tp-spike-learn

tp-spike-learn is a skill for Claude Code from CurtisThe/three-pillars-plugin. It costs 32 tokens per session (2,052 once invoked), scanned A, original, Apache-2.0.

A follow-up step that reviews the results of a technical investigation, called a spike, and proposes updates to project documents and related designs.

In plain words
What is it for?
Use it after a completed spike to update the roadmap, record conclusions, and identify downstream designs that may be affected.
Why use it?
It connects investigation findings back to the wider project, so useful discoveries do not remain isolated in the spike's files.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Part of the three-pillars plugin — 37 skills, 20 agents shipped together

Install

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.

agentmods
npx agentmods add skills/curtisthe/three-pillars-plugin/tp-spike-learn
Any agent
npx skills add CurtisThe/three-pillars-plugin --skill tp-spike-learn
Clone the repo
git clone --depth 1 https://github.com/CurtisThe/three-pillars-plugin

Made for: Claude Code.

Or install three-pillars, the plugin that ships this one along with the rest of its 37 skills, 20 agents.

Wrote 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.

agentmods badge for tp-spike-learn

README.md
[![agentmods](https://agentmods.dev/badge/skills/curtisthe/three-pillars-plugin/tp-spike-learn.svg)](https://agentmods.dev/skills/curtisthe/three-pillars-plugin/tp-spike-learn)
Your own site
<a href="https://agentmods.dev/skills/curtisthe/three-pillars-plugin/tp-spike-learn"><img src="https://agentmods.dev/badge/skills/curtisthe/three-pillars-plugin/tp-spike-learn.svg" alt="Measured on agentmods" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,052 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00032 $0.02052
Opus 5 $0.00016 $0.01026
Sonnet 5 $0.00006 $0.00410
Haiku 4.5 $0.00003 $0.00205

Measured 6d ago against content hash 2121f174901b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

tp-spike-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 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.

skills/tp-spike-learn/SKILL.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Spike Learn

Read a completed spike's artifacts and synthesize learnings into proposed updates for project docs and downstream designs.

Argument: {spike-name} (required) — must match an existing directory under three-pillars-docs/tp-designs/.

Prerequisites

  • three-pillars-docs/tp-designs/{spike-name}/spike-results.md must exist. If not, tell the user to run /tp-spike-results {spike-name} first and stop.

Steps

  1. Run first-run preflight per skills/_shared/first-run.md.

  2. Validate {spike-name} per skills/_shared/validate-name.md.

  3. Read the full spike directory: design.md, plan.md, spike-results.md, and any code or demo artifacts referenced.

  4. Read project docs per skills/_shared/read-project-docs.md.

  5. Update Design Inventory in product_roadmap.md: If the roadmap has a Design Inventory table, find the row for {spike-name} and propose updating its status to a short label + link per skills/_shared/living-doc-format.md (e.g., Done — GO (PR #NN) — [results](completed-tp-designs/…/spike-results.md) or Done — PARTIAL or Done — NO-GO). If the spike is NOT in the table (was created before roadmap registration existed), propose adding a row. Keep What and Status cells short — narrative belongs in the linked spike-results or seed. Show the proposed change and get user confirmation.

  6. Update Current Focus in product_roadmap.md: If the roadmap has a ## Current Focus table, propose changes based on the spike verdict:

    • GO/PARTIAL: Remove or update the spike's row. Update "Blocked By" on any row that listed this spike as a blocker — clear the blocker and update "Next Action" to the now-unblocked step (e.g., "Blocked on S9" → "/tp-design-detail — ready to proceed").
    • NO-GO: Update the spike's row to reflect the verdict. Mark any dependent rows as blocked with an explanation.
    • Promote new items to Current Focus if the verdict unblocks work that wasn't previously listed. Show the proposed Current Focus table and get user confirmation.
  7. Propose updates for each doc that needs changes, following the pattern in skills/_shared/propose-doc-edits.md. Explain why the spike findings motivate each change. For each living doc edited, follow skills/_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 ## History section (newest-first): - YYYY-MM-DD — one-sentence summary. Keep it under 800 non-ws chars.
  8. Learn-verification (advisory): run python3 "$TP_ROOT"/skills/_shared/verify_learn.py --range {default}...tp/{spike-name} --json (where {default} is the base branch — usually master). It reports three-pillars-docs/** lines (living and completed-tp-designs/) that still name a symbol or file this spike 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-6 doc updates. Advisory only — the helper always exits 0 and fails open; never block on it. Surface remaining hits in the step-12 report (and, in --auto, append them to decisions.md). Range note: {default}...tp/{spike-name} (three-dot) diffs merge-base→tp/{spike-name}, surfacing this spike's deletions — not the reverse.

  9. Scan for affected downstream designs: Read all design.md files under three-pillars-docs/tp-designs/ (excluding the current spike). Match architecture decision keywords from spike-results.md against each design's Scope and Entities sections. For each affected design, also check whether its declared dependencies or parent references include the current spike — if so, note whether the spike verdict changes the dependency status.

  10. Propagate NO-GO to dependent rows: If the verdict is NO-GO and step 6 found designs that declare this spike as a dependency (via Dependencies section or Parent field), propose updating those designs' rows in the Design Inventory table. Set their status to include a blocked annotation (e.g., "Designed" → "Blocked — {spike-name} NO-GO"). Show each proposed row change and get user confirmation. This ensures that /tp-plan will see the blocked status when it checks upstream dependencies, closing the feedback loop.

  11. Vision drift check (do not auto-propose vision edits): Compare spike-results.md against three-pillars-docs/vision.md. A spike can legitimately surface that a vision assumption was wrong — for example, a "GO" that reveals the problem is bigger than the vision framed it, or a "NO-GO" that invalidates a principle the vision depends on. If you find a genuine tension, flag it to the user with a specific citation (which finding, which vision bullet) and recommend /tp-docs-update vision as an explicit follow-up. Do not propose vision edits directly from this skill. Spike verdicts feed the vision via a deliberate human gate, not automatically.

  12. Commit the doc updates per skills/_shared/commit-after-work.md. Artifact paths to stage (include only those actually modified in steps 4–9):

    • three-pillars-docs/product_roadmap.md
    • three-pillars-docs/architecture.md
    • three-pillars-docs/known_issues.md
    • three-pillars-docs/known_issues_resolved.md (when this learn resolves an issue, move its entry verbatim from known_issues.md to this archive — never mark it resolved in place)
    • Any downstream three-pillars-docs/tp-designs/{other}/design.md files whose Design Inventory row was updated with a blocked annotation per step 9 Do NOT stage three-pillars-docs/vision.md — this skill never auto-edits vision. Commit message: Learn: {spike-name} spike.
  13. Report: Summarize what was updated, what designs are affected, any vision tensions flagged, and suggest /tp-design-complete {spike-name} as the next step.

Read the full file on GitHub · 63 lines

Changes

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.

  1. 6d ago First seen · 63 lines · 32 tokens per session scan A 2121f174901b

Subscribe to this mod's changes

tp-spike-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 32 tokens to every session and 2,052 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

microsoft/vscode · 72 tokens

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.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens