, or odin task execution. Use this skill whenever someone mentions a 500 error, a stack trace, a crash, 'check the logs', 'what went wrong', a service not starting, celery task failures, or any runtime error. Also triggers on: 'getting 500', 'backend error', 'celery error', 'odin failed', 'check logs', 'tail logs', 'debug this error', or /hk-local-logs.

allowed-tools

Bash, Read, Grep

argument-hint

[backend | frontend | celery | odin | task <id>] [--lines N] [--search <pattern>]

REPO_ROOT=$(git rev-parse --show-toplevel)

# Recent backend output (startup errors, migration failures)
tail -n $LINES "$REPO_ROOT/.dev-logs/backend.log"

# Full tracebacks from app logging (the real errors)
tail -n $LINES "$REPO_ROOT/taskit/taskit-backend/logs/taskit_detail.log"

cd "$REPO_ROOT/taskit/taskit-backend" && python manage.py showmigrations tasks 2>&1 | grep '\[ \]'

tail -n $LINES "$REPO_ROOT/.dev-logs/frontend.log"

tail -n $LINES "$REPO_ROOT/.dev-logs/celery.log"

# Find latest run log
ODIN_WD="$REPO_ROOT/odin/temp_test_dir"
LATEST=$(ls -t "$ODIN_WD/.odin/logs/run_"*.jsonl 2>/dev/null | head -1)

# Show structured entries (formatted)
if [ -n "$LATEST" ]; then
    tail -n $LINES "$LATEST" | python3 -c "
import sys, json
for line in sys.stdin:
    try:
        e = json.loads(line.strip())
        ts = e.get('timestamp','')[:19]
        action = e.get('action','')
        tid = (e.get('task_id','') or '')[:8]
        agent = e.get('agent','')
        dur = e.get('duration_ms','')
        meta = e.get('metadata','')
        print(f'{ts}  {action:<20s}  {tid:<10s}  {agent:<8s}  {dur}ms  {meta}')
    except: pass
"
fi

# Also check odin detail log for tracebacks
tail -n $LINES "$ODIN_WD/.odin/logs/odin_detail.log" 2>/dev/null

ODIN_WD="$REPO_ROOT/odin/temp_test_dir"

# Find the task output file (supports prefix matching)
TASK_FILE=$(ls "$ODIN_WD/.odin/logs/task_${ID}"*.out 2>/dev/null | head -1)

if [ -n "$TASK_FILE" ]; then
    tail -n $LINES "$TASK_FILE"
else
    echo "No output file found for task $ID"
    echo "Available task logs:"
    ls "$ODIN_WD/.odin/logs/task_"*.out 2>/dev/null | sed 's/.*task_/  task_/'
fi

ls "$REPO_ROOT/taskit/taskit-backend/logs/"*"${ID}"*.log 2>/dev/null | while read f; do
    echo "=== $(basename "$f") ==="
    tail -n $LINES "$f"
done

grep -n -i "$PATTERN" "$LOG_FILE" | tail -n $LINES

grep -rn -i "$PATTERN" "$REPO_ROOT/.dev-logs/" "$REPO_ROOT/taskit/taskit-backend/logs/taskit_detail.log" 2>/dev/null | tail -n 30

REPO_ROOT=$(git rev-parse --show-toplevel)
echo "=== Scanning all logs for errors ==="

for log_label_file in \
    "backend:.dev-logs/backend.log" \
    "backend-detail:taskit/taskit-backend/logs/taskit_detail.log" \
    "celery:.dev-logs/celery.log" \
    "odin:odin/temp_test_dir/.odin/logs/odin_detail.log"; do
    label="${log_label_file%%:*}"
    file="$REPO_ROOT/${log_label_file#*:}"
    if [ -f "$file" ]; then
        count=$(grep -c -iE "error|traceback|exception|500" "$file" 2>/dev/null || echo 0)
        if [ "$count" -gt 0 ]; then
            echo ""
            echo "--- $label ($count error lines) ---"
            grep -iE "error|traceback|exception|500" "$file" | tail -5
        fi
    fi
done

© deepklarity, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/hk-local-logs of deepklarity/harness-kit.

Open the folder on GitHubat commit 87305cd