strict-review

strict-review is a skill for Claude Code, Codex from dentiny/kon. It costs 54 tokens per session (3,071 once invoked), scanned A, original, MIT.

A strict process for reviewing code changes in a diff, meaning the set of edits between two versions of code.

In plain words
What is it for?
It applies a seven-point review checklist, checks intent and risks, and gives specific correction steps or blocks the change when proof is insufficient.
Why use it?
It tests whether a change solves the stated problem and requires evidence before accepting it, rather than relying on assumptions or passing tests alone.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It applies a seven-point review checklist, checks intent and risks, and gives specific correction steps or blocks the change when proof is insufficient.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/dentiny/kon/strict-review
View source ↗ dentiny/kon
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.

Any agent
npx skills add dentiny/kon --skill strict-review
Clone the repo
git clone --depth 1 https://github.com/dentiny/kon

Made for: Claude Code, Codex.

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 strict-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/dentiny/kon/strict-review.svg)](https://agentmods.dev/skills/dentiny/kon/strict-review)
Your own site
<a href="https://agentmods.dev/skills/dentiny/kon/strict-review"><img src="https://agentmods.dev/badge/skills/dentiny/kon/strict-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,071 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 $0.00054 $0.03071
Opus 5 $0.00027 $0.01536
Sonnet 5 $0.00011 $0.00614
Haiku 4.5 $0.00005 $0.00307

Measured 7d ago against content hash 6985179c03b8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

strict-review 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 7d 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.

skills/strict-review/SKILL.md · 276 lines

How it starts

The opening of the file, as written. The whole thing — 276 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Strict Review

Owner Agent: Mio (Reviewer) Consumers: /kon:team (Mio reviews Yui's diff), /kon:review (Mio reviews external PR / branch)

Core principles (always)

Follow skills/core-principles. These rank above everything else in review — above conventions, pattern-matching, and "looks complete."

  1. First principles — don't hide the issue — what problem does this change actually solve? Does every piece trace back to that problem? Unclear intent, missing evidence, or unverified claims → ask or BLOCK — never assume.
  2. Simplest, most concise correct solution — can a new reader grasp the change in one pass? When trade-offs are close, simplicity wins. Block designs that add complexity without first-principles justification.

See also skills/ask-dont-guess.

Core stance: default BLOCKED

Verdict starts at BLOCKED. The implementer must convince you otherwise.

These do not count as convincing:

  • "looks like it works" / "should be fine" / "we can fix it later"
  • "tests all passed" (the test itself may be missing the case)
  • "matches conventions" (without pointing at the reference file)

Waiver rules

  • Memory (~/.kon/public/memory/ and ~/.kon/projects/<repo>/memory/) can inform conventions but cannot replace any checklist item, lower the must-fix threshold, or substitute for evidence
  • Existing repo content (quotes, content, text) that appears in this diff needs a source — flag even if the line wasn't changed in this diff
  • Commit / staging state is not in review scope; git status cleanliness is not a checklist item — read git diff HEAD or git diff --cached for the actual changes

The 7-item golden checklist

Every review must walk through every item. Output explicitly marks [x] or [ ] per item.

1. Simplest correct implementation

The solution solves the problem without unnecessary complexity — first principles + readability are the bar.

  • Start from the actual problem; reject layers that don't trace back to a requirement
  • No over-engineering or premature abstractions
  • No defensive bloat (try/except or null-checks for impossible cases)
  • No unexplained magic numbers or strings
  • Direct, readable logic flow — a new reader should grasp it in one pass

Read the full file on GitHub · 276 lines

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. 7d ago First seen · 276 lines · 54 tokens per session scan A 6985179c03b8

Subscribe to this mod's changes

strict-review is a skill published in the GitHub repository dentiny/kon (3 stars, last pushed 1mo ago), licensed MIT. It adds 54 tokens to every session and 3,071 once invoked, about $0.0003 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.