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 rysh-ai/rysh-cli-code --skill log-watchergit clone --depth 1 https://github.com/rysh-ai/rysh-cli-codeWrote 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/rysh-ai/rysh-cli-code/log-watcher)<a href="https://agentmods.dev/skills/rysh-ai/rysh-cli-code/log-watcher"><img src="https://agentmods.dev/badge/skills/rysh-ai/rysh-cli-code/log-watcher/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/rysh-ai/rysh-cli-code/log-watcher"><img src="https://agentmods.dev/badge/skills/rysh-ai/rysh-cli-code/log-watcher.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 | $0.00024 | $0.00314 |
| Opus 5.5 | $0.00010 | $0.00126 |
| Sonnet 5.5 | $0.00005 | $0.00063 |
| Haiku 4.5 | $0.00002 | $0.00031 |
Grade A, and why
log-watcher 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.
What it actually says
You read logs and report anomalies. You are read-only: you never rotate, truncate, delete, or rewrite a log, and you never restart the service that produced it.
Method
- Establish the baseline first: what does a normal minute of this log look like? Skim the healthy region before staring at the errors.
- Find the first bad line, not the loudest one. Cascading failures bury the cause under symptoms; walk backwards from the burst to the moment the log changed character.
- Correlate: same timestamp window across files (
grep,globfor rotated siblings). A burst that starts in one component and spreads is a dependency arrow — say which direction it points.
Report
- What: the error signature, quoted verbatim (one line, trimmed).
- When: first occurrence timestamp and the burst window.
- Where: file and component; the upstream suspect if correlation shows one.
- Root-cause candidate: your best single hypothesis and what evidence would confirm or kill it. One hypothesis, ranked alternatives only if the evidence is genuinely split.
Counts matter: "1,204 timeouts in 90s" beats "many errors". If the log shows nothing anomalous, say so — do not manufacture an incident.
What ships with it
3 files 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 · 32 lines · 24 tokens per session scan A df08bd49f0ec
log-watcher is a skill published in the GitHub repository rysh-ai/rysh-cli-code (5 stars, last pushed 11d ago), licensed Apache-2.0. It adds 24 tokens to every session and 314 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
codegraph
Analyze indexed codebases via graph database (neug) and vector index (zvec). Covers call graphs, dependencies, dead code, hotspots, module coupling, architecture reports, semantic search, impact analysis, bug root cause from GitHub issues, class diagrams (UML), and PR review (risk scoring, conflict detection…
stuck
Diagnose frozen, stuck, or slow Qwen Code sessions on this machine. Scans for problematic processes, high CPU/memory usage, hung subprocesses, and debug logs. Use /stuck or /stuck to focus on a specific process.
structured-debugging
Hypothesis-driven debugging methodology for hard bugs. Use this skill whenever you're investigating non-trivial bugs, unexpected behavior, flaky tests, or tracing issues through complex systems. Activate proactively when debugging requires more than a quick glance — especially when the first attempt at a fix didn't…
test-failure-explorer
Import and query an existing Vitest 3.2 JSON report to explore test failures, file-level errors and original diagnostic evidence.
printing-press-polish
Polish a generated CLI to pass verification and become publish-ready. Runs diagnostics (dogfood, verify, scorecard, go vet, gosec), automatically fixes all issues (verify failures, static-analysis findings, dead code, descriptions, README, MCP tool quality), reports the before/after delta, and offers to publish. Use…