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/akshay5995/agent-skill-evals/runtime-fieldsnpx skills add akshay5995/agent-skill-evals --skill runtime-fieldsgit clone --depth 1 https://github.com/akshay5995/agent-skill-evalsWhat 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 | $0.00022 | $0.00045 |
| Opus 5 | $0.00011 | $0.00023 |
| Sonnet 5 | $0.00004 | $0.00009 |
| Haiku 4.5 | $0.00002 | $0.00005 |
Grade A, and why
runtime-fields 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 2d 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
runtime-fields
This fixture intentionally pairs a valid skill with malformed runtime test fields.
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.
- 2d ago First seen · 8 lines · 22 tokens per session scan A dfb3cf698670
runtime-fields is a skill published in the GitHub repository akshay5995/agent-skill-evals (2 stars, last pushed 1mo ago), licensed MIT. It adds 22 tokens to every session and 45 once invoked, about $0.0001 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
evaluate-skill
Measure a skill's reliability — run it k times for a pass@k score, design or interpret its eval, or compare it against the base agent. Use when the user wants to run, design, or interpret a skill's eval, or write an .eval.yaml spec.
context-boundary-reporter
Write a machine-checkable context boundary receipt from provided project context files.
alert
Send an operational alert. Use when asked to send an alert, page, or notification.
claude-code-smoke
Use when asked to run the Claude Code smoke evaluation.
grill-skill
Build and harden a skill with evals — interview to design its eval tasks, then run, measure, and iterate. Use when the user wants to create or improve a skill's eval, or run the create → test → improve loop for a skill.
commit-simple
Branch, commit, and push changes. Use when preparing a commit or pushing work.