whyguard: Skill for Kiro

.kiro/skills/review-evidence-quality/SKILL.md

review-evidence-quality is a skill for Kiro from rosselps/whyguard. It costs 48 tokens per session (431 once invoked), scanned A, original, MIT.

A checklist for judging whether issues, pull requests, commits, comments, and tests really support a claimed reason for code. A protected property is behavior that must continue to work.

In plain words
What is it for?
Use it whenever someone says code exists because of a past decision or incident. It helps classify evidence as strong, medium, or weak and decide whether the claimed property is supported.
Why use it?
It reduces the risk of trusting a weak historical connection or an agent-written summary. It checks that the evidence refers to the same code and behavior before the claim is used.

Skill for Kiro

Written for Kiro: installed under .kiro/.

This is rosselps/whyguard's own configuration. It tells Kiro how to work on whyguard itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything whyguard configures →

Reuse

Borrowing it

Nothing to install: this file belongs to rosselps/whyguard. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/rosselps/whyguard/main/.kiro/skills/review-evidence-quality/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/rosselps/whyguard

Made for: Kiro.

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 review-evidence-quality

README.md
[![agentmods](https://agentmods.dev/badge/skills/rosselps/whyguard/review-evidence-quality/github.svg)](https://agentmods.dev/skills/rosselps/whyguard/review-evidence-quality)
Your own site
<a href="https://agentmods.dev/skills/rosselps/whyguard/review-evidence-quality"><img src="https://agentmods.dev/badge/skills/rosselps/whyguard/review-evidence-quality/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.

agentmods 80×15 button for review-evidence-quality

Your own site · 80×15
<a href="https://agentmods.dev/skills/rosselps/whyguard/review-evidence-quality"><img src="https://agentmods.dev/badge/skills/rosselps/whyguard/review-evidence-quality.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 431 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00048 $0.00431
Opus 5 $0.00024 $0.00216
Sonnet 5 $0.00010 $0.00086
Haiku 4.5 $0.00005 $0.00043

Measured 10d ago against content hash 299bb000688d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

review-evidence-quality 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 10d 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.

.kiro/skills/review-evidence-quality/SKILL.md · 41 lines

What it actually says

When to use this skill

Whenever a Finding or another agent claims "this code exists because of X" — verify the claim against the evidence-strength rubric in .kiro/steering/evidence-policy.md before accepting it.

Evidence strength rubric

Strength Criteria
Strong A PR/issue/comment explicitly names the symbol and protected behavior, or a regression test clearly represents it.
Medium A commit message and code/test changes strongly imply the behavior, without explicit confirmation.
Weak Only a temporal or semantic correlation exists, with no explicit explanation.

Workflow

  1. Read every evidence item's type, title, summary, and strength — not just its ID.
  2. Confirm the evidence actually references the same symbol/file/behavior under review, not a superficially similar one.
  3. Downgrade your trust in the finding if:
    • the only evidence is weak;
    • the evidence references a different function or file than the one being changed;
    • the evidence is a commit message alone with no linked issue/PR/test.
  4. Never let an LLM-authored summary substitute for reading the actual evidence item.
  5. If evidence is insufficient, explicitly report reasonStatus: unknown and recommend manual review — do not fabricate a plausible-sounding justification.

Anti-patterns to avoid

  • Accepting a riskScore/confidenceScore at face value without checking which evidence strengths fed into it.
  • Merging evidence from an unrelated finding because the file path looks similar.
  • Treating the absence of a search result as proof that no incident occurred (weak evidence is not the same as evidence of safety).
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. 10d ago First seen · 41 lines · 48 tokens per session scan A 299bb000688d

Subscribe to this mod's changes

review-evidence-quality is a skill published in the GitHub repository rosselps/whyguard (0 stars, last pushed 1mo ago), licensed MIT. It adds 48 tokens to every session and 431 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

code-review-php

Deep PHP-specific code review covering strict types, PHPStan compliance, PSR standards, domain modeling, and ORM boundary violations. Applied in addition to the generic code-review skill when PHP code is detected. Invoked when reviewing PHP PRs, Symfony/Laravel changes, or performing PHP-specific quality checks.

soulcodex/agentic · 66 tokens

svelte-vitals

Use when writing or reviewing SvelteKit routes/components — svelte-vitals rule knowledge (SEO, performance, correctness, security, architecture, accessibility) and how to run the scanner.

oekazuma/svelte-vitals · 42 tokens

find-simplifications

Use for a periodic repo-wide sweep of qwen-code for accumulated excess surface — dead components and files, orphaned locale keys, exports nothing consumes, added-then-removed scaffolding — filing candidates on a tracking issue and landing only what a maintainer has said yes to. Repo-wide and evidence-first; every…

QwenLM/qwen-code · 103 tokens

swarm-pr-review

Run a graph-guided, tool-augmented PR review using context packing, parallel exploration, mandatory repository-agnostic risk-family coverage with dispatch scaled to diff size and risk, independent reviewer validation, critic challenge, and metrics writeback. Use for deep pull request review with low false-positive…

ZaxbyHub/opencode-swarm · 91 tokens

review

Validate plans, execution, or PRs against wish criteria — returns SHIP / FIX-FIRST / BLOCKED with severity-tagged gaps.

automagik-dev/genie · 29 tokens

include-test-files-that-assert-on-behavior-being-changed-in-decl

When delegating a task affected by this skill, include.

ZaxbyHub/opencode-swarm · 29 tokens