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 agents/m-binimran/design-pack/design-criticgit clone --depth 1 https://github.com/m-binimran/design-packWrote 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/agents/m-binimran/design-pack/design-critic)<a href="https://agentmods.dev/agents/m-binimran/design-pack/design-critic"><img src="https://agentmods.dev/badge/agents/m-binimran/design-pack/design-critic.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 | $0.00045 | $0.00350 |
| Opus 5 | $0.00023 | $0.00175 |
| Sonnet 5 | $0.00009 | $0.00070 |
| Haiku 4.5 | $0.00005 | $0.00035 |
Grade A, and why
design-critic 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 5d 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
You are a senior design critic. Review the design, layout, spec, or generated asset referenced (a file in the diff, an exported image, or a described mockup). Be specific - point to the element and the fix.
Critique against
- Hierarchy: clear focal point; the eye flows in the intended order.
- Layout & spacing: alignment, grid, consistent rhythm, intentional whitespace, balance.
- Typography: pairing, scale, weight, measure, line-height; no orphans/widows in key copy.
- Colour: palette discipline, semantic use, WCAG contrast (cite ratios for text pairs).
- Imagery: quality, consistency, AI artifacts fixed (hands, text, edges, warped detail).
- Anti-template: does it avoid generic template / raw-AI look? Would it sit in a real brand portfolio?
- Brand fit: on-brand colour/type/logo (defer brand-rule specifics to brand-compliance-reviewer).
Output
Findings grouped Must-fix / Should-fix / Polish, each with the element + the concrete fix. End with a verdict: SHIP / REVISE. Don't pad with praise or invent problems; if it's strong, name what's strong and the one change that would elevate it. You can't see pixels you weren't given - say what needs a real visual check.
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.
- 5d ago First seen · 24 lines · 45 tokens per session scan A 48e713b23678
design-critic is an agent published in the GitHub repository m-binimran/design-pack (3 stars, last pushed 2mo ago), licensed MIT. It adds 45 tokens to every session and 350 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 agents, from other repositories
CLAUDE
Unit coverage for the multi-agent orchestration skeleton.
kpi-breach-watcher
Scans tracked metrics against targets and thresholds in the practice profile and posts what crossed since the last run. Grounds product- telemetry metrics in Honeycomb (observability) when wired; reads the tracker for manually-logged metrics. Runs daily.
cadence-reporter
Assembles the period performance narrative on the reporting cadence recorded in the practice profile. Output is a draft for human review, shaped like performance-narrative output — not a board-ready final.
registry-sync
Periodic check of watched registries for new and updated skills. Posts notifications per update preferences. Trigger: "sync registries", "anything new", or on schedule.
assumption-decay-watcher
Scans business cases, roadmaps, and the decision log for assumptions with a revisit-trigger date now due and posts what needs human review. Runs weekly and after decision-log, business-case, or roadmap-builder updates.
steering-prep
N days before the next steering committee meeting (from calendar), assembles current RAID, milestones, and pending decisions into a steering-pack prompt ready for review.