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 skills add dentiny/kon --skill strict-reviewgit clone --depth 1 https://github.com/dentiny/konWrote 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/dentiny/kon/strict-review)<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>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 | $0.00054 | $0.03071 |
| Opus 5 | $0.00027 | $0.01536 |
| Sonnet 5 | $0.00011 | $0.00614 |
| Haiku 4.5 | $0.00005 | $0.00307 |
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.
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."
- 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.
- 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 statuscleanliness is not a checklist item — readgit diff HEADorgit diff --cachedfor 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
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.
- 7d ago First seen · 276 lines · 54 tokens per session scan A 6985179c03b8
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.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…