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 Shailesh200/prism --skill prism-verify-regressiongit clone --depth 1 https://github.com/Shailesh200/prismWrote 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/shailesh200/prism/prism-verify-regression)<a href="https://agentmods.dev/skills/shailesh200/prism/prism-verify-regression"><img src="https://agentmods.dev/badge/skills/shailesh200/prism/prism-verify-regression.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 | $0.00070 | $0.00490 |
| Opus 5 | $0.00035 | $0.00245 |
| Sonnet 5 | $0.00014 | $0.00098 |
| Haiku 4.5 | $0.00007 | $0.00049 |
Grade A, and why
prism-verify-regression 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
Verify the change, not the whole repository
"Run the tests" is either too slow to be useful or too narrow to be meaningful. The useful version is: work out which tests cover what changed, run those, and say what is still unverified.
The procedure
1. Find what changed. changed_paths if the user did not say. It reports
the working-tree and branch diff.
2. Select the suite. test_impact on those paths returns the tests that
cover them.
Report gaps out loud. If a changed path has no test covering it, that is the single most valuable finding here — running a green suite that never touches the change is worse than not running it, because it manufactures confidence.
3. Run them with your own tools. Prism selects; it does not execute. Use the editor's test runner, terminal, or task tools.
4. For anything user-facing, drive the browser. If the change touches routes,
components or interaction, use your Playwright or browser tools to exercise the
affected flow. blast_radius on a changed component tells you which screens to
check — that is how you avoid testing only the one page the user mentioned.
5. Report honestly. Three separate categories, never merged:
- what you ran and it passed
- what you ran and it failed
- what you did not run, and why
The third is the one that gets dropped, and it is the one that matters. "No Playwright configured, so the checkout flow is unverified" is a useful sentence. Silence in its place is a false all-clear.
Boundaries
Prism has no test runner and no browser. It reads the repository and names the tests. If the editor has no way to run them, say the suite was selected but not executed — do not report a selection as a result.
Never describe a test as passing unless you saw it pass in this session.
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 · 49 lines · 70 tokens per session scan A f7545224ff9f
prism-verify-regression is a skill published in the GitHub repository Shailesh200/prism (3 stars, last pushed today), licensed MIT. It adds 70 tokens to every session and 490 once invoked, about $0.0003 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 2026-09-05.
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.