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 skills add turmyshevd/openclawgotchi --skill logginggit clone --depth 1 https://github.com/turmyshevd/openclawgotchiWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/turmyshevd/openclawgotchi/logging)<a href="https://agentmods.dev/skills/turmyshevd/openclawgotchi/logging"><img src="https://agentmods.dev/badge/skills/turmyshevd/openclawgotchi/logging/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/turmyshevd/openclawgotchi/logging"><img src="https://agentmods.dev/badge/skills/turmyshevd/openclawgotchi/logging.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00016 | $0.00613 |
| Opus 5.5 | $0.00006 | $0.00245 |
| Sonnet 5.5 | $0.00003 | $0.00123 |
| Haiku 4.5 | $0.00002 | $0.00061 |
Grade A, and why
Logging 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 1mo 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Logging
You have several log sinks. Use them so you (and Dmitry) can see what broke and when.
Where logs are
| What | Where | How to read |
|---|---|---|
| Critical errors | data/ERROR_LOG.md |
read_file("data/ERROR_LOG.md") or tool log_error() to append |
| Display failures | data/display_error.log |
read_file("data/display_error.log") — written by gotchi_ui.py on crash |
| Daily notes | memory/YYYY-MM-DD.md |
write_daily_log(entry) to append; read via read_file |
| Code changes | CHANGELOG.md |
log_change(description) to append |
| Service / system | journalctl | manage_service(gotchi-bot, logs) or bash journalctl -u gotchi-bot -n 50 |
| Conversation | gotchi.db (messages) |
recall_messages(limit) |
When to use what
-
Something broke (display, service, disk, health):
Calllog_error("short description")so it’s indata/ERROR_LOG.md. Then you can say “last error was …” or read the file when asked. -
health_check() found problems:
Calllog_error("health_check: <what’s wrong>")so there’s a record. -
User says “what went wrong”:
Readdata/ERROR_LOG.md(and optionallydata/display_error.log) and summarize. -
Daily / notable events:
Usewrite_daily_log(entry). -
You changed code/config:
Uselog_change(description).
No direct system log “tool”
You don’t have a function that returns raw system logs; use manage_service(service, action=logs) or execute_bash("journalctl -u gotchi-bot -n 50") when you need recent service output.
Size limits (so we don't fill disk on Pi)
- ERROR_LOG.md — only last 300 lines kept; older lines are dropped when appending.
- display_error.log — only last 200 lines kept.
- Daily logs and CHANGELOG are not auto-trimmed; trim manually if needed.
Summary
- Errors →
log_error(message)→data/ERROR_LOG.md - Display crash → already in
data/display_error.log(no tool needed) - “When did something break?” → read
data/ERROR_LOG.md
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.
- 1mo ago First seen · 61 lines · 16 tokens per session scan A 9f241ba6b526
Logging is a skill published in the GitHub repository turmyshevd/openclawgotchi (51 stars, last pushed 4mo ago), licensed MIT. It adds 16 tokens to every session and 613 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
gh-issues
Fetch GitHub issues, spawn sub-agents to implement fixes and open PRs, then monitor and address PR review comments. Usage: /gh-issues [owner/repo] [--label bug] [--limit 5] [--milestone v1.0] [--assignee @me] [--fork user/repo] [--watch] [--interval 5] [--reviews-only] [--cron] [--dry-run] [--model glm-5]…
orca-replay
Answers questions about a past agent run from its recording rather than from memory, and replays or forks that run. Use when asked why an earlier run did something, or to reproduce a failure.
arxiv-agentic-verifier
Source Paper: Scaling Agentic Verifier for Competitive Coding (ID: 4a4c4dae6a5145ebc4d62eb2d64b0f0f) Type: Code Verification / Test Generation.
openclaw-tune
OpenClaw system-level maintenance — cleans sessions/.bak rotation, disk bloat under /.openclaw/, validates model fallback chain, audits cron health, prunes short-term-recall noise. Run after openclaw update or every 1-2 weeks. Different from workspace document tune-up (single-responsibility canonical .md files, token…
incident-response
Framework for managing incidents from detection through postmortem. Use during active incidents, for creating runbooks, or when conducting postmortems.
agent-browser
A command-line tool for controlling a web browser without a visible window. It can open pages, inspect their accessibility structure, interact with forms, take screenshots, create PDFs, and run JavaScript.