analyze-findings

analyze-findings is a skill for Claude Code from seqra/opentaint. It costs 24 tokens per session (1,282 once invoked), scanned A, original, Apache-2.0.

A static-analysis triage skill for reviewing OpenTaint findings, which are reported possible vulnerabilities in source code.

In plain words
What is it for?
Use it to reconcile rescan results, inspect source-to-sink flows, and assign evidence-based TP or FP verdicts to finding files for a specified programming language.
Why use it?
It separates distinct issues and judges each one as a true positive or false positive using the reported code flow and existing triage records.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the appsec-workflow plugin — 16 skills shipped together

Install

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.

agentmods
npx agentmods add skills/seqra/opentaint/analyze-findings
Any agent
npx skills add seqra/opentaint --skill analyze-findings
Clone the repo
git clone --depth 1 https://github.com/seqra/opentaint

Made for: Claude Code.

Or install appsec-workflow, the plugin that ships this one along with the rest of its 16 skills.

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 analyze-findings

README.md
[![agentmods](https://agentmods.dev/badge/skills/seqra/opentaint/analyze-findings.svg)](https://agentmods.dev/skills/seqra/opentaint/analyze-findings)
Your own site
<a href="https://agentmods.dev/skills/seqra/opentaint/analyze-findings"><img src="https://agentmods.dev/badge/skills/seqra/opentaint/analyze-findings.svg" alt="Measured on agentmods" height="20"></a>
Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,282 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00024 $0.01282
Opus 5 $0.00012 $0.00641
Sonnet 5 $0.00005 $0.00256
Haiku 4.5 $0.00002 $0.00128

Measured 6d ago against content hash 116cf47af821, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

analyze-findings 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 6d 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.

skills/analyze-findings/SKILL.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: Analyze Findings

A finding file bundles all of one rule's results. Read each result's code flow, split the bundle into distinct vulnerabilities, and give each a TP/FP verdict on its own evidence

Inputs

Provided by the caller, fall back to the default value when omitted. Ask back only when a required input is missing and has no sensible default

  • project-root (optional) — root of the target project. Opentaint keeps all analysis artifacts under the fixed <project-root>/.opentaint/ directory, so every .opentaint/... path below resolves there. Default: current directory
  • language (required) — target language for this project and language-specific instructions
  • findings (required) — the finding file(s) to triage, each .opentaint/tracking/findings/<name>.yaml bundling one rule's SARIF results in sarif_hashes

Workflow

1. Reconcile before judging

A finding whose notes open with a reconcile line is a rescan result under a rule whose other findings are already triaged — most often the same vulnerability with a shifted hash, not a new one. Before judging it fresh, read the rule's already-triaged finding files and compare flows (source → sink, same essential path): if one matches, move this finding's sarif_hashes into that finding, drop this file, and let the inherited verdict stand — don't re-judge a flow already triaged. Only when no triaged finding matches do you treat it as new and continue below.

2. One result at a time — STOP checklist

For each hash in the bundle, before any verdict, read its raw result from .opentaint/results/report.sarif:

  • find its SARIF result via sarif_hashes — each entry is the leading 16 chars of that result's vulnerabilitySourceSinkHash/vulnerabilityWithTraceHash fingerprint, so match it against the result's fingerprints/partialFingerprints — then read the raw codeFlows[]
  • walk every step, source → hops → sink, confirming it's the same tainted value end to end; confirm the flow against the application source (the built project's own sources under .opentaint/project/sources/) and dependency code, not the trace text alone
  • judge each result on its own trace — no verdict shared across results just because they share the rule

Read the full file on GitHub · 85 lines

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. 6d ago First seen · 85 lines · 24 tokens per session scan A 116cf47af821

Subscribe to this mod's changes

analyze-findings is a skill published in the GitHub repository seqra/opentaint (153 stars, last pushed yesterday), licensed Apache-2.0. It adds 24 tokens to every session and 1,282 once invoked, about $0.0001 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.

Related

Other skills, from other repositories

plugin-code-review-orchestrated

Orchestrates a code review of the spring-plugin repository through scope/context passes, routing, domain reviewer subskills, and per-artifact validation. Use when asked to review a PR, diff, commit, branch, module, or file set, to run a full orchestrated review, or to produce a validated review report.

explyt/spring-plugin · 72 tokens

github-issue-manager

Classifies a user request as Bug, Compatibility, Feature, Question, or Task for the explyt/spring-plugin GitHub repo, lightly researches the relevant codebase, searches similar existing issues, and either reports an existing issue or creates a correctly titled and labeled one following the repository issue forms. Use…

explyt/spring-plugin · 97 tokens

review-async-lifecycle

Normative reviewer for EDT safety, coroutines, cancellation, read/write actions, disposal, listeners and async lifecycle in the explyt spring-plugin. Use during orchestrated code review when the diff touches threading, background tasks, read or write actions, listeners, MessageBus, Disposable ownership or progress…

explyt/spring-plugin · 66 tokens

review-core-correctness

Normative mandatory reviewer for correctness, contracts, architecture sanity, UX behavior, code quality and tests in the explyt spring-plugin codebase. Use during orchestrated code review of a PR, diff, commit or branch, or when asked to review correctness, logic, architecture or test coverage of plugin changes.

explyt/spring-plugin · 67 tokens

review-findings-validator

Normative per-artifact validator: reads exactly one reviewer artifact, re-verifies every claim against real source code, classifies findings as TP, FP, or Need more data, and writes exactly one validated artifact. Use during the validation wave of an orchestrated code review, when asked to validate reviewer findings…

explyt/spring-plugin · 77 tokens

review-persistence-security-resources

Normative reviewer for persistence, settings, secrets, logging hygiene, resources, caches, cross-platform behavior and long-lived state in the explyt/spring-plugin IntelliJ plugin. Use when reviewing changes that touch PersistentStateComponent, settings UI, credentials, caches, service fields, logging, file paths…

explyt/spring-plugin · 83 tokens