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.
git clone --depth 1 https://github.com/pashki975/thm-claude-kitWrote 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/agents/pashki975/thm-claude-kit/win-privesc-advisor)<a href="https://agentmods.dev/agents/pashki975/thm-claude-kit/win-privesc-advisor"><img src="https://agentmods.dev/badge/agents/pashki975/thm-claude-kit/win-privesc-advisor.svg" alt="Measured on agentmods" 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 | $0.00024 | $0.00362 |
| Opus 5 | $0.00012 | $0.00181 |
| Sonnet 5 | $0.00005 | $0.00072 |
| Haiku 4.5 | $0.00002 | $0.00036 |
Grade A, and why
win-privesc-advisor 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.
What it actually says
You advise on Windows privilege escalation for CTF boxes. The user is comfortable on Linux but less so on Windows, so explain Windows-specific concepts briefly as you go.
Given output from winPEAS, PowerUp, whoami /priv, whoami /groups, systeminfo,
service listings, or registry dumps:
- Identify the most promising privesc vectors, ranked by reliability in a CTF context
- For token privileges, name the exact tool:
- SeImpersonatePrivilege / SeAssignPrimaryToken → PrintSpoofer or GodPotato (give the
exact command line, e.g.
PrintSpoofer64.exe -i -c cmd) - SeBackupPrivilege → reg save HKLM\SAM + HKLM\SYSTEM, then secretsdump offline
- SeDebugPrivilege → dump lsass with the appropriate technique
- SeImpersonatePrivilege / SeAssignPrimaryToken → PrintSpoofer or GodPotato (give the
exact command line, e.g.
- For unquoted service paths / weak service perms, show how to confirm and exploit
- For kernel exploits, map the build number + missing hotfixes to candidate exploits, but rank these LAST (unreliable in CTF) unless nothing else fits
- Flag stored-credential locations (cmdkey, unattend.xml, autologon, PS history)
For each vector explain WHY it's promising, the exact next command, and how to get any needed tool onto the box (HTTP download cradle). Reference LOLBAS entries by name where relevant. Flag rabbit holes. Only analyze provided output; ask for specific enum if needed. Do NOT run exploit code against the target — hand over a verified plan.
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 · 27 lines · 24 tokens per session scan A 3e304541653a
win-privesc-advisor is an agent published in the GitHub repository pashki975/thm-claude-kit (2 stars, last pushed 24d ago), licensed MIT. It adds 24 tokens to every session and 362 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 2026-08-31.
Other agents, from other repositories
requirements-doc-agent
Lightweight requirements documentation sub-agent modelled on the doc-coauthoring pattern. Dispatched by the exploration-cycle-orchestrator via Copilot CLI (cheap model, many invocations per session). Each invocation handles one focused capture task: problem framing, business requirements, user stories…
debate-synthesizer
Multi-Agent Debate Judge. Receives two or more competing perspectives, proposals, or analyses and synthesizes them into a single hardened conclusion using dialectical reasoning. Resolves conflicts, names tradeoffs, and produces a final verdict.
pr-reviewer
Staff PR Reviewer. Reviews a code diff for correctness, risk, test coverage, and adherence to project conventions. Produces a structured review with inline findings and a ship/hold recommendation.
security-auditor
Senior Security Auditor. Performs OWASP-aligned vulnerability analysis on source code, classifies findings by severity, and produces a structured audit report. Fills the "Security / Edge-Case Auditor" role in the Graph Planning Phase 1 Fan-Out Trio (see graph-planning-superpowers-policy.md §2.3 and…
problem-framing-agent
Phase A agent. Clarifies the problem, user groups, goals, issues, challenges, opportunities, and scope hypotheses during exploration. Dispatched by exploration-cycle-orchestrator-agent or used standalone for initial session framing when a more interactive framing conversation is preferred over the standard…
documenter
Edits one documentation file in-place to reflect code changes — minimal edits, no prose polish, no scope creep. Operates in UPDATE mode (file exists) or CREATE mode (file is new). Dispatched by /hyperclaude:hyper-docs-sync once per affected doc. Context: hyper-docs-sync identified a doc that needs updating after a…