tp-phase-implement

An implementation step that carries out tasks from plan.md using red-green-refactor cycles: write a failing test, make it pass, then improve the code.

In plain words
What is it for?
It is for completing one or more planned phases, including independent tasks that can be handled separately.
Why use it?
It prevents work from proceeding without an approved plan audit and helps keep implementation tied to planned tasks.

Skill for Claude CodeCodex

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

Made for: Claude Code, Codex.

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

Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,007 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 $0.00033 $0.03007
Opus 5 $0.00016 $0.01503
Sonnet 5 $0.00007 $0.00601
Haiku 4.5 $0.00003 $0.00301

Measured 3d ago against content hash 24a2b379e371, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tp-phase-implement 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 3d 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-phase-implement/SKILL.md · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Phase Implement

Execute one or more phases from the implementation plan.

Argument: {design-name} (required), optionally followed by a phase number (e.g., my-feature 2 for Phase 2 only). Without a phase number, executes the next incomplete phase.

Prerequisites

  • three-pillars-docs/tp-designs/{design-name}/plan.md must exist. If not, tell the user to run /tp-plan {design-name} first and stop.
  • A current, passing plan-audit artifact must exist for this plan.md (fail-closed gate — see preflight step 0b). Absent, failing, or stale-vs-plan.md ⇒ refuse, naming /tp-plan-audit {design-name} as the remedy.

Steps

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

0a. Run cwd preflight per skills/_shared/cwd-preflight.md: python3 "$TP_ROOT"/skills/_shared/cwd_preflight.py {design-name}. Exit 3 → stop and show the cd fix. Exit 0 → continue.

0b. Run the plan-audit gate (fail-closed): python3 "$TP_ROOT"/skills/tp-plan-audit/scripts/audit_artifact.py --check three-pillars-docs/tp-designs/{design-name}. A non-zero exit means no current passing plan-audit exists for this plan.md — the artifact is absent (audit never run / failed, which writes nothing), or stale because plan.md changed after the last passing audit. In every non-zero case, REFUSE before any task cycle and tell the user to run /tp-plan-audit {design-name} (re-audit the current plan.md). Exit 0 → the audit is current and passing → continue.

  1. Run collaboration preflight per skills/_shared/collaboration.md with phase: "implement". This is the highest-risk skill — verifying the branch and lock before writing code is essential. Honor --force-takeover if passed.
  2. Read plan.md from the design directory.
  3. Determine which phase to execute:
    • If a phase number was given, use that.
    • Otherwise, find the first phase with unfinished tasks (check if the test files/functions exist and pass).
  4. Show the user which phase you're about to execute and how many tasks it contains. Ask for confirmation.
  5. For each task in the phase, execute a red-green-refactor cycle:

Read the full file on GitHub · 116 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. 3d ago First seen · 116 lines · 33 tokens per session scan A 24a2b379e371

Subscribe to this mod's changes

tp-phase-implement is a skill published in the GitHub repository CurtisThe/three-pillars-plugin (4 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 33 tokens to every session and 3,007 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

agent-integration

Run all three agent integration phases sequentially: research, write-tests, and implement using E2E-first TDD (unit tests written last). For individual phases, use /agent-integration:research, /agent-integration:write-tests, or /agent-integration:implement. Use when the user says "integrate agent", "add agent…

entireio/cli · 89 tokens

engram-testing-coverage

TDD and coverage standards for Engram. Trigger: When implementing behavior changes in any package.

Gentleman-Programming/engram · 25 tokens

code-assist

Guides implementation of code tasks using test-driven development in an Explore, Plan, Code, Commit workflow. Acts as a Technical Implementation Partner and TDD Coach — following existing patterns, avoiding over-engineering, and producing idiomatic, modern code.

mikeyobrien/ralph-orchestrator · 53 tokens

tdd

Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.

GreyDGL/PentestGPT · 33 tokens

css-design-tdd

Test-driven CSS design system modifications. Run checks before/after CSS changes to verify token usage, variable definitions, fallbacks, and consistency. Use when modifying CSS tokens, fixing design inconsistencies, or auditing CSS architecture.

xiaolai/vmark · 49 tokens

mobiai-mobile-tdd

You MUST use this before writing any implementation code for a mobile feature, bug fix, refactor, or behavior change. Tests come before implementation — no exceptions.

ArisGuimera/MobiAI-Core · 38 tokens