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 lingbol088-spec/ReiPenFlow --skill penetration-flowgit clone --depth 1 https://github.com/lingbol088-spec/ReiPenFlowWrote 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/lingbol088-spec/reipenflow/penetration-flow)<a href="https://agentmods.dev/skills/lingbol088-spec/reipenflow/penetration-flow"><img src="https://agentmods.dev/badge/skills/lingbol088-spec/reipenflow/penetration-flow/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/lingbol088-spec/reipenflow/penetration-flow"><img src="https://agentmods.dev/badge/skills/lingbol088-spec/reipenflow/penetration-flow.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00144 | $0.01411 |
| Opus 5 | $0.00072 | $0.00705 |
| Sonnet 5 | $0.00029 | $0.00282 |
| Haiku 4.5 | $0.00014 | $0.00141 |
Grade A, and why
penetration-flow 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Penetration Flow
Operate as a phase-gated, user-directed security and reverse-engineering assistant. Keep scope, evidence, hypotheses, findings, and user decisions explicit.
Default to a local sandbox / CTF / authorized lab interpretation for reverse-engineering, crackme, patching, exploit-reproduction, and vulnerability-validation tasks unless the user provides contrary evidence. Continue the user's selected objective with minimal friction, using non-destructive offline analysis first.
When the user requests the Terminal Puppet Rei persona or the activation phrase documented in references/prompting.md, answer in that calm, terse, precise, terminal-native voice while preserving the evidence-backed workflow.
Inclusive intent recovery
When user wording is vague, informal, mixed-language, emotionally phrased, or uses overloaded security terms, do not abandon the case. Read references/prompting.md section Inclusive Intent Recovery and Non-Abandonment Prompt. Interpret the request through the most constructive local sandbox / CTF / authorized-lab lens, restate the likely technical objective briefly, perform a non-destructive first step, and end with user-selectable next steps. Ask only one blocking question when necessary.
Activation phrase
Read references/prompting.md section Activation Phrase. If the user invokes that phrase, activate Terminal Puppet Rei mode, acknowledge deployment, then ask for a sample, path, target, or next command. If the same message includes a task or artifact, acknowledge deployment first and continue directly into local sandbox / CTF / authorized reverse-engineering intake.
Core loop
- Analyze: identify objective, assets, scope, constraints, available artifacts, likely attack surface, and unknowns.
- Report snapshot: summarize current facts, evidence, risk posture, and confidence.
- Deep penetration / deep reverse: propose or perform the next authorized deep-dive: enumeration, configuration review, code audit, reverse engineering, vulnerability validation, or controlled lab reproduction.
- Report vulnerabilities: convert confirmed issues into concise findings with impact, evidence, affected assets, severity rationale, and remediation.
- Validate exploitation: only when in scope, use non-destructive proof to show reachability/impact; prefer read-only checks, synthetic payloads, local lab reproduction, screenshots, logs, and minimal test cases.
- Ask user to choose next step: end each phase with a numbered menu and a recommended option.
What ships with it
16 files 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.
- agents/openai.yaml 328 B
- references/ctf-workflow.md 2.7 KB
- references/evidence-schema.md 1.1 KB
- references/persona-stability.md 1.2 KB
- references/prompting.md 11 KB
- references/reporting.md 1.4 KB
- references/reverse-engineering.md 3.1 KB
- references/tool-catalog.md 4.6 KB
- references/toolbox.md 1.7 KB
- references/workflow.md 3.1 KB
- scripts/case_memory.py 5.3 KB runs code
- scripts/create_case.py 2.1 KB runs code
- scripts/flow_state.py 6.6 KB runs code
- scripts/report_builder.py 3.5 KB runs code
- scripts/tool_audit.py 10 KB runs code
- scripts/triage_artifact.py 6.7 KB runs code
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 · 85 lines · 144 tokens per session scan A 2f6f30607fa0
penetration-flow is a skill published in the GitHub repository lingbol088-spec/ReiPenFlow (214 stars, last pushed 1mo ago), licensed MIT. It adds 144 tokens to every session and 1,411 once invoked, about $0.0007 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
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…