sentinel-dv: Skill for Claude Code

.agents/skills/sentinel-dv-regression-triage/SKILL.md

sentinel-dv-regression-triage is a skill for Claude Code, Codex from kiranreddi/sentinel-dv. It costs 68 tokens per session (895 once invoked), scanned A, original, Apache-2.0.

A tool for investigating failed SystemVerilog, UVM, or cocotb test runs. These are hardware-design testing technologies used to check whether a chip behaves correctly.

In plain words
What is it for?
Use it to assess a regression run, explain a drop in pass rate, group related failures, compare results with a baseline, and write a traceable failure report.
Why use it?
It helps separate real design failures from build problems, assertion errors, timeouts, simulator differences, and flaky tests. It bases the explanation on recorded run and failure evidence.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present. Also seen: installed under .agents/ (shared by several agents).

This is kiranreddi/sentinel-dv's own configuration. It tells Claude Code and Codex how to work on sentinel-dv itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything sentinel-dv configures →

Part of the sentinel-dv plugin — 3 skills, 1 MCP server shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to kiranreddi/sentinel-dv. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/kiranreddi/sentinel-dv/main/.agents/skills/sentinel-dv-regression-triage/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/kiranreddi/sentinel-dv

Made for: Claude Code, Codex.

Or install sentinel-dv, the plugin that ships this one along with the rest of its 3 skills, 1 MCP server.

Wrote 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.

agentmods badge for sentinel-dv-regression-triage

README.md
[![agentmods](https://agentmods.dev/badge/skills/kiranreddi/sentinel-dv/sentinel-dv-regression-triage/github.svg)](https://agentmods.dev/skills/kiranreddi/sentinel-dv/sentinel-dv-regression-triage)
Your own site
<a href="https://agentmods.dev/skills/kiranreddi/sentinel-dv/sentinel-dv-regression-triage"><img src="https://agentmods.dev/badge/skills/kiranreddi/sentinel-dv/sentinel-dv-regression-triage/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.

agentmods 80×15 button for sentinel-dv-regression-triage

Your own site · 80×15
<a href="https://agentmods.dev/skills/kiranreddi/sentinel-dv/sentinel-dv-regression-triage"><img src="https://agentmods.dev/badge/skills/kiranreddi/sentinel-dv/sentinel-dv-regression-triage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 895 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00068 $0.00895
Opus 5 $0.00034 $0.00447
Sonnet 5 $0.00014 $0.00179
Haiku 4.5 $0.00007 $0.00089

Measured 12d ago against content hash 2107a5aee114, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

sentinel-dv-regression-triage 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 12d 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.

.agents/skills/sentinel-dv-regression-triage/SKILL.md · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sentinel DV Regression Triage

Turn an indexed regression into a traceable, prioritized report. Preserve every returned identifier and distinguish observed facts from heuristics.

Inputs

Accept a run_id, suite, CI build reference, or a request to find the latest failing run. Ask for a baseline only when the requested comparison cannot be resolved from indexed runs.

Preflight

  1. Confirm the Sentinel DV tools are available by calling runs.list with page=1.
  2. If the tool is unavailable, stop and report that the Sentinel DV MCP server must be configured and its artifact store indexed.
  3. Treat empty results as an indexing or scope condition, not as a passing regression.

Workflow

  1. Resolve the target with runs.list using the narrowest supported filters. Do not invent time filters. Use runs.get for CI metadata and runs.summary for counts.
  2. Call regression.health with run_id or suite. Treat the score as a scoped indicator whose unavailable components are null, omitted from effective_weights, and explained in data_quality; it is not independent sign-off proof.
  3. For suite history, call regressions.summary with suite, window_days, and an explicit as_of when reproducibility matters.
  4. Call tests.cluster for the run. Rank using distinct_test_count, failure_count, severity, category, and recurrence. Clusters are signature heuristics, not established root causes. Disclose clusters_truncated.
  5. If a baseline exists, call runs.diff. Separate new_failures, persistent_failures, resolved_failures, test changes, and coverage_deltas.
  6. For leading clusters, page through failures.list with run_id or representative test_id and include_evidence=true. Continue until all pages in the intended scope are read or state the exact bounded subset.
  7. Page through assertions.failures when assertions are implicated. Resolve relevant definitions with assertions.get.
  8. Use tests.history for the logical test cohort. Its is_flaky field means mixed pass/fail outcomes in a bounded indexed history; report it as a flakiness signal, not proof.
  9. Use runs.cross_sim only when multiple simulators are relevant. Its comparisons are latest-result cohorts matched by suite, framework, DUT top, and test name.
  10. Deepen only the highest-impact unresolved cases with tests.get, tests.topology, wave.summary, or wave.signals.

Read the full file on GitHub · 57 lines

Files

What ships with it

1 file 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.

Changes

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.

  1. 12d ago First seen · 57 lines · 68 tokens per session scan A 2107a5aee114

Subscribe to this mod's changes

sentinel-dv-regression-triage is a skill published in the GitHub repository kiranreddi/sentinel-dv (4 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 68 tokens to every session and 895 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 2026-08-31.