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 xiaolai/eou-foundry --skill generate-regression-casesgit clone --depth 1 https://github.com/xiaolai/eou-foundryWrote 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/xiaolai/eou-foundry/generate-regression-cases)<a href="https://agentmods.dev/skills/xiaolai/eou-foundry/generate-regression-cases"><img src="https://agentmods.dev/badge/skills/xiaolai/eou-foundry/generate-regression-cases.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 5.1 | $0.00231 | $0.01131 |
| Opus 5 | $0.00115 | $0.00566 |
| Sonnet 5 | $0.00046 | $0.00226 |
| Haiku 4.5 | $0.00023 | $0.00113 |
Grade A, and why
generate-regression-cases 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 8d 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generate Regression Cases
Convert $source (one or more incident reports or audit failures) into candidate regression cases.
Inputs
$source(required) — path to one or more incident reports or audit failure files. Accepts a direct file path or a glob (e.g.,foundry/audits/incidents/*.yml). Every matched file must contain at least one observable failure symptom.
Required reading
foundry/failure-taxonomy.yml— classify each failure by F-codefoundry/constitution.yml— invariants that constrain what counts as a valid regression caseschemas/incident.schema.yml— validate structured YAML incident files against this schemaschemas/regression-case.schema.yml— the schema for the output regression case files
Stop conditions
Halt and report before generating cases if:
$sourceresolves to no readable files.- No observable failure symptom can be extracted from any source file — labels and conclusions without at least one observable symptom (error message, wrong output, missing artifact, schema mismatch) are not accepted as source input.
schemas/regression-case.schema.ymldoes not exist — cannot validate output structure.
Procedure
- Load
$source. If it is a glob, read all matching files. - For each incident or audit failure, extract the observable failure symptom.
- Classify the failure using
foundry/failure-taxonomy.yml(F1–F12). - Derive the regression case: the minimal input that reproducibly triggers the failure.
- Construct the fixture path:
foundry/self-evolution/regression/fixtures/{case_id}/. - Check
foundry/self-evolution/regression/cases/for existing cases that cover this failure — skip if a duplicate exists; record the duplicate case ID instead. - For each new case, write the regression case file with all required fields.
- Set
activation_status: candidateon all generated cases — neveractive.
Required fields per case (per schemas/regression-case.schema.yml)
id: # regression-{eou_id}-{failure_class}-{YYYYMMDD}
source_incident_id: # incident or audit ID this case was derived from
failure_class: # F1-F12 code
eou_id: # EOU that exhibited the failure
fixture_path: # foundry/self-evolution/regression/fixtures/{case_id}/
failure_shape_assertion: # observable output that indicates the failure is occurring (non-empty)
activation_status: # candidate — never active without human approval
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.
- 8d ago First seen · 91 lines · 231 tokens per session scan A ca89525a5e68
generate-regression-cases is a skill published in the GitHub repository xiaolai/eou-foundry (10 stars, last pushed 14d ago), licensed ISC. It adds 231 tokens to every session and 1,131 once invoked, about $0.0012 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
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.
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".
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
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.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.