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 CurtisThe/three-pillars-plugin --skill tp-design-auditgit clone --depth 1 https://github.com/CurtisThe/three-pillars-pluginWrote 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/curtisthe/three-pillars-plugin/tp-design-audit)<a href="https://agentmods.dev/skills/curtisthe/three-pillars-plugin/tp-design-audit"><img src="https://agentmods.dev/badge/skills/curtisthe/three-pillars-plugin/tp-design-audit/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/curtisthe/three-pillars-plugin/tp-design-audit"><img src="https://agentmods.dev/badge/skills/curtisthe/three-pillars-plugin/tp-design-audit.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00023 | $0.03544 |
| Opus 5.5 | $0.00009 | $0.01418 |
| Sonnet 5.5 | $0.00005 | $0.00709 |
| Haiku 4.5 | $0.00002 | $0.00354 |
Grade A, and why
tp-design-audit 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 today.
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 — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Audit
Thorough multi-angle review of a detailed design against the actual codebase. Catches interface mismatches, schema conflicts, resource constraints, and implementation feasibility issues before code is written.
Argument: {design-name} (required) — must match an existing directory under three-pillars-docs/tp-designs/.
Prerequisites
three-pillars-docs/tp-designs/{design-name}/detailed-design.mdmust exist.
Steps
- Run first-run preflight per skills/_shared/first-run.md.
0. Preflight
Run the collaboration preflight per skills/_shared/collaboration.md with phase: "design-audit". The audit may update detailed-design.md and plan.md in Step 8 — the lock ensures those edits come from the rightful owner. Honor --force-takeover if passed.
0b. Repo-map preamble (optional)
Per skills/_shared/repo-map-preamble.md. If aider is on PATH, generate a structural map of the codebase before audit. Use it to focus the parallel exploration agents in Step 2 — verifying interfaces against files PageRank confirms exist is faster than launching agents blind.
1. Load design artifacts
Read both design.md and detailed-design.md from the design directory.
1b. Read project context
Read project docs per skills/_shared/read-project-docs.md. Check that the design does not contradict decisions recorded in architecture.md. Flag contradictions as INCONSISTENT findings.
1c. Vision alignment check
Read three-pillars-docs/vision.md if it exists and explicitly evaluate:
- Advances the vision? Which problem, principle, or user from
three-pillars-docs/vision.mddoes this design serve? If you can't name one, flag this as a CRITICAL MISALIGNMENT finding — either the design should not be built, or the vision is stale and needs/tp-docs-update. - Conflicts with non-goals? Does any module, behavior, or interface in the detailed design cross into territory the vision has marked as a non-goal? Flag as CRITICAL MISALIGNMENT with a specific citation (file path in detailed-design + vision bullet).
- Violates principles? Does the design's approach trade away a vision principle for convenience? (e.g., vision says "no network calls" but the design introduces a telemetry endpoint). Flag as MEDIUM MISALIGNMENT unless the design explicitly acknowledges and justifies the trade-off in its own document.
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.
- today Changed 35fe378f7480
- 9d ago Changed · +9 lines 200cdca741e7
- 29d ago Changed · +20 lines 79037c5a7d91
- 1mo ago First seen · 146 lines · 23 tokens per session scan A 4aabc0faa1df
tp-design-audit is a skill published in the GitHub repository CurtisThe/three-pillars-plugin (4 stars, last pushed yesterday), licensed Apache-2.0. It adds 23 tokens to every session and 3,544 once invoked, about $0.0001 per session on Opus 5.5. 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
nw-fp-usable-design
Naming conventions, API ergonomics, and usability patterns for functional code.
design-reviewer
Use after AC and before RED for any wave that ships UI. Performs component API audit against installed dist files, produces per-route mockup, defines visual ACs, flags design-system gaps. Output written to .wave/dr.md.
frontend-design
A guide to building polished web interfaces, including their layout, colors, typography, responsive behavior, and interactive states.
prototype
Build a bounded disposable experiment to resolve a specific uncertainty. Triggers on "prototype", "原型".
a11y-review
A review of a website or application for accessibility, meaning whether people with disabilities can use it. It covers standards such as WCAG, keyboard controls, screen readers, focus, contrast, and color-based signals.
critique-theater
Five-dimension design quality review — score the artifact against craft, brand, accessibility, and copy, then fix what falls short before handing it over.