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.
npx agentmods add skills/sliday/harn/trace-loggernpx skills add sliday/harn --skill trace-loggergit clone --depth 1 https://github.com/sliday/harnWhat 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 | $0.00041 | $0.00810 |
| Opus 5 | $0.00020 | $0.00405 |
| Sonnet 5 | $0.00008 | $0.00162 |
| Haiku 4.5 | $0.00004 | $0.00081 |
Grade A, and why
trace-logger scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Trace Logger Skill
Generate a PostToolUse hook that logs all tool calls to JSONL for debugging and eval generation.
Steps
- Create
scripts/harness/trace_logger.shwith the following content:
#!/usr/bin/env bash
# PostToolUse trace logger — appends JSONL to .claude/agent-trace.jsonl
# Non-blocking observability hook. Always exits 0.
set -euo pipefail
# Harn trace logger — records all tool calls for observability
# Why: https://harn.app/kb/evals.html — "Testing Agent Skills Systematically"
command -v jq &>/dev/null || exit 0
LOG_FILE=".claude/agent-trace.jsonl"
mkdir -p "$(dirname "$LOG_FILE")"
# Rotate log if > 5000 lines
if [ -f "$LOG_FILE" ] && [ "$(wc -l < "$LOG_FILE" 2>/dev/null)" -gt 5000 ]; then
tail -2500 "$LOG_FILE" > "${LOG_FILE}.tmp" && mv "${LOG_FILE}.tmp" "$LOG_FILE"
fi
# Read hook JSON payload from stdin
PAYLOAD="$(cat 2>/dev/null || echo '{}')"
# Extract fields with jq, fallback to defaults
TOOL_NAME="$(echo "$PAYLOAD" | jq -r '.tool_name // "unknown"' 2>/dev/null || echo "unknown")"
EXIT_CODE="$(echo "$PAYLOAD" | jq -r '.exit_code // 0' 2>/dev/null || echo "0")"
ARGS_SUMMARY="$(echo "$PAYLOAD" | jq -r '.tool_input // .parameters // {} | tostring' 2>/dev/null | head -c 200 || echo "{}")"
SESSION_ID="${CLAUDE_SESSION_ID:-unknown}"
TIMESTAMP="$(date -u +"%Y-%m-%dT%H:%M:%SZ")"
# Build JSONL entry and append
jq -n -c \
--arg ts "$TIMESTAMP" \
--arg tool "$TOOL_NAME" \
--arg args "$ARGS_SUMMARY" \
--arg exit "$EXIT_CODE" \
--arg sid "$SESSION_ID" \
'{timestamp: $ts, tool_name: $tool, args_summary: $args, exit_code: ($exit | tonumber), session_id: $sid}' \
>> "$LOG_FILE" 2>/dev/null
exit 0
- Make the script executable:
chmod +x scripts/harness/trace_logger.sh
- Wire the hook into
.claude/settings.json. Merge the following into thehooksobject (create if absent):
{
"hooks": {
"PostToolUse": [
{
"matcher": "",
"hooks": [
{
"type": "command",
"command": "bash scripts/harness/trace_logger.sh",
"timeout": 3
}
]
}
]
}
}
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.
- 2d ago First seen · 92 lines · 41 tokens per session scan A 6d29d392e64f
trace-logger is a skill published in the GitHub repository sliday/harn (5 stars, last pushed 4mo ago), licensed MIT. It adds 41 tokens to every session and 810 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…