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 rafmacalaba/armada --skill armada-resumegit clone --depth 1 https://github.com/rafmacalaba/armadaWrote 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/rafmacalaba/armada/armada-resume)<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>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 | $0.00043 | $0.00261 |
| Opus 5 | $0.00022 | $0.00130 |
| Sonnet 5 | $0.00009 | $0.00052 |
| Haiku 4.5 | $0.00004 | $0.00026 |
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.
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
- On session start, read
armada/state/active.json. If it exists, the session is being resumed. - Run
armada reconcile(ornode src/cli.js reconcile) to detect drift: phases whose status differs from what is on disk. - Print the resume line and drift list. The resume line shows the active feature, last phase, and next action.
- Continue execution from
nextAction. Do not re-dispatch phases whose status is"passed". - If
phaseGraph.phases[*].statusis"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.
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 · 19 lines · 0 tokens per session scan A 912b79872ecf
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.
Other skills, from other repositories
agentping
Reach the human out-of-band when you are blocked and they may be away from the chat. Sends a real OS notification (or phone push / Slack / custom channel) and can block for the reply: a free-text answer, an approve/deny decision, or a pick-one choice. Use when you need approval before a risky or irreversible action…
batch
Execute batch operations on multiple files in parallel. Automatically discovers files, splits into chunks, and processes with parallel worker agents. Use /batch followed by operation and file pattern.
gws-calendar
Google Calendar: Manage calendars and events.
loop
Create a loop that runs a prompt now and follows up either on a fixed schedule or through self-paced wakeups. Usage - /loop check the build, /loop 5m check the build, /loop check the PR every 30m. /loop list to show jobs, /loop clear to cancel all.
gws-gmail-reply
Gmail: Reply to a message (handles threading automatically).
gws-gmail-send
Skill "gws-gmail-send" from googleworkspace/cli, covering gmail +send, usage, flags, examples and tips.