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.
curl -O https://raw.githubusercontent.com/rosselps/whyguard/main/.kiro/skills/review-evidence-quality/SKILL.mdgit 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/skills/rosselps/whyguard/review-evidence-quality)<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.
<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>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 | $0.00048 | $0.00431 |
| Opus 5 | $0.00024 | $0.00216 |
| Sonnet 5 | $0.00010 | $0.00086 |
| Haiku 4.5 | $0.00005 | $0.00043 |
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.
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
- Read every evidence item's
type,title,summary, andstrength— not just its ID. - Confirm the evidence actually references the same symbol/file/behavior under review, not a superficially similar one.
- 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.
- the only evidence is
- Never let an LLM-authored summary substitute for reading the actual evidence item.
- If evidence is insufficient, explicitly report
reasonStatus: unknownand recommend manual review — do not fabricate a plausible-sounding justification.
Anti-patterns to avoid
- Accepting a
riskScore/confidenceScoreat 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).
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.
- 10d ago First seen · 41 lines · 48 tokens per session scan A 299bb000688d
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.
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.
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.
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…
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…
review
Validate plans, execution, or PRs against wish criteria — returns SHIP / FIX-FIRST / BLOCKED with severity-tagged gaps.
include-test-files-that-assert-on-behavior-being-changed-in-decl
When delegating a task affected by this skill, include.