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 TheSmokeDev/taskchad-os --skill log-triagegit clone --depth 1 https://github.com/TheSmokeDev/taskchad-osWrote 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/thesmokedev/taskchad-os/log-triage)<a href="https://agentmods.dev/skills/thesmokedev/taskchad-os/log-triage"><img src="https://agentmods.dev/badge/skills/thesmokedev/taskchad-os/log-triage/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/thesmokedev/taskchad-os/log-triage"><img src="https://agentmods.dev/badge/skills/thesmokedev/taskchad-os/log-triage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00062 | $0.00485 |
| Opus 5 | $0.00031 | $0.00243 |
| Sonnet 5 | $0.00012 | $0.00097 |
| Haiku 4.5 | $0.00006 | $0.00049 |
Grade A, and why
log-triage 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 6d 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.
What it actually says
Log Triage
Turn noisy logs into a ranked, human-readable incident digest.
Sources
- Bot log — the chat process log (e.g.
bot.log/ whereverrun_chat.shwrites). Start here. - Langfuse — if
LANGFUSE_*is configured, traces give per-request timing, model calls, and errors. See.claude/sections/08_*(observability).
Triage method
- Scope — last N hours, or since the last known-good marker.
- Extract errors — grep for
ERROR/CRITICAL/Traceback/Unhandled. - Cluster — group by normalized message (strip timestamps, IDs, paths) so "the same error 200 times" reads as one cluster with a count.
- Rank — by frequency × severity. The top 1–3 clusters are the headline.
- Diagnose — for each headline cluster: first seen, last seen, count, the representative stack frame, and a one-line hypothesis.
Output
🔧 Log triage — last <window>
1. <normalized error> ×<count>
first <ts> · last <ts>
at <file:line>
likely: <hypothesis>
2. ...
Quiet otherwise: <count> warnings, no other errors.
Keep it to the signal. Do not paste raw log spans — cite file:line and counts.
This skill is read-only; it diagnoses, it does not restart or patch.
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.
- 6d ago First seen · 54 lines · 62 tokens per session scan A e76194a8446b
log-triage is a skill published in the GitHub repository TheSmokeDev/taskchad-os (23 stars, last pushed 3d ago), licensed MIT. It adds 62 tokens to every session and 485 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
skillify-meta-loop
Use when a recurring bug, support question, client incident, or manual task surfaces 2+ times, when a codified rule keeps getting violated despite being written down, when a teammate or client hits an issue anyone could hit, or when delivery/setup friction repeats. Triggers: "skillify this", "this keeps happening"…
diagnose
Use when an AI Brain vault needs a health check or something feels off: Claude ignores CLAUDE.md, journal entries missing from /weekly, hooks not firing, something broke after a git pull, a friend's install misbehaves, Obsidian crashes or pegs the CPU, a .claude/worktrees folder appeared, Granola/WhatsApp/Slack/Gmail…
python-code-quality
Code quality checks, linting, formatting, and type checking commands for the Agent Framework Python codebase. Use this when running checks, fixing lint errors, or troubleshooting CI failures.
wiki-lint
Run a deterministic, read-only health check on an Obsidian wiki. Use for lint, vault health check, audit wiki health, find orphans, find dead links, frontmatter audit, provenance audit, or wiki audit. Reports graph, link, frontmatter, provenance-ledger, empty-section, and stale-index findings; it does not reason…
atmos-introspection
Introspection & Querying: describe/list commands, config filtering, workspace introspection, dependency graphs, YQ integration, --help= scoped CLI help.
atmos-schemas
JSON Schema for Atmos: stack-manifest and atmos.yaml config schemas, IDE auto-completion, validate stacks/schema/config, SchemaStore integration.