A command that carries out an implementation plan using test-driven development (TDD), where tests are written or made to fail before the code is completed.

Use it after planning to implement the steps, run the Red–Green–Refactor cycle, and return to planning when the work is done.

It gives implementation work a repeatable test, code, and cleanup cycle while applying basic quality checks.

act — Command by JeremyDev87

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 commands/jeremydev87/codingbuddy/act

Clone the repo

git clone --depth 1 https://github.com/JeremyDev87/codingbuddy

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,857 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.

Model	Per session	Once invoked
Fable 5	$0.00000	$0.01857
Opus 5	$0.00000	$0.00928
Sonnet 5	$0.00000	$0.00371
Haiku 4.5	$0.00000	$0.00186

Measured 2d ago against content hash 8987790d058d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

act 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 2d 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.

packages/claude-code-plugin/commands/act.md · 218 lines

How it starts

The opening of the file, as written. The whole thing — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ACT Mode

Purpose

Execute the implementation plan with TDD

Mode Availability

Standalone Mode (no MCP server)

This command works without the CodingBuddy MCP server. In standalone mode, you get:

Mode detection and transition
TDD cycle execution (Red → Green → Refactor)
Basic quality standards enforcement
Agent-guided implementation

MCP Enhanced Mode

With the CodingBuddy MCP server connected, you additionally get:

parse_mode with full context tracking
Specialist agent dispatch for implementation verification
Contextual checklists (security, accessibility, performance)
Cross-session context persistence

Activation

Invoke via /codingbuddy:act (namespaced) or the ACT keyword.

Legacy bare /act is deprecated. See Migration Guide.

This command activates ACT mode for the CodingBuddy workflow.

Instructions

Important:

ACT mode executes the plan created in PLAN mode
After ACT completes, automatically return to PLAN mode (default behavior)
User can request EVAL for quality assessment

Trigger:

Type ACT after PLAN is ready
Execute implementation steps defined in PLAN

🔴 Agent Activation (STRICT):

When ACT is triggered, the default ACT agent (loaded via parse_mode in MCP mode; Software Engineer in standalone mode) MUST be automatically activated
The Agent's development philosophy and code quality checklist MUST be followed
In MCP mode, the agent framework is loaded via parse_mode. In standalone mode, basic workflow guidance is provided by the mode detection hook.

Purpose: Execute implementation following TDD cycle, augmented coding principles, and quality standards

What ACT does (with Software Engineer):

Execute TDD Cycle (via Software Engineer)
- 🔴 For core logic: Red → Green → Refactor cycle
- Write failing test first
- Implement minimal code to pass
- Refactor only after tests pass
- 🔴 Required: Follow Software Engineer's TDD cycle

Read the full file on GitHub · 218 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.

2d ago First seen · 218 lines · 0 tokens per session scan A 8987790d058d

Subscribe to this mod's changes

act is a command published in the GitHub repository JeremyDev87/codingbuddy (31 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,857 tokens. 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 2026-08-30.

Code review Planning Testing ai-agents ai-coding ai-coding-assistant ai-rules claude-code typescript

act

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

ACT Mode

Purpose

Mode Availability

Standalone Mode (no MCP server)

MCP Enhanced Mode

Activation

Instructions

What this file has done since we first saw it

Other commands, from other repositories

extract

codex-review

raw-export

stats

update-plugins

setup