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/curtisthe/three-pillars-plugin/tp-design-learnnpx skills add CurtisThe/three-pillars-plugin --skill tp-design-learngit 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-learn)<a href="https://agentmods.dev/skills/curtisthe/three-pillars-plugin/tp-design-learn"><img src="https://agentmods.dev/badge/skills/curtisthe/three-pillars-plugin/tp-design-learn.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 | $0.00034 | $0.02289 |
| Opus 5 | $0.00017 | $0.01144 |
| Sonnet 5 | $0.00007 | $0.00458 |
| Haiku 4.5 | $0.00003 | $0.00229 |
Grade A, and why
tp-design-learn 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Learn
Read a completed design's artifacts and synthesize what was built into proposed updates for project docs and downstream designs.
Argument: {design-name} (required) — must match an existing directory under three-pillars-docs/tp-designs/ or three-pillars-docs/completed-tp-designs/.
Prerequisites
design.mdandimplementation-audit.md(or at minimumplan.mdwith all tasks Done) must exist. If not, tell the user what's missing and stop.
Steps
-
Run first-run preflight per skills/_shared/first-run.md.
-
Validate
{design-name}perskills/_shared/validate-name.md. -
Locate the design directory: check
three-pillars-docs/tp-designs/{design-name}/first, thenthree-pillars-docs/completed-tp-designs/{design-name}/. -
Read the full design directory:
design.md,detailed-design.md,plan.md,implementation-audit.md, and anyreview.mdfiles. -
Read project docs per
skills/_shared/read-project-docs.md. -
Update Design Inventory in
product_roadmap.md: If the roadmap has a Design Inventory table, find the row for{design-name}and propose updating its status to a short label + link perskills/_shared/living-doc-format.md(e.g.,Done — PR #NN — [design](completed-tp-designs/…/design.md)). If the design is NOT in the table (was created before roadmap registration existed), propose adding a row. Keep the What and Status cells short — narrative belongs in the linked design or seed. Show the proposed change and get user confirmation. -
Update Current Focus in
product_roadmap.md: If the roadmap has a## Current Focustable, propose changes:- Remove the completed design's row from Current Focus (it's done).
- Update "Blocked By" on any row that listed this design as a blocker — clear the blocker if this was the only one.
- Promote the next logical item if removing this row leaves a priority gap. Look at the Design Inventory for designs whose dependencies are now satisfied.
- Update "Next Action" on any row whose next step changed because this design completed (e.g., a dependent design can now proceed to
/tp-design-detail). Show the proposed Current Focus table and get user confirmation.
-
Propose updates for each doc that needs changes, following the pattern in
skills/_shared/propose-doc-edits.md. Explain why the completed design motivates each change. For each living doc edited, followskills/_shared/living-doc-format.md:- Update the
*Last updated: YYYY-MM-DD*date on line 2–3. - Append one dated line at the top of the
## Historysection (newest-first):- YYYY-MM-DD — one-sentence summary.Keep it under 800 non-ws chars.
- Update the
-
Learn-verification (advisory): run
python3 "$TP_ROOT"/skills/_shared/verify_learn.py --range {default}...tp/{design-name} --json(where{default}is the base branch — usuallymaster). It reportsthree-pillars-docs/**lines (living andcompleted-tp-designs/) that still name a symbol or file this design retired (deleted/renamed in the diff) — the "learn ran ≠ docs match as-built" gap. Treat any hit as a propagation miss: fold the scrub into the step-7 doc updates. Advisory only — the helper always exits 0 and fails open; never block on it. Surface any remaining hits in the step-12 report (and, in--auto, append them todecisions.md). Range note:{default}...tp/{design-name}(three-dot) diffs merge-base→tp/{design-name}, surfacing this design's deletions — nottp/{design-name}...{default}, which would surface the wrong (base) side.
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 · 72 lines · 34 tokens per session scan A c9f6922da59a
tp-design-learn is a skill published in the GitHub repository CurtisThe/three-pillars-plugin (4 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 34 tokens to every session and 2,289 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…