forge-execute

forge-execute is a skill for Claude Code, Codex from srnichols/plan-forge. It costs 39 tokens per session (1,315 once invoked), scanned A, original, MIT.

A guided workflow for carrying out an existing software delivery plan. It lists available plans, estimates their cost, lets you choose an execution mode, and reports progress while the plan runs.

In plain words
What is it for?
Use it to select and run deployment-roadmap phases or other prepared plans. It is for projects that already have plan files and an orchestration setup.
Why use it?
It gives a planned project a repeatable way to move from preparation to execution. It also checks whether the required tools and workers are available before starting.

Skill for Claude CodeCodex

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/srnichols/plan-forge/forge-execute
Any agent
npx skills add srnichols/plan-forge --skill forge-execute
Clone the repo
git clone --depth 1 https://github.com/srnichols/plan-forge

Made for: Claude Code, Codex.

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 forge-execute

README.md
[![agentmods](https://agentmods.dev/badge/skills/srnichols/plan-forge/forge-execute.svg)](https://agentmods.dev/skills/srnichols/plan-forge/forge-execute)
Your own site
<a href="https://agentmods.dev/skills/srnichols/plan-forge/forge-execute"><img src="https://agentmods.dev/badge/skills/srnichols/plan-forge/forge-execute.svg" alt="Measured on agentmods" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,315 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 $0.00039 $0.01315
Opus 5 $0.00019 $0.00658
Sonnet 5 $0.00008 $0.00263
Haiku 4.5 $0.00004 $0.00131

Measured yesterday against content hash 829b6321cd6f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

forge-execute 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 yesterday.

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.

presets/shared/skills/forge-execute/SKILL.md · 142 lines

How it starts

The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Forge Execute Skill

Trigger

"Run my plan" / "Execute the plan" / "Start plan execution" / "Run phase N"

Steps

1. Pre-flight Check

Use the forge_smith MCP tool to verify the environment is ready for plan execution.

Check for:

  • Orchestrator present and ready
  • CLI workers available (gh copilot, claude, or codex)
  • MCP dependencies installed

If no CLI workers available: STOP. Report that gh copilot CLI, claude CLI, or codex CLI must be installed. Suggest mode: 'assisted' as a fallback.

2. List Available Plans

Use the forge_status MCP tool to show all phases from DEPLOYMENT-ROADMAP.md with their current status.

Present to user:

  • Phase name
  • Current status (planned, in-progress, complete, paused)
  • Plan file path

If no plans found: STOP. Report that no DEPLOYMENT-ROADMAP.md or plan files exist. Suggest running the Step 0 (Specify) pipeline prompt first.

3. Plan Selection

If the user didn't specify a plan in the argument:

  • Present the list of available plans from Step 2
  • Ask which plan to execute
  • Confirm the selection

If the user specified a plan: verify the file exists and proceed.

4. Cost Estimate

Use the forge_run_plan MCP tool with estimate: true to get a cost preview without executing.

Present:

  • Number of slices
  • Estimated cost (USD)
  • Model(s) to be used
  • Confidence level of estimate

If estimated cost exceeds $5.00: Warn the user and ask for explicit confirmation before proceeding.

5. Mode Selection

Ask the user to choose execution mode:

  • Auto — CLI worker executes all slices autonomously with validation gates
  • Assisted — Human reviews each slice output, gates run automatically

Also ask:

  • Model preference (or accept default from .forge.json)
  • Whether to enable Quorum mode for high-complexity slices

6. Execute

Use the forge_run_plan MCP tool with the selected parameters:

  • plan: path from Step 3
  • mode: from Step 5
  • model: from Step 5 (or omit for default)
  • quorum: from Step 5 (or "false")

Read the full file on GitHub · 142 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. yesterday First seen · 142 lines · 39 tokens per session scan A 829b6321cd6f

Subscribe to this mod's changes

forge-execute is a skill published in the GitHub repository srnichols/plan-forge (5 stars, last pushed 2d ago), licensed MIT. It adds 39 tokens to every session and 1,315 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 2026-09-03.