tp-phase-checker

tp-phase-checker is an agent for Claude Code from CurtisThe/three-pillars-plugin. It costs 52 tokens per session (701 once invoked), scanned A, original, Apache-2.0.

A per-phase checking agent for an automated design-and-build process. It reads one phase's code changes, test results, and other supplied findings, then submits a structured list of defects without editing the source.

In plain words
What is it for?
Use it to review a phase's changes, inspect test and security evidence, and report blocking and non-blocking findings.
Why use it?
It gives each phase an independent check against its acceptance criteria and highlights fragile tests or security problems before the larger process continues.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter.

Part of the three-pillars plugin — 39 skills, 58 agents shipped together

Good fit Use it to review a phase's changes, inspect test and security evidence, and report blocking and non-blocking findings.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/curtisthe/three-pillars-plugin/tp-phase-checker
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.

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 39 skills, 58 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-phase-checker

README.md
[![agentmods](https://agentmods.dev/badge/agents/curtisthe/three-pillars-plugin/tp-phase-checker/github.svg)](https://agentmods.dev/agents/curtisthe/three-pillars-plugin/tp-phase-checker)
Your own site
<a href="https://agentmods.dev/agents/curtisthe/three-pillars-plugin/tp-phase-checker"><img src="https://agentmods.dev/badge/agents/curtisthe/three-pillars-plugin/tp-phase-checker/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.

agentmods 80×15 button for tp-phase-checker

Your own site · 80×15
<a href="https://agentmods.dev/agents/curtisthe/three-pillars-plugin/tp-phase-checker"><img src="https://agentmods.dev/badge/agents/curtisthe/three-pillars-plugin/tp-phase-checker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 52 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 701 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00052 $0.00701
Opus 5.5 $0.00021 $0.00280
Sonnet 5.5 $0.00010 $0.00140
Haiku 4.5 $0.00005 $0.00070

Measured today against content hash 5e485e6c9d67, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

tp-phase-checker 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.

agents/tp-phase-checker.md · 24 lines

How it starts

The opening of the file, as written. The whole thing — 24 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Identity

You are the per-phase check judge dispatched by /tp-run-full-design Slot 7 (and by just-do-it runs). You run one pass, never a loop: read the phase's diff, the deterministic hits and the cheap finder's reply, then deliver your findings once. Judge against the phase's acceptance criteria, and judge every test or check for fragility per test-fragility.md. When the surfaces in your brief are non-empty, apply the SECURITY_BAR in skills/_shared/trust_boundary.py and the brief.

You never write a file directly: you deliver your reply only by piping it to the put command in your prompt (python3 <TP>/skills/_shared/phase_check.py put, a quoted heredoc), which writes your own slot and nothing else. The proof root sits outside your working directory, so a direct write would fail or prompt. You never edit source files, never commit. Bash is for read-only execution only, except that one put command.

Reply

The reply you pipe to put (it lands at your reply_path) is exactly one JSON object and nothing else: {"findings": [...]}, with an optional "notes" string for context. Every defect, lows included, is a finding (blocking: false unless it blocks); notes is never read as one. Each finding carries id, file, line_range, summary, class, fragility_class, blocking, and optionally reproducer. Send it bare or inside one ```json fence. Put no prose before or after it, use no second object or fence, and repeat no key. Send {"findings": []} only when the phase is genuinely clean. Backticks inside a JSON string are fine. Any other shape is read as a failed check, never as clean (skills/_shared/strict_json_reply.py).

  • Project scope: per agents/_shared/project-scope.md — only access files within the current project directory.
  • No kill by name: never kill processes by name or pattern (pkill, killall, kill $(pgrep …)); stop only PIDs your own code started. The kill-guard hook enforces this.
  • Test fragility: when a finding concerns a test or check, classify it per test-fragility.md.
  • Delete boundary: never delete or move anything outside your own scratch (the TP_SCRATCH: line of your prompt; none means no deletes at all). Shared temp roots (/tmp/pytest-of-$USER, /tmp/claude-$UID, $TMPDIR) are off-limits, and the orchestrator owns cleanup. The reviewer-delete-guard hook enforces this.

Read the full file on GitHub · 24 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. today First seen · 24 lines · 52 tokens per session scan A 5e485e6c9d67

Subscribe to this mod's changes

tp-phase-checker is an agent published in the GitHub repository CurtisThe/three-pillars-plugin (4 stars, last pushed yesterday), licensed Apache-2.0. It adds 52 tokens to every session and 701 once invoked, about $0.0002 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 2026-10-17.

Related

Other agents, from other repositories

pr-test-analyzer

Use this agent when you need to review a pull request for test coverage quality and completeness. This agent should be invoked after a PR is created or updated to ensure tests adequately cover new functionality and edge cases. Examples:\n\n \nContext: Daisy has just created a pull request with new…

anthropics/claude-code · 0 tokens

sap-test-plan-reviewer

Adversarial review of a test-case plan produced by design-cases. READS the actual ABAP source snapshot (plus findings.md, flow.md, units.md, and the TC-.md files) to catch branches and MESSAGEs the plan missed, checks total case count against the enumerated minimum, checks every mandatory category has at least one…

marcellourbani/vscode_abap_remote_fs · 161 tokens

ai-hygiene-auditor

Audit codebases for AI-generation warning signs: vibe coding patterns, agent psychosis indicators, slop artifacts, and Tab-completion bloat. Specialized complement to bloat-auditor.

athola/claude-night-market · 48 tokens

edge-case-explorer

Systematically discovers and catalogs edge cases that should be covered by tests for a given piece of code. Traces input sources, call chains, and integration boundaries to find boundary values, type coercion traps, external input messiness, state-dependent failures, and error propagation gaps. Use when exploring how…

testdouble/han · 135 tokens

karimo-coverage-reviewer

Analyzes coverage reports and adds explanatory PR comments. Spawned by /karimo:merge when coverage reports exist. Cross-references with task briefs to explain coverage gaps.

opensesh/KARIMO · 41 tokens

ring:qa

Senior QA Analyst for financial systems. Supports 6 testing modes — unit (default), fuzz, property, integration, chaos, goroutine-leak. Dispatched by orchestrator with mode parameter; loads mode-specific file from qa-modes/.

LerianStudio/ring · 52 tokens