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 agentmods add agents/rosselps/whyguard/whyguard-reviewergit clone --depth 1 https://github.com/rosselps/whyguardWrote 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/rosselps/whyguard/whyguard-reviewer)<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>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 | $0.00014 | $0.00539 |
| Opus 5 | $0.00007 | $0.00269 |
| Sonnet 5 | $0.00003 | $0.00108 |
| Haiku 4.5 | $0.00001 | $0.00054 |
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 *" 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.
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.
- 4d ago First seen · 65 lines · 14 tokens per session scan D d20e6160ecee
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.
Other agents, from other repositories
architect
The architecture document MUST reflect the reality of the code, not just the desired target state. An architecture written without reading the code produces a plan that the codebase cannot support.
dev-brownfield
When riskcontext is absent from a story, this override enforces a full structural gate at implementation time as a safety net.
protocol
This is the normative protocol for coding agents that use Agents Shipgate as a local governance check before reporting an agent-capability change complete.
use-with-claude-code
This page is the compatibility guide for Claude Code skill installation. For the normative agent protocol, use claude-code.md and protocol.md. The canonical Claude Code control command is.
use-with-codex
This page is the compatibility guide for Codex plugin and skill installation. For the normative agent protocol, use codex.md and protocol.md. The canonical Codex control command is.
use-with-cursor
This page is the compatibility guide for Cursor rules. For the normative agent protocol, use cursor.md and protocol.md. The canonical Cursor control command is.