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.
curl -O https://raw.githubusercontent.com/kiranreddi/sentinel-dv/main/.agents/skills/sentinel-dv-regression-triage/SKILL.mdgit clone --depth 1 https://github.com/kiranreddi/sentinel-dvWrote 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/kiranreddi/sentinel-dv/sentinel-dv-regression-triage)<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.
<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>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 | $0.00068 | $0.00895 |
| Opus 5 | $0.00034 | $0.00447 |
| Sonnet 5 | $0.00014 | $0.00179 |
| Haiku 4.5 | $0.00007 | $0.00089 |
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.
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
- Confirm the Sentinel DV tools are available by calling
runs.listwithpage=1. - If the tool is unavailable, stop and report that the Sentinel DV MCP server must be configured and its artifact store indexed.
- Treat empty results as an indexing or scope condition, not as a passing regression.
Workflow
- Resolve the target with
runs.listusing the narrowest supported filters. Do not invent time filters. Useruns.getfor CI metadata andruns.summaryfor counts. - Call
regression.healthwithrun_idorsuite. Treat the score as a scoped indicator whose unavailable components arenull, omitted fromeffective_weights, and explained indata_quality; it is not independent sign-off proof. - For suite history, call
regressions.summarywithsuite,window_days, and an explicitas_ofwhen reproducibility matters. - Call
tests.clusterfor the run. Rank usingdistinct_test_count,failure_count, severity, category, and recurrence. Clusters are signature heuristics, not established root causes. Discloseclusters_truncated. - If a baseline exists, call
runs.diff. Separatenew_failures,persistent_failures,resolved_failures, test changes, andcoverage_deltas. - For leading clusters, page through
failures.listwithrun_idor representativetest_idandinclude_evidence=true. Continue until all pages in the intended scope are read or state the exact bounded subset. - Page through
assertions.failureswhen assertions are implicated. Resolve relevant definitions withassertions.get. - Use
tests.historyfor the logical test cohort. Itsis_flakyfield means mixed pass/fail outcomes in a bounded indexed history; report it as a flakiness signal, not proof. - Use
runs.cross_simonly when multiple simulators are relevant. Its comparisons are latest-result cohorts matched by suite, framework, DUT top, and test name. - Deepen only the highest-impact unresolved cases with
tests.get,tests.topology,wave.summary, orwave.signals.
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.
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.
- 12d ago First seen · 57 lines · 68 tokens per session scan A 2107a5aee114
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.
Other skills, from other repositories
jetson-video-pipeline
Use when executing and verifying Jetson Video Codec SDK or PyNvVideoCodec encode/decode, transcode, segmentation, container decode, AV1, or acceptance workflows with exact artifact handoffs.
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.
holohub-app-lifecycle
Use for non-failing HoloHub app work with ./holohub: scaffold, build, run, test, visual evidence, lint, and flow benchmarking.
code-plan
Turn a task description and repository into a structured implementation plan (files to create, files to modify, tests to add, risks).
ros2-robotics
Best practices for ROS 2 robotics development, covering package structure, nodes, topics/services/actions, launch files, QoS, tf2 transforms, and testing. Use when creating ROS 2 packages, writing nodes in rclpy or rclcpp, defining custom messages/services/actions, writing launch files, configuring QoS profiles…
SmartHome Video Anomaly Benchmark
VLM evaluation suite for video anomaly detection in smart home camera footage.