frontier-plan-opencode-executor

frontier-plan-opencode-executor is a skill for Claude Code, Codex from alexdcd/Mafia-Claude-Skills. It costs 103 tokens per session (3,335 once invoked), scanned C, original, Apache-2.0.

A procedure for carrying out a detailed implementation plan from an advanced AI model in OpenCode, a coding environment that can use other models.

In plain words
What is it for?
Use it for multi-step implementation plans when each change should be applied gradually, checked, and reviewed for unsafe or destructive effects.
Why use it?
It checks the plan against the real repository before changes are made, reducing errors caused by incorrect file names, imports, assumptions, or missing tests.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents; mentions AGENTS.md; mentions OpenCode.

Good fit Use it for multi-step implementation plans when each change should be applied…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/alexdcd/mafia-claude-skills/frontier-plan-opencode-executor
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.

Any agent
npx skills add alexdcd/Mafia-Claude-Skills --skill frontier-plan-opencode-executor
Clone the repo
git clone --depth 1 https://github.com/alexdcd/Mafia-Claude-Skills

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 frontier-plan-opencode-executor

README.md
[![agentmods](https://agentmods.dev/badge/skills/alexdcd/mafia-claude-skills/frontier-plan-opencode-executor.svg)](https://agentmods.dev/skills/alexdcd/mafia-claude-skills/frontier-plan-opencode-executor)
Your own site
<a href="https://agentmods.dev/skills/alexdcd/mafia-claude-skills/frontier-plan-opencode-executor"><img src="https://agentmods.dev/badge/skills/alexdcd/mafia-claude-skills/frontier-plan-opencode-executor.svg" alt="Measured on agentmods" height="20"></a>
Per session 103 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,335 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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 $0.00103 $0.03335
Opus 5 $0.00051 $0.01667
Sonnet 5 $0.00021 $0.00667
Haiku 4.5 $0.00010 $0.00333

Measured 7d ago against content hash 309291e10b4e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade C, and why

frontier-plan-opencode-executor scanned grade C with 1 finding 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 7d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

- `rm -rf`
skills/frontier-plan-opencode-executor/SKILL.md · 344 lines

How it starts

The opening of the file, as written. The whole thing — 344 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Frontier Plan OpenCode Executor

Core Principle

The frontier plan is a strong hypothesis, not ground truth.

Execute the intent of the plan step by step, but validate every instruction against the actual repository before editing code. Frontier AI plans frequently fail on: nonexistent file names, invented imports, unavailable libraries, patterns that don't match the repo, missing tests, idealized architecture, and breaking internal APIs.

Never batch large changes. Never skip verification. Never hide uncertainty. Never perform destructive actions without explicit approval.

When to Use

  • You receive a detailed, multi-step implementation plan written by a frontier AI
  • The plan has 3+ distinct steps with specific file paths and code patterns
  • You are using a non-frontier coding model that benefits from execution discipline
  • The plan carries risk of conflicting with the actual codebase

Do NOT use for:

  • Single-file changes or trivial fixes
  • Plans with only 1-2 simple steps
  • Plans you wrote yourself during the same session
  • Rapid iteration where the user wants speed over safety

Core Workflow

0. PREFLIGHT: Establish Repository Baseline

Before touching any file, understand the repo state and detect pre-existing failures.

1. git status --short          # Is the repo clean?
2. Inspect package.json         # Available scripts, dependencies
3. Inspect AGENTS.md, README.md # Project conventions, commands
4. Detect available verification commands from package.json scripts
5. Run the cheapest baseline verification if available (lint or typecheck)

If baseline already fails:

  • Record the failure explicitly: exact command, exit status, and short error summary
  • Do NOT attempt broad cleanup or fix unrelated issues
  • Continue only if the planned change can be isolated from the existing failure
  • Do not attribute pre-existing failures to your implementation

Dangerous state detection:

  • If git status shows uncommitted changes unrelated to the plan, warn the user
  • If lockfiles are modified, warn the user
  • If the repo is in a conflicted/rebasing state, stop and ask

Read the full file on GitHub · 344 lines

Files

What ships with it

1 file beside SKILL.md 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.

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. 7d ago First seen · 344 lines · 103 tokens per session scan C 309291e10b4e

Subscribe to this mod's changes

frontier-plan-opencode-executor is a skill published in the GitHub repository alexdcd/Mafia-Claude-Skills (48 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 103 tokens to every session and 3,335 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

claude-md-improver

Audit and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, improve, or fix CLAUDE.md files. Scans for all CLAUDE.md files, evaluates quality against templates, outputs quality report, then makes targeted updates. Also use when the user mentions "CLAUDE.md maintenance" or "project…

anthropics/claude-plugins-official · 82 tokens

agent-platform-rag-engine-management

Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…

google/skills · 85 tokens

gke-reliability

Improves GKE workload reliability, using PDBs, health probes, and topology spread constraints. Use when configuring GKE workload reliability, setting up PDBs, or configuring GKE health probes (liveness, readiness, startup). Don't use for disaster recovery setup or full cluster backups (use gke-backup-dr instead).

google/skills · 73 tokens

gke-workload-security

Audits, configures, and hardens workload-level security controls for Google Kubernetes Engine (GKE) applications and namespaces. Covers running cluster security audits (auditcluster.sh), configuring Workload Identity Federation (impersonation, KSA/GSA binding, and pod setup), enforcing Network Policies (default-deny…

google/skills · 181 tokens

agent-platform-model-registry

Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.

google/skills · 60 tokens

google-cloud-solution-agentic-analytics-spark-knowledge-catalog

Discovers requirements and generates guidance to design and deploy a governed, secure agentic-analytics solution for data that's distributed across Google Cloud, other cloud providers, or on-premises. Data that's outside Google Cloud (such as data from Databricks, Snowflake, Salesforce, SAP, or Oracle systems) is…

google/skills · 138 tokens