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/understudylabs/understudy-agent-tools/watch-logsnpx skills add understudylabs/understudy-agent-tools --skill watch-logsgit clone --depth 1 https://github.com/understudylabs/understudy-agent-toolsWrote 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/understudylabs/understudy-agent-tools/watch-logs)<a href="https://agentmods.dev/skills/understudylabs/understudy-agent-tools/watch-logs"><img src="https://agentmods.dev/badge/skills/understudylabs/understudy-agent-tools/watch-logs.svg" alt="Measured on agentmods" 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 | $0.00089 | $0.01375 |
| Opus 5 | $0.00044 | $0.00687 |
| Sonnet 5 | $0.00018 | $0.00275 |
| Haiku 4.5 | $0.00009 | $0.00137 |
Grade A, and why
watch-logs scanned grade A with 1 finding 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 3d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
(log file paths/globs, command outputs such as a `curl` health probe), How it starts
The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Watch Logs
Stand up a scheduled log/event review that is cheap by construction: a
deterministic trigger script snapshots the watched sources, hashes them, and
only when the hash changes does an inexpensive LLM review fire. The review
itself is a small, well-bounded workload — summarize what changed, cite lines,
say "nothing wrong" honestly — sized so a tiny open model (Gemma 2B class)
could eventually serve it. Every review is recorded from day one as an
understudy.eval_result.v1 row, so the workload accumulates training-grade
evidence without any training now.
When to use
The developer wants recurring "look at my logs/events and tell me what's
wrong" monitoring. This skill owns the watcher loop: interview → config →
deterministic trigger → gated review → eval-row capture. For turning existing
LLM traces into evals use ../ingest-traces/SKILL.md;
for building a frozen eval from the accumulated reviews use
../capture-evidence/SKILL.md; for eventually
distilling the review onto a small model use
../distill-classifier/SKILL.md.
Safety Gates
- Deterministic gate before any spend. Never wire a scheduler directly to a model call. The trigger script must run first; a review fires only on exit code 1 (changed). Unchanged state costs zero tokens.
- Logs may contain secrets. Snapshots stay local under
~/.understudy/watch-logs/. Before any remote review route (gateway or provider), confirm with the developer what the logs can contain and prefer a local model slot for sensitive logs; never upload raw snapshots anywhere. - Approve the review route and spend bound once, up front (model, route, max tokens, cadence). The cron/launchd job then runs unattended inside that bound. No new routes or models without re-approval.
- Command sources run arbitrary shell. Only put commands in the watch config that the developer typed or explicitly approved; show the final config before installing any schedule.
- Honest reviews only. The prompt contract requires "nothing wrong" when nothing is wrong, and citations for every claimed anomaly. Do not tune the prompt toward always finding something.
What ships with it
2 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.
- 3d ago First seen · 110 lines · 89 tokens per session scan A 7c66207f136d
watch-logs is a skill published in the GitHub repository understudylabs/understudy-agent-tools (16 stars, last pushed 4d ago), licensed MIT. It adds 89 tokens to every session and 1,375 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
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…