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 commands/dragoon0x/canon/critiquegit clone --depth 1 https://github.com/Dragoon0x/canonWrote 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/commands/dragoon0x/canon/critique)<a href="https://agentmods.dev/commands/dragoon0x/canon/critique"><img src="https://agentmods.dev/badge/commands/dragoon0x/canon/critique.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 | $0.00047 | $0.00634 |
| Opus 5 | $0.00023 | $0.00317 |
| Sonnet 5 | $0.00009 | $0.00127 |
| Haiku 4.5 | $0.00005 | $0.00063 |
Grade A, and why
critique 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 4d 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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/critique
Critique the current interface with the eye of a senior design director. This is not an audit. Rule compliance is the floor. This is about the ceiling.
Lens
- Point of view. Does the interface have one? Could this be any app, or is it clearly this app?
- Hierarchy. Is the most important thing the most prominent? Is anything fighting for attention that shouldn't be?
- Rhythm. Does spacing, weight, and density feel orchestrated or arranged?
- Surprise. Is there a memorable moment? Or is every screen predictable?
- Restraint. What could be removed without loss? Usually 20–40% of elements.
- Coherence. Does every screen feel like the same product? Or does each look AI-generated separately?
Failure Modes to Name
| Mode | Symptom | Example diagnosis |
|---|---|---|
| Generic SaaS | Purple gradient, Inter, rounded cards, no distinguishing feature | "This looks like every Y Combinator seed-stage site from 2023." |
| Everything is a button | Too many primary CTAs competing | "The page has 7 primary buttons. Pick 1 per screen." |
| Fear of empty space | Every pixel filled | "Double the page padding. Halve the card count." |
| Fear of weight | Everything is 16px regular | "Headlines need to feel like headlines. Scale up, weight up." |
| Undifferentiated neutrals | Same gray for text, borders, backgrounds | "Pick 3 tiers and stick to them." |
| Over-shadowed | Shadow on every element | "Shadow = elevation = meaningful. Not decoration." |
| AI color cliche | Purple-to-blue or teal-to-pink gradients | "Don't use the default AI palette. Commit to a direction." |
| Font pairing panic | 4+ typefaces | "One display, one body, one mono. That's it." |
| State poverty | Only default state designed | "What happens when it's loading? Empty? Failed?" |
Output Structure
- The headline diagnosis in one sentence. ("This product looks like a dashboard template from 2022, not a product with a point of view.")
- The three biggest problems, each with evidence and prescription.
- The three biggest opportunities — things not wrong yet, but where a specific move would elevate the work.
- One bold swing — a direction change worth considering, even if it's scary.
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.
- 4d ago First seen · 43 lines · 47 tokens per session scan A b73c0c273bed
critique is a command published in the GitHub repository Dragoon0x/canon (5 stars, last pushed 4mo ago), licensed MIT. It adds 47 tokens to every session and 634 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 commands, from other repositories
review-pr
Fetch a pull request diff, run code-reviewer analysis, translate findings to owner voice, and post a single batched inline GitHub review.
freeze
Activate the REA kill switch — writes .rea/HALT with a reason, blocking all governed tool calls until unfrozen.
review
Run the code-reviewer agent against the current branch's diff and produce structured findings.
rea
Print REA session status — autonomy level, HALT state, policy profile, and recent audit entries.
tasks
Read the task store at .rea/tasks.jsonl and render a clean summary table.
plan-work
Invoke the product-owner agent to plan and propose tasks for a goal.