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 paruff/uFawkesAI --skill continuous-evalsgit clone --depth 1 https://github.com/paruff/uFawkesAIWrote 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/paruff/ufawkesai/continuous-evals)<a href="https://agentmods.dev/skills/paruff/ufawkesai/continuous-evals"><img src="https://agentmods.dev/badge/skills/paruff/ufawkesai/continuous-evals/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/paruff/ufawkesai/continuous-evals"><img src="https://agentmods.dev/badge/skills/paruff/ufawkesai/continuous-evals.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 | $0.00072 | $0.00866 |
| Opus 5.5 | $0.00029 | $0.00346 |
| Sonnet 5.5 | $0.00014 | $0.00173 |
| Haiku 4.5 | $0.00007 | $0.00087 |
Grade A, and why
continuous-evals 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 17d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: continuous-evals
Load trigger: "load continuous-evals skill" > DORA: AI Capability 7: Quality internal platforms Token cost: Low to load; a run costs one cheap-model call per task
Purpose
Agent configuration is code: a reworded rule or a retired skill can silently change what agents do. This skill makes configuration changes regression-safe the same way tests make code changes safe.
How it works
| Piece | Path |
|---|---|
| Tasks (one JSON file each) | .agents/evals/tasks/*.json |
| Baseline rate per rubric dimension | .agents/evals/baseline.json |
| Runner | scripts/run-evals.sh |
| Gate's own self-test (offline, stub agent) | scripts/test-run-evals.sh |
| CI gate | .github/workflows/agent-config-ci.yml |
Each task runs in a throwaway copy of the working tree (CI: OpenCode; locally
claude -p by default) with a per-task timeout, and is scored on three rubric
dimensions from its transcript:
- task success —
expect:output_regex,file_absent,file_present; - tool use —
rubric.tool_use.forbidden/required: anchored, case-insensitive regexes over tool names, MCP tools included; - trajectory —
rubric.trajectory.max_steps: model steps taken.
The run fails if any dimension's rate drops below baseline.json, if there
are no tasks, or if a task has no expectation or no rubric. CI runs it on
config changes, on pushes to main, and weekly.
A non-zero agent exit also fails a task, unless it sets
"ignore_agent_exit": true in expect: use that only for "must not happen"
tasks (e.g. protected-env) where a blocked tool call may legitimately exit
non-zero. A crashed agent also leaves a file absent, so never use it for tasks
that expect a positive result.
Procedure
- Changing configuration? Run
scripts/run-evals.shbefore pushing. CI runs it anyway on any change toAGENTS.md,.agents/,.claude/,.opencode/, hooks, or.pre-commit-config.yaml. - An agent got something wrong in real work? Add a task that reproduces it:
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.
- 17d ago Changed · +13 lines 1407d5b7e1a7
- 20d ago Changed · +5 lines cf9e16ef6eed
- 21d ago First seen · 63 lines · 72 tokens per session scan A 2b2a9ebf6a3c
continuous-evals is a skill published in the GitHub repository paruff/uFawkesAI (2 stars, last pushed yesterday), licensed MIT. It adds 72 tokens to every session and 866 once invoked, about $0.0003 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 2026-09-30.
Other skills, from other repositories
working-effectively-with-legacy-code
Apply Michael Feathers-inspired legacy-code rules when changing hard-to-test code safely with characterization tests, seams, sprout methods, or wrap methods.
refactoring-guru
Apply Refactoring.Guru-inspired rules when diagnosing code smells, choosing refactoring techniques, and stopping cleanup before uncontrolled redesign.
refactoring
Apply Martin Fowler-inspired refactoring rules when improving existing code structure while preserving observable behavior.
generate-tests
Use when the user asks to generate, create, write, or add unit tests for existing code, or to cover a class, method, or file with tests — including Java targets using JUnit 5, Mockito, or AssertJ. Not for analysis-only requests that stop at listing test cases.
generate-test-cases
Use when the user asks to analyze code for test coverage, list what test cases are needed, or review testing strategy — WITHOUT generating actual test code.
template-formal
Strongly-typed multiagent ant-robot colony exemplar — ADTs, session-typed protocols, affine-discipline resource handles, storage-as-functor framing, Active-Inference-flavored decision loop, mypy-as-oracle negative controls.