whyguard-reviewer

whyguard-reviewer is an agent for coding agents from rosselps/whyguard. It costs 14 tokens per session (539 once invoked), scanned D, original, MIT.

A specialised coding agent for reviewing and implementing WhyGuard while preserving its past behavior and links to supporting evidence.

In plain words
What is it for?
Use it to implement WhyGuard changes, maintain evidence-linked historical explanations, avoid registering protections in the wrong repository, and run the required type, lint, formatting, and relevant checks.
Why use it?
It keeps work limited to the intended repository, prevents unapproved architectural changes, and requires human review for risky decisions and generated tests.

Agent

Install

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.

agentmods
npx agentmods add agents/rosselps/whyguard/whyguard-reviewer
Clone the repo
git clone --depth 1 https://github.com/rosselps/whyguard

Wrote 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.

agentmods badge for whyguard-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/rosselps/whyguard/whyguard-reviewer.svg)](https://agentmods.dev/agents/rosselps/whyguard/whyguard-reviewer)
Your own site
<a href="https://agentmods.dev/agents/rosselps/whyguard/whyguard-reviewer"><img src="https://agentmods.dev/badge/agents/rosselps/whyguard/whyguard-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 539 The whole file, excluding the scripts and references it only reads on demand.
Security scan D 2 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00014 $0.00539
Opus 5 $0.00007 $0.00269
Sonnet 5 $0.00003 $0.00108
Haiku 4.5 $0.00001 $0.00054

Measured 4d ago against content hash d20e6160ecee, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade D, and why

whyguard-reviewer scanned grade D with 2 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 4d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

- "sudo *"

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

- "rm -rf *"
.kiro/agents/whyguard-reviewer.md · 65 lines

What it actually says

Follow AGENTS.md and .kiro/steering/.

This agent is scoped to work on the WhyGuard repository itself (whyguard/) — not a target repository being protected by WhyGuard. The .kiro/hooks/*.template and this file's own whyguard MCP server entry describe the target workspace's intended setup; never register a live PreToolUse hook against WhyGuard's own repository (see AGENTS.md rule 16).

Do not broaden the scope set out in .kiro/steering/product.md without an ADR. Do not add a service, database, framework, or integration without one either.

Never state a historical reason without evidence ids. Distinguish the protected behavior from its current implementation.

Never execute a generated regression test automatically — a human must review and run it. This applies to output from whyguard.propose_regression_test as much as to anything an LLM might draft later.

Treat whyguard.register_decision as requiring an explicit human "yes" before it is called with confirm: true. Never call it speculatively or as part of an otherwise-automated chain of tool calls.

Before finishing any task, run pnpm typecheck, pnpm lint, pnpm format:check, and the relevant pnpm test scope.

Changes

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.

  1. 4d ago First seen · 65 lines · 14 tokens per session scan D d20e6160ecee

Subscribe to this mod's changes

whyguard-reviewer is an agent published in the GitHub repository rosselps/whyguard (0 stars, last pushed 1mo ago), licensed MIT. It adds 14 tokens to every session and 539 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it D with 2 findings (asks for root, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.