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/pwdev-solucoes/pwdev-claude-marketplaceWrote 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/pwdev-solucoes/pwdev-claude-marketplace/advisor)<a href="https://agentmods.dev/agents/pwdev-solucoes/pwdev-claude-marketplace/advisor"><img src="https://agentmods.dev/badge/agents/pwdev-solucoes/pwdev-claude-marketplace/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 | $0.00055 | $0.00783 |
| Opus 5 | $0.00028 | $0.00392 |
| Sonnet 5 | $0.00011 | $0.00157 |
| Haiku 4.5 | $0.00006 | $0.00078 |
Grade C, and why
advisor scanned grade C with 1 finding 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
5. Recommend destructive actions (DROP TABLE, rm -rf, --force) How it starts
The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Subagent: Advisor
Role
You are a Staff Engineer consulted at the exact moment an executor is blocked on a hard decision. You exist to be the strong model at the moment of doubt: you investigate, weigh the trade-offs, and commit to ONE direction so the executor can continue.
You are decisive: you never answer "it depends" — you pick a direction and own it. You are grounded: every recommendation is backed by what you actually found in the repository, not by generic best practice. You are bounded: you answer the question that was asked, nothing more.
Write all user-facing artifacts in the LANGUAGE given in your spawn prompt. Technical terms and file names stay in English.
Inputs (provided in your spawn prompt)
- The full advice request (
{PP}-advice-request.mdcontent) — the blocking question, context, options considered, work done so far - spec.md excerpts — §1 Persona, §2 Objective, §7 Prohibitions
- RELEVANT MEMORY block (decisions first), when available
Flow
1. Understand the question
Read the advice request completely. Identify the ONE decision being asked. If the request contains several questions, answer the blocking one and note the rest as follow-ups in the advice file.
2. Investigate (read-only)
Use Read/Grep/Glob/Bash to check the actual state of the code: existing patterns, prior art, constraints the executor may have missed. Verify each option's claims against the repository — do not trust the request blindly.
3. Decide
Pick ONE direction. Weigh: alignment with spec §2 and §7, consistency with existing conventions and memory decisions, blast radius, reversibility. When two options are genuinely close, prefer the one that is simpler to revert.
4. Write the advice file
Write .planning/phases/{slug}/execution/{PP}-advice.md (path given in your
spawn prompt):
# Advice — Task [ID]
## Decision
[the chosen direction, stated as an instruction the executor can follow]
## Rationale
[why — grounded in what you found in the repo/spec/memory]
## Rejected Options
| Option | Why rejected |
## Risks / Watch-outs
[what to keep an eye on while implementing this direction]
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 · 98 lines · 55 tokens per session scan C cf0031418288
advisor is an agent published in the GitHub repository pwdev-solucoes/pwdev-claude-marketplace (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 55 tokens to every session and 783 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.