armada-resume

armada-resume is a skill for Claude Code, Codex from rafmacalaba/armada. It costs 43 tokens per session (261 once invoked), scanned A, original, MIT.

A recovery procedure for an interrupted Armada session. It reads the saved session state, compares it with the files on disk, and continues from the recorded next action.

In plain words
What is it for?
Use it to resume sessions, reconcile phase status, identify missing evidence, and redispatch only unfinished or unsupported phases.
Why use it?
It prevents completed work from being repeated after a crash, timeout, or manual interruption. It also exposes differences between the saved state and the actual project files.

Skill for Claude CodeCodex

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

Good fit Use it to resume sessions, reconcile phase status, identify missing evidence, and…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/rafmacalaba/armada/armada-resume
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 rafmacalaba/armada --skill armada-resume
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.

agentmods badge for armada-resume

README.md
[![agentmods](https://agentmods.dev/badge/skills/rafmacalaba/armada/armada-resume.svg)](https://agentmods.dev/skills/rafmacalaba/armada/armada-resume)
Your own site
<a href="https://agentmods.dev/skills/rafmacalaba/armada/armada-resume"><img src="https://agentmods.dev/badge/skills/rafmacalaba/armada/armada-resume.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 261 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00043 $0.00261
Opus 5 $0.00022 $0.00130
Sonnet 5 $0.00009 $0.00052
Haiku 4.5 $0.00004 $0.00026

Measured 7d ago against content hash 912b79872ecf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

armada-resume 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 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.

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-resume/SKILL.md · 19 lines

What it actually says

Armada: Session Resume

When a session is interrupted (crash, timeout, kill), resume from the last saved state. Do not re-execute completed work. Surface any drift between state and reality.

Rules

  1. On session start, read armada/state/active.json. If it exists, the session is being resumed.
  2. Run armada reconcile (or node src/cli.js reconcile) to detect drift: phases whose status differs from what is on disk.
  3. Print the resume line and drift list. The resume line shows the active feature, last phase, and next action.
  4. Continue execution from nextAction. Do not re-dispatch phases whose status is "passed".
  5. If phaseGraph.phases[*].status is "dispatched", check if the subagent returned evidence. If not, re-dispatch that phase.

Example: armada reconcile shows Phase 2 dispatched but no evidence on disk — re-dispatch Phase 2.

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 · 19 lines · 0 tokens per session scan A 912b79872ecf

Subscribe to this mod's changes

armada-resume is a skill published in the GitHub repository rafmacalaba/armada (95 stars, last pushed 9d ago), licensed MIT. It adds 43 tokens to every session and 261 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.