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 el-feo/ai-context --skill testprofgit clone --depth 1 https://github.com/el-feo/ai-contextWrote 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/el-feo/ai-context/testprof)<a href="https://agentmods.dev/skills/el-feo/ai-context/testprof"><img src="https://agentmods.dev/badge/skills/el-feo/ai-context/testprof/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/el-feo/ai-context/testprof"><img src="https://agentmods.dev/badge/skills/el-feo/ai-context/testprof.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 | $0.00113 | $0.01966 |
| Opus 5.5 | $0.00045 | $0.00786 |
| Sonnet 5.5 | $0.00023 | $0.00393 |
| Haiku 4.5 | $0.00011 | $0.00197 |
Grade A, and why
testprof 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TestProf: RSpec Performance Optimization
Expert guidance for diagnosing and fixing slow RSpec test suites. Based on field-tested techniques from Evil Martians' work reducing a 30,000-spec Rails suite from 4m30s to 2m (and targeting 1m30s with parallelization).
The core idea: slow test suites are rarely slow for one reason. They're slow for a handful of fixable reasons, stacked. This skill walks you through diagnosing which reasons apply, then fixing each one — in an order that avoids wasted effort.
How to use this skill
When a user brings a slow RSpec suite, investigate their actual codebase before prescribing anything. A skill full of generic advice is worse than useless — the value is in mapping the general patterns onto their specific code. Follow this order:
- Characterize the problem — ask for total runtime, example count, and whether it's "slow everywhere" or "slow in specific files." This determines which profiler to run first.
- Investigate concretely, don't speculate. Before giving advice, actually:
- Read
spec/spec_helper.rbandspec/rails_helper.rbfor suspicious requires (rubocop/rspec/support, SimpleCov config, global hooks). - Grep the
Gemfilefor the suspects: SimpleCov, blind_index, any encryption gem, retry gems (retriable, Faraday retry middleware). - For slow individual specs, read the service file being tested — grep for
sleep,retry,ObjectSpace,create_list(:...,with large numbers. - Look at the factory definitions for the types involved. Association fan-out is a common cause. This is the difference between a suggestion list and a diagnosis. Always do the investigation first.
- Read
- Run the right diagnostic next — see "Diagnostic decision tree" below. If Claude can't run the profiler (no shell access to the user's env), write the exact commands the user should run and explain how to interpret the output.
- Apply fixes in order of payoff — coverage and GC issues often give the biggest single wins and require the least invasive changes, so check them before rewriting specs.
- Measure after each change — keep the before/after numbers so you can tell what worked.
What ships with it
4 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 · 120 lines · 113 tokens per session scan A ef42909e28ca
testprof is a skill published in the GitHub repository el-feo/ai-context (12 stars, last pushed 2mo ago), licensed MIT. It adds 113 tokens to every session and 1,966 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.