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 jxoesneon/Ciel --skill ai-regression-testinggit clone --depth 1 https://github.com/jxoesneon/CielWrote 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/jxoesneon/ciel/ai-regression-testing)<a href="https://agentmods.dev/skills/jxoesneon/ciel/ai-regression-testing"><img src="https://agentmods.dev/badge/skills/jxoesneon/ciel/ai-regression-testing/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/jxoesneon/ciel/ai-regression-testing"><img src="https://agentmods.dev/badge/skills/jxoesneon/ciel/ai-regression-testing.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 | $0.00018 | $0.00564 |
| Opus 5 | $0.00009 | $0.00282 |
| Sonnet 5 | $0.00004 | $0.00113 |
| Haiku 4.5 | $0.00002 | $0.00056 |
Grade A, and why
ai-regression-testing 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 9d 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
CIEL ADAPTATION: AI Regression Testing
This skill provides CIEL's specialized testing strategy for mitigating systematic blind spots in AI-assisted development. It focuses on contract-first verification and sandbox/production parity.
Integration Context
Adapted from ~/.agents/skills/ai-regression-testing/. This skill complements the core TDD mandate by targeting common AI failure patterns, such as "hallucinated success" and path inconsistency.
Core Patterns
1. Sandbox/Production Parity
Problem: AI fixes the production path but forgets the sandbox/mock path (or vice versa). Solution: Assert identical response shapes in both modes.
2. Contract Verification
Problem: AI adds a field to the response object but forgets to include it in the underlying data query (e.g., SELECT clause). Solution: Assert all required fields exist in the final API response.
3. Error/State Integrity
Problem: old data persists in the UI after an error, or optimistic updates lack proper rollback. Solution: Explicit tests for state cleanup and restoration on failure.
Orchestration Logic
1. Post-Fix Verification
After every bug fix (via systematic-debugging), CIEL must generate a specific regression test named after the bug (e.g., BUG-R1 regression).
2. Bug-Check Workflow
Run npm run test and npm run build before any AI-led code review to catch mechanical failures early.
3. Strategy: Test Where Bugs Cluster
Focus testing effort on auth, multi-path logic, and state management where AI regressions are most frequent. Do not aim for 100% coverage; aim for 100% regression prevention.
Original Documentation preserved at source.
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.
- 9d ago First seen · 72 lines · 18 tokens per session scan A eef65c0247c2
ai-regression-testing is a skill published in the GitHub repository jxoesneon/Ciel (1 stars, last pushed 2d ago), licensed Apache-2.0. It adds 18 tokens to every session and 564 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
mutation-testing
Use when adding or reviewing a gate, guard rule, CI grep, or test assertion in this plugin's own scripts — and whenever a suite is green and you need to know whether that means anything. Runs scripts/mutate.sh, which breaks the code on purpose and reports which assertions failed to notice. Triggers from code-reviewer…
aidex-bugfix
Use when fixing a bug, resolving a reported issue, or when something is broken and needs a test-driven fix — investigate root cause, write a failing regression test (RED), implement the minimum fix, confirm the test passes (GREEN), then commit test and fix together. Fires on "fix this bug", "this is broken", "it's not…
workflow-test-fix
Unified test-fix pipeline combining test generation (session, context, analysis, task gen) with iterative test-cycle execution (adaptive strategy, progressive testing, CLI fallback). Triggers on "workflow-test-fix", "test fix workflow".
tdd-workflow
Use this skill when writing new features, fixing bugs, or refactoring code. Enforces test-driven development with 80%+ coverage including unit, integration, and E2E tests.
tdd-guide
Test-Driven Development specialist enforcing write-tests-first methodology. Use PROACTIVELY when writing new features, fixing bugs, or refactoring code. Ensures 80%+ test coverage.
build-test
Run the project's build / typecheck / lint / test commands and emit the build.passing + tests.passing signals devloop convergence reads.