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 skills/knowns-dev/knowns/kn-reviewnpx skills add knowns-dev/knowns --skill kn-reviewgit clone --depth 1 https://github.com/knowns-dev/knownsWrote 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/knowns-dev/knowns/kn-review)<a href="https://agentmods.dev/skills/knowns-dev/knowns/kn-review"><img src="https://agentmods.dev/badge/skills/knowns-dev/knowns/kn-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 | $0.00019 | $0.01863 |
| Opus 5 | $0.00010 | $0.00932 |
| Sonnet 5 | $0.00004 | $0.00373 |
| Haiku 4.5 | $0.00002 | $0.00186 |
Grade A, and why
kn-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 242 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review
Post-implementation quality review. Run after kn-implement, before kn-commit.
Announce: "Using kn-review for task [ID] (or current changes)."
Core principle: MULTI-PERSPECTIVE REVIEW → SEVERITY TRIAGE → FIX P1 → COMMIT.
When to Use
- After implementing a task, before committing
- When user says "review my code", "check this", "review before commit"
- As the review step inside
/kn-flowafter each task or integrated wave - As part of
/kn-gopipeline (optional — can be enabled)
If the user asks to review and finish a whole approved spec or task wave, route to /kn-flow @doc/<spec-path> so review is paired with implementation and combined verification.
Inputs
- Task ID (optional — if provided, reviews against task ACs and spec)
- Current git diff (always)
Step 1: Gather Review Context
git diff --stat
git diff
If task ID provided:
mcp_knowns_tasks({ "action": "get", "taskId": "$ARGUMENTS" })
If task has spec:
mcp_knowns_docs({ "action": "get", "path": "<spec-path>", "smart": true })
Read the linked spec's full Locked Decisions section, then retrieve only relevant current System Decisions:
mcp_knowns_search({ "action": "retrieve", "query": "<task + feature area>",
"sourceTypes": ["decision"], "status": "accepted", "includeHistorical": false, "limit": 8 })
Search for relevant conventions and past review patterns:
mcp_knowns_search({ "action": "search", "query": "<feature area>", "type": "memory" })
Step 2: Multi-Perspective Review
Review the diff from 4 perspectives. For each, produce findings with severity.
2a. Code Quality
- Readability and simplicity
- DRY — duplicated logic
- Error handling — missing or swallowed errors
- Type safety — any
any, unsafe casts, missing types - Naming — unclear variable/function names
2b. Architecture
- Separation of concerns — business logic in handlers, UI logic in components
- Coupling — tight dependencies between unrelated modules
- API design — consistent patterns, proper HTTP methods/status codes
- File organization — follows project conventions
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.
- 6d ago First seen · 242 lines · 19 tokens per session scan A d3fe68bc4885
kn-review is a skill published in the GitHub repository knowns-dev/knowns (242 stars, last pushed today), licensed MIT. It adds 19 tokens to every session and 1,863 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
review
Two-stage code review: spec compliance first, then code quality. Auto-triggered after implementation. Also available as /review.
devils-advocate
Challenge a plan, design, or PR by finding every flaw, risk, and wrong assumption. Use before committing to an architecture or shipping a major change.
receiving-feedback
Use when receiving code review feedback or corrections - before implementing suggestions. Requires technical verification and reasoned evaluation, not blind agreement or performative responses.
atlas-review
Review code changes and capture learnings for CLAUDE.md by following the canonical review command doc.
code-review
Performs multi-dimensional code review covering security, quality, spec compliance, and maintainability. Used when reviewing completed implementations or before merging changes.
maxsim-simplify
Reviews changed code for reuse opportunities, quality issues, and efficiency improvements, then fixes actionable items. Used after implementing features or when code feels over-engineered.