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 arunveersingh/ai --skill day-18-regression-harnessgit clone --depth 1 https://github.com/arunveersingh/aiWrote 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/arunveersingh/ai/day-18-regression-harness)<a href="https://agentmods.dev/skills/arunveersingh/ai/day-18-regression-harness"><img src="https://agentmods.dev/badge/skills/arunveersingh/ai/day-18-regression-harness/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/arunveersingh/ai/day-18-regression-harness"><img src="https://agentmods.dev/badge/skills/arunveersingh/ai/day-18-regression-harness.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 | $0.00106 | $0.01396 |
| Opus 5.5 | $0.00042 | $0.00558 |
| Sonnet 5.5 | $0.00021 | $0.00279 |
| Haiku 4.5 | $0.00011 | $0.00140 |
Grade A, and why
regression-harness 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 5d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Regression harness
A food delivery app's AI tags each dish's allergens, and the allergy filter hides tagged dishes. The eval has 1,307 cases on four lines: 1,200 everyday dishes (bar 95%), 80 harm dishes with peanuts, tree nuts or sesame, 12 past mistakes where the allergen hid in a component (satay, praline, hummus), and 15 restaurant texts claiming a dish is safe. All green, but run only after prompt edits. In nine days: prompt v12 ("tag an allergen only if the ingredient list names it") fixes one case and breaks three incident cases; the provider's "latest" alias moves to a new snapshot and two attacks get through; the menu-import team cuts dish text at 300 characters and 9 harm dishes lose their allergen. Only the prompt change was tested, on the one case it meant to fix; the other two weren't tested at all. A shawarma wrap loses "tahini (sesame)" off the end of its list and a customer with a sesame allergy ends up in the emergency room. With a harness that runs every case on every change, each change is blocked on its first run.
Untouched is not unchanged. If anything the step reads changed, every case runs again.
Part A — Ask (project rules)
Whenever you change anything an AI step reads (prompt, model, tool, input format, reference data):
1. TOUCHES: name which of those this change touches. If unsure, say all.
2. RUN: the full harness, every case on every line. Never a subset.
3. REPORT: fingerprint old vs new, each line old vs new, and
fixed: <case ids> | broke: <case ids>
4. If any line fails or any case broke, stop and reply:
REGRESSION | <line> | <case ids> | <change that caused it>
Never set a model ID to an alias like "latest". Never edit a case or a label to get green.
Done means the harness passed on exactly the configuration being shipped.
In an orchestrated flow (spec → plan → tasks → implement): next to each AI step in the spec, list what it reads (prompt, model snapshot, tools, data); that list is the manifest. The first task for the step is the one-command harness, and every later task ends with its output. In CI, any diff touching a manifest item runs the harness, even in another team's repo, and deploy accepts only a fingerprint that passed.
What ships with it
2 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.
- 5d ago First seen · 63 lines · 106 tokens per session scan A 30da3e6323ef
regression-harness is a skill published in the GitHub repository arunveersingh/ai (3 stars, last pushed 3d ago), licensed Apache-2.0. It adds 106 tokens to every session and 1,396 once invoked, about $0.0004 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 2026-10-21.
Other skills, from other repositories
cli-eval
Create and run evaluation suites, watch live benchmark progress, view scorecards, compare model performance, and integrate eval runs with CI workflows from the CLI.
model-merging
Merge multiple fine-tuned models using mergekit to combine capabilities without retraining. Use when creating specialized models by blending domain-specific expertise (math + coding + chat), improving performance beyond single models, or experimenting rapidly with model variants. Covers SLERP, TIES-Merging, DARE, Task…
darwinian-evolver
Evolve prompts/regex/SQL/code with Imbue's evolution loop.
dummy-dataset
Generate realistic dummy datasets for testing with customizable columns, constraints, and output formats (CSV, JSON, SQL, Python script). Use when creating test data, building mock datasets, or generating sample data for development and demos.
validate
Validate Semantica pipelines, extraction quality, graph schemas, and ontology consistency. Returns structured error/warning checklists. Uses PipelineValidator, PipelineBuilder.validatepipeline(), GraphValidator, and OntologyValidator. Sub-commands: pipeline, step, dependencies, extraction, graph, ontology, performance.
launching-evals
Run, monitor, analyze, and debug LLM evaluations via nemo-evaluator-launcher. Covers running evaluations, checking status and live progress, debugging failed runs, exporting artifacts and logs, and analyzing results. ALWAYS triggers on mentions of running evaluations, checking progress, debugging failed evals…