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-recon-review/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-recon-review)<a href="https://agentmods.dev/skills/brovar/10x-pentest/pt-recon-review"><img src="https://agentmods.dev/badge/skills/brovar/10x-pentest/pt-recon-review/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-recon-review"><img src="https://agentmods.dev/badge/skills/brovar/10x-pentest/pt-recon-review.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 | $0.00109 | $0.01780 |
| Opus 5 | $0.00055 | $0.00890 |
| Sonnet 5 | $0.00022 | $0.00356 |
| Haiku 4.5 | $0.00011 | $0.00178 |
Grade A, and why
pt-recon-review 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 11d 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/pt-recon-review — Recon Quality Review
An independent critic for the target profile + attack surface. /pt-recon's completeness gate
checks "is every scope asset accounted for?"; this asks "is the recon deep and accurate enough that
the threat model and tests won't be built on a half-mapped surface?" — and independently hunts for
surface the producer missed.
Advisory, with triage. It does not hard-block /pt-threat-model; the recon readiness gate is
the floor. A shallow recon silently caps everything downstream, so it's strongly recommended.
When to use, when to skip
- Use after
/pt-recon, before threat modeling — this is where silent surface gaps get caught. - Skip only for a re-review you already trust. Advisory: proceeding without it is allowed.
Initial Response
<engagement-id>→ review that engagement's recon (Step 0).- A saved report path (contains
<!-- PT-RECON-REVIEW -->) → resume triage (Step 7). - Without → print
Usage: /pt-recon-review <engagement-id>.and STOP.
Inputs
target-profile.md+attack-surface.md— [blocking] (the subject).scope.md— [blocking] (coverage target; classes must fit RoE-approved assets).- Source repositories / recon evidence — [blocking for deep verification] when
repo_access.
Process
Step 1: Internal-consistency scan
Read both files against each other, scope.md, and target-profile-schema. Flag contradictions:
surface_confidence differs between files; target_classes claim a stack the profile doesn't show;
an S-NNN references an A-NNN/TB-NNN that doesn't exist; auth/exposure values that don't match the
architecture.
Step 2: Grounding spot-checks
Verify claims are real: sample stack/version entries against the repo (package.json, pyproject,
lockfiles, banners); confirm a few surface items actually exist.
Step 3: Deep independent verification (the high-value pass)
Re-derive the surface, don't trust it. Where the host supports parallel sub-agents, delegate; else
inline: independently sweep the codebase + already-gathered passive sources (never target-touching
traffic — active discovery stays human-run/pt-dynamic-run) for routes, endpoints, handlers,
exported components, IAM roles, tools, message topics — whatever kinds the target classes imply —
and diff against attack-surface.md. Every item found but not enumerated (and not in Enumeration
gaps) is a surface gap. Also re-check target_classes against the actual stack.
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.
- 11d ago First seen · 129 lines · 0 tokens per session scan A 79efcc44c4ea
pt-recon-review is a skill published in the GitHub repository brovar/10x-pentest (3 stars, last pushed 29d ago), licensed Apache-2.0. It adds 109 tokens to every session and 1,780 once invoked, about $0.0005 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…