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.
git 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/plugins/curtisthe/three-pillars-plugin/three-pillars-plugin)<a href="https://agentmods.dev/plugins/curtisthe/three-pillars-plugin/three-pillars-plugin"><img src="https://agentmods.dev/badge/plugins/curtisthe/three-pillars-plugin/three-pillars-plugin/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/plugins/curtisthe/three-pillars-plugin/three-pillars-plugin"><img src="https://agentmods.dev/badge/plugins/curtisthe/three-pillars-plugin/three-pillars-plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
three-pillars 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{
"name": "three-pillars",
"version": "2.5.1",
"description": "Structured TDD pipeline, council deliberation, and session continuity for Claude Code",
"author": {
"name": "Curtis"
},
"license": "Apache-2.0",
"homepage": "https://github.com/CurtisThe/three-pillars-plugin",
"repository": "https://github.com/CurtisThe/three-pillars-plugin",
"keywords": ["tdd", "council", "spike", "design", "session"],
"skills": "./skills/",
"hooks": "./skills/_shared/hooks/claude-code-hooks.json",
"agents": [
"./agents/council-ada-medium.md",
"./agents/council-ada.md",
"./agents/council-aristotle-medium.md",
"./agents/council-aristotle.md",
"./agents/council-aurelius-medium.md",
"./agents/council-aurelius.md",
"./agents/council-feynman-medium.md",
"./agents/council-feynman.md",
"./agents/council-kahneman-medium.md",
"./agents/council-kahneman.md",
"./agents/council-karpathy-medium.md",
"./agents/council-karpathy.md",
"./agents/council-lao-tzu-medium.md",
"./agents/council-lao-tzu.md",
"./agents/council-machiavelli-medium.md",
"./agents/council-machiavelli.md",
"./agents/council-meadows-medium.md",
"./agents/council-meadows.md",
"./agents/council-munger-medium.md",
"./agents/council-munger.md",
"./agents/council-musashi-medium.md",
"./agents/council-musashi.md",
"./agents/council-rams-medium.md",
"./agents/council-rams.md",
"./agents/council-socrates-medium.md",
"./agents/council-socrates.md",
"./agents/council-sun-tzu-medium.md",
"./agents/council-sun-tzu.md",
"./agents/council-sutskever-medium.md",
"./agents/council-sutskever.md",
"./agents/council-taleb-medium.md",
"./agents/council-taleb.md",
"./agents/council-torvalds-medium.md",
"./agents/council-torvalds.md",
"./agents/council-watts-medium.md",
"./agents/council-watts.md",
"./agents/tp-certifier.md",
"./agents/tp-drafter-xhigh.md",
"./agents/tp-drafWhat it installs
The manifest is a name and a version. 39 skills, 58 agents travel with it, and installing the plugin installs all of them — 3,897 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill tp-design-complete A 52 tokens
- Skill tp-merge-from-main A 85 tokens
- Skill tp-pr-iterate A 85 tokens
- Skill council A 27 tokens
- Skill tp-plan-audit A 34 tokens
- Skill tp-post-merge A 58 tokens
- Skill tp-implementation-audit A 26 tokens
- Skill tp-phase-implement A 33 tokens
- Skill tp-pr-fix A 50 tokens
- Skill tp-design A 36 tokens
- Skill tp-design-audit A 23 tokens
- Skill tp-merge A 107 tokens
- Skill tp-plan A 33 tokens
- Skill tp-promote A 97 tokens
- Skill tp-run-full-design A 42 tokens
- Skill tp-revert A 44 tokens
- Skill tp-test-setup A 43 tokens
- Skill tp-design-detail A 31 tokens
- Skill tp-docs-init A 70 tokens
- Skill tp-guide A 29 tokens
- Skill tp-phase-review A 27 tokens
- Skill tp-spike A 31 tokens
- Skill tp-spike-auto A 30 tokens
- Skill tp-escalate A 48 tokens
- Skill tp-session-save A 33 tokens
- Skill tp-setup A 45 tokens
- Skill tp-spike-results A 36 tokens
- Skill tp-design-release A 40 tokens
- Skill tp-inflight A 66 tokens
- Skill tp-spike-plan A 27 tokens
- Skill tp-spec A 25 tokens
- Skill tp-design-learn A 34 tokens
- Skill tp-docs-update A 39 tokens
- Skill tp-spike-learn A 32 tokens
- Skill tp-session-restore A 34 tokens
- Skill tp-spike-implement A 27 tokens
- Skill tp-task-cycle A 36 tokens
- Skill tp-migrate A 41 tokens
