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.
npx skills add alexdcd/Mafia-Claude-Skills --skill frontier-plan-opencode-executorgit clone --depth 1 https://github.com/alexdcd/Mafia-Claude-SkillsWrote 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.
[](https://agentmods.dev/skills/alexdcd/mafia-claude-skills/frontier-plan-opencode-executor)<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>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 5.1 | $0.00103 | $0.03335 |
| Opus 5 | $0.00051 | $0.01667 |
| Sonnet 5 | $0.00021 | $0.00667 |
| Haiku 4.5 | $0.00010 | $0.00333 |
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` 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 statusshows 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
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.
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.
- 7d ago First seen · 344 lines · 103 tokens per session scan C 309291e10b4e
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.
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…
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…
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).
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…
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-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…