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 escoffier-labs/skillet --skill thermometergit clone --depth 1 https://github.com/escoffier-labs/skilletWrote 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/escoffier-labs/skillet/thermometer)<a href="https://agentmods.dev/skills/escoffier-labs/skillet/thermometer"><img src="https://agentmods.dev/badge/skills/escoffier-labs/skillet/thermometer/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/escoffier-labs/skillet/thermometer"><img src="https://agentmods.dev/badge/skills/escoffier-labs/skillet/thermometer.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 | $0.00044 | $0.01086 |
| Opus 5 | $0.00022 | $0.00543 |
| Sonnet 5 | $0.00009 | $0.00217 |
| Haiku 4.5 | $0.00004 | $0.00109 |
Grade A, and why
thermometer 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 10d 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
thermometer
A thermometer turns "slow" into a workload, a metric, and a measured boundary. No optimization starts from intuition alone. The same input, environment, and sampling method must exist before and after the change.
The measurement law
No performance claim without a repeatable baseline and a comparable after measurement. A faster result from a different workload, warm cache, machine, dataset, build mode, or sampling method is not a comparison.
Correctness, security, durability, and accessibility remain requirements. Trading one away for speed requires explicit user approval and must appear in the report.
1. Pin the question
Turn the complaint into one primary metric:
- latency for a named operation and percentile
- throughput under a stated concurrency level
- peak or retained memory for a defined workload
- CPU time or utilization for a named process
- startup time to a defined ready signal
- artifact or bundle size for a named build target
Name the workload, environment, dataset size, cache state, build mode, and target. If no target exists, use the baseline to quantify the opportunity and report the measured result without inventing a service-level objective.
2. Choose the proving command
Prefer the repository's existing benchmark, load test, profiler, tracing setup, or production-like fixture. Otherwise build the smallest repeatable command that exercises the reported path.
The command must produce machine-readable or plainly comparable output. Record tool versions and material environment settings. Avoid a new benchmark framework when a stable existing command can measure the path.
3. Establish the baseline
- Confirm the workload returns correct results.
- Warm up when the runtime, cache, or just-in-time compiler needs it. Keep cold-start work cold when startup is the metric.
- Collect at least five samples unless each run is prohibitively expensive.
- Record the median and range or another spread measure appropriate to the tool.
- Keep raw samples available for review.
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.
- 10d ago First seen · 142 lines · 44 tokens per session scan A 6f74cf2f06ae
thermometer is a skill published in the GitHub repository escoffier-labs/skillet (4 stars, last pushed 9d ago), licensed MIT. It adds 44 tokens to every session and 1,086 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
craft-fix
The Craftsman standard for driving fixes against an existing craft-audit workspace — "fix the findings", "fix SEC-003", "work through the audit", "start the climb". An ACTION skill, not a domain: it picks findings off the master tracker's climb sequence, re-verifies each is still real, gets the user's approval, and…
production-audit
Exhaustive production-readiness audit of any codebase or product. Runs diverse-angle discovery passes until two consecutive passes find nothing new, adversarially verifies every finding against the real code, and reports one flat severity-tagged list with file:line evidence. No summary, no hedging.
spark-engineer
Use when writing Spark jobs, debugging performance issues, or configuring cluster settings for Apache Spark applications, distributed data processing pipelines, or big data workloads. Invoke to write DataFrame transformations, optimize Spark SQL queries, implement RDD pipelines, tune shuffle operations, configure…
Reverse Engineering & Binary Analysis
Binary analysis, assembly interpretation, disassembly, decompilation, firmware RE, and protocol reverse engineering.
log-analyzer
A log-analysis helper that reads application and system logs to find unusual patterns and likely causes. Logs are records of events such as errors, requests, warnings, and service activity.
remove-deadcode
Remove unused code from this project with ultrawork mode, LSP-verified safety, atomic commits. Triggers: remove dead code, dead code, cleanup, remove unused.