- Skill tp-session-clear A 33 tokens
- Agent tp-finalizer A 76 tokens
- Agent tp-explainer A 67 tokens
- Agent tp-worker A 35 tokens
- Agent tp-certifier A 46 tokens
- Agent tp-phase-checker A 52 tokens
- Agent tp-readonly-auditor A 40 tokens
- Agent tp-review-confirmer-deep A 44 tokens
- Agent tp-task-worker A 52 tokens
- Agent tp-task-worker-local-medium A 60 tokens
- Agent council-sun-tzu A 34 tokens
- Agent tp-drafter-xhigh A 56 tokens
- Agent tp-impl-auditor A 36 tokens
- Agent tp-generator A 34 tokens
- Agent tp-runbook A 37 tokens
- Agent tp-spawn-host A 34 tokens
- Agent tp-review-confirmer-medium A 27 tokens
- Agent council-meadows A 32 tokens
- Agent council-musashi-medium A 27 tokens
- Agent council-munger-medium A 27 tokens
- Agent council-lao-tzu-medium A 31 tokens
- Agent council-meadows-medium A 27 tokens
- Agent tp-review-confirmer A 39 tokens
- Agent council-aristotle-medium A 29 tokens
- Agent council-watts-medium A 27 tokens
- Agent council-sutskever-medium A 31 tokens
- Agent council-ada A 31 tokens
- Agent council-ada-medium A 27 tokens
- Agent council-machiavelli-medium A 31 tokens
- Agent council-munger A 32 tokens
- Agent council-musashi A 33 tokens
- Agent council-karpathy A 33 tokens
- Agent council-karpathy-medium A 27 tokens
- Agent tp-task-worker-opus-xhigh A 63 tokens
- Agent council-aristotle A 32 tokens
- Agent council-kahneman-medium A 31 tokens
- Agent council-lao-tzu A 34 tokens
- Agent council-feynman A 35 tokens
- Agent council-feynman-medium A 29 tokens
- Agent council-taleb-medium A 27 tokens
- Agent tp-drafter A 50 tokens
- Agent council-aurelius A 32 tokens
- Agent council-aurelius-medium A 29 tokens
- Agent council-socrates A 33 tokens
- Agent council-socrates-medium A 29 tokens
- Agent council-torvalds-medium A 31 tokens
- Agent council-kahneman A 35 tokens
- Agent council-rams-medium A 27 tokens
- Agent council-sutskever A 34 tokens
- Agent council-machiavelli A 33 tokens
- Agent council-taleb A 33 tokens
- Agent council-torvalds A 33 tokens
- Agent tp-task-worker-local-xhigh A 62 tokens
- Agent tp-task-worker-opus-medium A 61 tokens
- Agent tp-task-worker-sonnet-medium A 62 tokens
- Agent tp-task-worker-sonnet-xhigh A 64 tokens
- Agent council-rams A 32 tokens
- Agent council-watts A 32 tokens
- Agent council-sun-tzu-medium A 31 tokens
What ships with it
2 files beside plugin.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · +37 lines 737293e96ffa
- 20d ago Changed · +2 lines 50e2414dbc8a
- 1mo ago First seen · 36 lines scan A 1943d6fb2076
three-pillars is a plugin published in the GitHub repository CurtisThe/three-pillars-plugin (4 stars, last pushed yesterday), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
jira-pack
Issue-tracker pack: /jira-fix takes a ticket link of any type, verifies tracker access, classifies it as a defect or a change, reproduces the defect or writes a failing acceptance test for the change, routes the work to core executors, comments back with evidence and moves the ticket to the QA column. Opt-in; requires.
whetstone
Engineering-craft skills: red-green TDD, flaky-test audit, diagnosis, doubt review, grilling, merge-conflict resolution, research reports with grounded claims, HTML reports, skill linting and a column budget. Every gate among them carries a deterministic self-verify.
es6kr
A collection of AI coding skills including TDD, commit management, dotfile sync, and more.
superpowers-deepseek-v4
Superpowers DeepSeek v4: composable agent skills for TDD, debugging, and collaboration. Independently maintained; not identical to obra/superpowers.
knowledge-virtuoso
15 knowledge skills — design patterns, refactoring, SOLID, debugging, clean architecture, testing, API design, security, scrum, performance, microservices, git workflow, CI/CD, accessibility, and database design.
safeword
AI coding agent workflows: BDD, auto-linting, quality reviews, debugging, and refactoring. Run safeword install in a project to enroll it.