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 comisai/comis --skill log-troubleshootinggit clone --depth 1 https://github.com/comisai/comisWrote 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/comisai/comis/log-troubleshooting)<a href="https://agentmods.dev/skills/comisai/comis/log-troubleshooting"><img src="https://agentmods.dev/badge/skills/comisai/comis/log-troubleshooting/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/comisai/comis/log-troubleshooting"><img src="https://agentmods.dev/badge/skills/comisai/comis/log-troubleshooting.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 | $0.00089 | $0.01972 |
| Opus 5.5 | $0.00036 | $0.00789 |
| Sonnet 5.5 | $0.00018 | $0.00394 |
| Haiku 4.5 | $0.00009 | $0.00197 |
Grade A, and why
log-troubleshooting 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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Log Troubleshooting
You have read-only access to the daemon logs directory at ~/.comis/logs/.
This skill bundles scripts/log-digest.py -- a Python CLI that parses NDJSON logs and produces structured, context-friendly summaries. Use it as your primary analysis tool. It uses only Python 3 standard library (no pip install needed).
All script paths below are relative to this skill's directory. Resolve them against the directory containing the manifest file shown in <location> (e.g., if <location> is ~/.comis/skills/log-troubleshooting/SKILL.md, then scripts/log-digest.py means ~/.comis/skills/log-troubleshooting/scripts/log-digest.py).
Invoke the resolved script by its absolute path while keeping the tool working directory inside the execution workspace. Never set cwd to the skill directory; it is outside workspace bounds. In command examples below, replace each relative scripts/... path with its resolved absolute path.
Quick Start
For most troubleshooting requests, start here:
python3 scripts/log-digest.py ~/.comis/logs/daemon.log
This produces a structured summary: entry count, time range, level distribution, top modules, every error and warning as a compact one-liner, slowest operations ranked by duration, and unique error messages with counts. Read the output and report findings to the user -- this single command answers most "what's wrong?" questions.
Log Location and Rotation
| File | Description |
|---|---|
~/.comis/logs/daemon.log |
Active log (current session) |
~/.comis/logs/daemon.1.log |
Most recent rotated log |
~/.comis/logs/daemon.2.log .. daemon.5.log |
Older rotated logs |
Rotation triggers at 10MB per file, 5 rotated files kept.
Start with daemon.log (current) unless investigating a past incident.
Log Format
Each line is a single JSON object (NDJSON / Pino structured logging).
Pino level codes:
| Code | Name | Meaning |
|---|---|---|
| 10 | TRACE | Finest granularity, rarely enabled |
| 20 | DEBUG | Internal steps, tool calls, intermediate state |
| 30 | INFO | Boundary events: started, stopped, request complete |
| 40 | WARN | Degraded but functional |
| 50 | ERROR | Broken functionality |
| 60 | FATAL | Unrecoverable, daemon cannot continue |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 181 lines · 89 tokens per session scan A 15bd17807661
log-troubleshooting is a skill published in the GitHub repository comisai/comis (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 89 tokens to every session and 1,972 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
post-rollback-diagnose
On-demand diagnózis egy sikertelen frissítés + auto-rollback után. A dashboard "Frissítés diagnózisa" gombja indítja (opt-in). NEM cron-vezérelt.
diagnose-skill-run
Diagnose a failed or suspicious Runx skill execution from receipts and harness evidence, then propose the smallest bounded improvement without replaying the failed operation.
postmortem-draft
Turn resolved-incident fragments into a traceable postmortem that separates fragment-cited facts from hypotheses, blocks publication while unknowns remain, and keeps the comms send behind a human gate.
b3os-ai-code-safety
As code and logic grow, the cost is not the happy path — it is coupling: a change ripples into places you did not touch, and a "small fix" breaks something unrelated. This skill is a code-structure and refactoring guide: structure well from the initial design so a change stays local, apply operational safety where…
dos-self-improve
Run the DOS self-improvement loop: propose a candidate, verify it in an isolated worktree, measure suite/truth/metric gates, and keep only confirmed gains. Use for recursive improvement; use dos-enforce-tune for policy knobs.
runtime-diagnostics
Investigate Pioneer Gateway or desktop CPU, memory, slow work, queues, and runtime stalls using process metrics, local snapshots, bounded native profiles, and exact release symbols. Use for Pioneer performance diagnosis and interpreting its diagnostic artifacts.