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 explyt/spring-plugin --skill review-findings-validatorgit clone --depth 1 https://github.com/explyt/spring-pluginWrote 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/explyt/spring-plugin/review-findings-validator)<a href="https://agentmods.dev/skills/explyt/spring-plugin/review-findings-validator"><img src="https://agentmods.dev/badge/skills/explyt/spring-plugin/review-findings-validator.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00077 | $0.03234 |
| Opus 5 | $0.00039 | $0.01617 |
| Sonnet 5 | $0.00015 | $0.00647 |
| Haiku 4.5 | $0.00008 | $0.00323 |
Grade A, and why
review-findings-validator 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 8d 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 — 266 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review findings validator
You are not another generic reviewer. You are a per-artifact validator. This is a normative skill: in a single run you validate exactly one reviewer artifact and determine which findings are truly confirmed, which are false positives, and which need more data.
Non-negotiable review method
- Read
REVIEW_SCOPE.md,REVIEW_PACKET.mdand exactly one reviewer artifact in full. - Never rely only on summaries.
- For every
Critical,High, andMediumfinding, and for anyLowfinding with low/medium confidence that could change prioritization, perform a full per-finding investigation (see below). Low-severity findings with high confidence do not require the full investigation. - Build one validated artifact for that one reviewer artifact, not a global truth set for the whole review.
Per-finding investigation method
CRITICAL: One finding at a time. No batching.
Process findings strictly sequentially: pick one finding, investigate it fully (Steps 1–5), write the verdict, and only then pick the next finding.
Never batch-read code for multiple findings at once. Each finding gets its own investigation cycle with its own tool calls. The reason: each finding may require following different call chains across different files, and batching leads to shallow analysis where mitigating factors are missed.
For each finding that requires investigation, follow this exact sequence:
Step 1 — Read the actual code. Open and read the source file(s) at the exact location(s) cited by the reviewer. Never validate a finding from the reviewer's description alone.
Step 2 — Trace the real execution path, following call chains across files. Explain in plain language what actually happens at runtime. Follow the control flow: what calls this code, what guards exist before it, what happens on success and failure. If the finding claims a race condition, identify the exact window. If it claims data loss, trace the data flow.
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.
- 8d ago First seen · 266 lines · 77 tokens per session scan A b36081c312e8
review-findings-validator is a skill published in the GitHub repository explyt/spring-plugin (160 stars, last pushed yesterday), licensed Apache-2.0. It adds 77 tokens to every session and 3,234 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
analyze-external-methods
Analyze an OpenTaint scan's dropped external methods and decide which of them are propagators and optionally sinks. Use when a dropped-external-methods.yaml needs classification for dropped method type.
create-rule
Author and verify an OpenTaint rule. Use whenever a rule creation is needed.
appsec-agent
Run an end-to-end OpenTaint application-security analysis while owning the long project build and scans and delegating each other pipeline stage. Use when the user asks to find vulnerabilities, or scan an application for security issues.
create-dataflow-approximation
Model a method's taint propagation as code-based dataflow approximation and refine it against a test project until the sample passes. Use for a dropped method that requires code-based approximation.
create-test-project
Create an OpenTaint test project with positive/negative samples for verifying a rule or approximation. Use when a rule or approximation needs a test project to check against.
discover-attack-surface
Classify project-used dependency members and record the taint sources among them not covered by the built-in rules. Use for the source-discovery depth pass.