A set of rules for finishing a feature through a pull request, which is a proposed code change reviewed before it is merged.

Use it to create a pull request, record its link, and report a clear blocker if creating one is not possible.

It keeps feature work reviewable and prevents direct changes to the main branch.

armada-pr — Skill for Claude Code and Codex by rafmacalaba: A set of rules for finishing a feature through…

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/rafmacalaba/armada/armada-pr

Any agent

npx skills add rafmacalaba/armada --skill armada-pr

Clone the repo

git clone --depth 1 https://github.com/rafmacalaba/armada

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/rafmacalaba/armada/armada-pr.svg)](https://agentmods.dev/skills/rafmacalaba/armada/armada-pr)

Your own site

<a href="https://agentmods.dev/skills/rafmacalaba/armada/armada-pr"><img src="https://agentmods.dev/badge/skills/rafmacalaba/armada/armada-pr.svg" alt="Measured on agentmods" height="20"></a>

Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 276 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	$0.00037	$0.00276
Opus 5	$0.00018	$0.00138
Sonnet 5	$0.00007	$0.00055
Haiku 4.5	$0.00004	$0.00028

Measured 4d ago against content hash cf67b0e4b5d6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

armada-pr 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 4d 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.

src/skills/armada-pr/SKILL.md · 19 lines

What it actually says

Armada: PR-First Finish

The final step before reporting a feature lane done is creating a pull request. Never merge locally, never push master directly. The PR URL is the proof of delivery.

Rules

Create the PR from the lane branch: gh pr create --base master. Include a summary of changes and evidence links.
Never git merge locally. Never git push origin master. The PR is the only path to integration.
Write the PR URL into armada/state/active.json field prUrl. Example: "prUrl": "https://github.com/owner/repo/pull/42".
If a PR is genuinely blocked (no remote, no permissions), state "PR blocked: " and report it to the commodore. Do not claim done without a PR URL or a stated blocker.
Do not close or merge the PR yourself. The human partner reviews and merges.

Example: gh pr create --base master --title "feat: skills expansion wave 2.5" --body "Phase 1-3 evidence attached."

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.

4d ago First seen · 19 lines · 0 tokens per session scan A cf67b0e4b5d6

Subscribe to this mod's changes

armada-pr is a skill published in the GitHub repository rafmacalaba/armada (92 stars, last pushed 6d ago), licensed MIT. It adds 37 tokens to every session and 276 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 2026-08-30.

Git and workflow ai-coding automation cli opencode orchestrator scaffolding

aoe

Use when launching, monitoring, or controlling AI coding agents (Claude Code, Codex, OpenCode, etc.) in tmux via Agent of Empires (aoe). Covers creating sessions, capturing agent output, running parallel worktree agents, and organizing work into groups and profiles. Prefer aoe over raw tmux for agent management.

agent-of-empires/agent-of-empires · 71 tokens

aoe

Manage AI coding agent sessions via Agent of Empires (aoe).

agent-of-empires/agent-of-empires · 17 tokens

debate

Structured adversarial analysis protocol. Quick single-agent modes (challenge, panel, pre-mortem, red team) plus a decision-review protocol where one agent proposes, one critiques, the proposer revises, and a binding/advisory judge panel decides ADOPT/REVISE/REJECT/ESCALATE.

EZotoff/ez-omo-config · 67 tokens

update-to-latest

Safety-critical operational pipeline for analyzing and executing OpenCode/OMO updates with explicit approval, patch preservation, rollback capability, and evidence-state discipline.

EZotoff/ez-omo-config · 33 tokens

patch-tracker

Track and verify custom patches to external dependencies. Register, audit, and verify patches survive updates. CRUD lifecycle for patch entries with post-update verification.