Borrowing it
Nothing to install: this file belongs to brovar/10x-pentest. 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/brovar/10x-pentest/main/.github/skills/pt-dynamic-analyze/SKILL.mdgit clone --depth 1 https://github.com/brovar/10x-pentestWrote 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/brovar/10x-pentest/pt-dynamic-analyze)<a href="https://agentmods.dev/skills/brovar/10x-pentest/pt-dynamic-analyze"><img src="https://agentmods.dev/badge/skills/brovar/10x-pentest/pt-dynamic-analyze/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/brovar/10x-pentest/pt-dynamic-analyze"><img src="https://agentmods.dev/badge/skills/brovar/10x-pentest/pt-dynamic-analyze.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 | $0.00123 | $0.01782 |
| Opus 5 | $0.00062 | $0.00891 |
| Sonnet 5 | $0.00025 | $0.00356 |
| Haiku 4.5 | $0.00012 | $0.00178 |
Grade A, and why
pt-dynamic-analyze 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 9d 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/pt-dynamic-analyze — Dynamic Analysis (Stage 4)
Ingest the human-provided raw evidence (dynamic/evidence/<TC>/), interpret each case, and assign a
verdict — then map it to a finding action + ledger status via the canonical table in
test-objectives-schema §5. Files Verified findings (grounded in real captured evidence, never
model say-so — the tier-integrity invariant), promotes matching code Potentials, downgrades to
Potential-Unverifiable where a safe proof wasn't possible, or appends follow-up cases for the
human to run (the re-plan half of the loop).
When to use, when to skip
- Use whenever new evidence is present under
dynamic/evidence/awaiting analysis. - Skip cases without evidence yet — analyze only cases with evidence present (state
run, which the executor sets, orcaptured); leaveplanned/blockedones for the executor (human or/pt-dynamic-run). Don't fabricate a verdict for a case that wasn't run.
Initial Response
- With
<engagement-id>: proceed to Step 0. - Without: print
Usage: /pt-dynamic-analyze <engagement-id>.and STOP.
Inputs
dynamic/test-plan.md— [blocking] (the cases + their links).dynamic/evidence/**— [blocking] — the executor's raw outputs +run.md(human or/pt-dynamic-run).test-objectives.md— [blocking] (thedynamic/bothrows to resolve; ledger to update).scope.md— [blocking].- Code findings — [optional] — the Potentials this stage may promote.
Process
Step 0: Validate + resume
Validate inputs; confirm each case's run.md records what actually ran — executor: human | agent
and, for confirm: true, who authorized it (a run case missing this is a gate failure regardless of
executor). Resume: analyze only cases with evidence present; findings are append-only; ledger
writes are idempotent per row; never reset the ledger or demote a verified finding.
Step 1: Verdict each case with evidence
Take each case in state run/captured with evidence, read the files, and set verdict ∈ vulnerable | secure | inconclusive | unverifiable, grounded in the files — never invented. This stage is the
sole writer of captured/analyzed: stamp status → captured on ingest (evidence present), then
analyzed once verdicted.
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.
- 9d ago First seen · 119 lines · 0 tokens per session scan A d78894793197
pt-dynamic-analyze is a skill published in the GitHub repository brovar/10x-pentest (3 stars, last pushed 27d ago), licensed Apache-2.0. It adds 123 tokens to every session and 1,782 once invoked, about $0.0006 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…