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-gategit 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-gate)<a href="https://agentmods.dev/skills/rafmacalaba/armada/armada-gate"><img src="https://agentmods.dev/badge/skills/rafmacalaba/armada/armada-gate/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/rafmacalaba/armada/armada-gate"><img src="https://agentmods.dev/badge/skills/rafmacalaba/armada/armada-gate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00033 | $0.00411 |
| Opus 5.5 | $0.00013 | $0.00164 |
| Sonnet 5.5 | $0.00007 | $0.00082 |
| Haiku 4.5 | $0.00003 | $0.00041 |
Grade A, and why
armada-gate 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 1mo 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
You are gating an armada phase. Verify every success criterion in the current phase with evidence.
Process
- Read the current phase in
armada/REQUIREMENTS.md. Note its success criteria. - For each criterion, gather evidence:
- If it involves a test run: run the test command and capture output.
- If it involves a visual check: capture a screenshot.
- If it involves file presence or content: verify on disk.
- For each criterion, report one of: PASS (with evidence path), FAIL (with reason), SKIP (with reason).
- If all criteria pass, the phase gates. Report "PHASE PASS" and update the phase status.
- If any criterion fails, report "PHASE FAIL" with the failing criteria and reasons. Do not proceed.
Evidence format
Phase: <N> -- <name>
Criteria:
[PASS] <criterion> -- evidence: <path or output snippet>
[FAIL] <criterion> -- reason: ...
[SKIP] <criterion> -- reason: ...
Result: PASS | FAIL
Adaptive depth
- QA always gates. Low risk uses focused smoke and acceptance; medium uses affected tests and integration smoke; high uses full relevant and negative-path evidence.
- Activate security, adversary, or architect only when risk or changed surface requires them.
- Group findings by root cause, files, or threat class before remediation. Only
BLOCKINGstops phase; defer unrelated pre-existing findings with rationale.
Rules
- Never skip a criterion without a documented reason.
- Evidence paths must be relative to the repo root.
- Screenshots go in
armada/screenshots/<feature>/. - Test output goes in the gate report. Keep it terse.
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.
- 1mo ago First seen · 43 lines · 33 tokens per session scan A 97fa72c2ab26
armada-gate is a skill published in the GitHub repository rafmacalaba/armada (103 stars, last pushed 1mo ago), licensed MIT. It adds 33 tokens to every session and 411 once invoked, about $0.0001 per session on Opus 5.5. 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
create-issue
Draft and submit a GitHub issue from a user idea or bug description, with bilingual body and correct labels.
requirements-writer
Use when converting PM intake into a slice SPEC.md with observable acceptance outcomes, explicit scope, and advisory sibling build dependencies.
backlog-capture
Quickly capture product ideas, feature requests, or insights from meetings and conversations. Rapid documentation with smart categorization and deduplication.
queue-handoff
Use when ending a turn, finishing a slice, blocked on another agent's work, or escalating to a human — durable work handoff via queue items so the system keeps moving across compactions, missed messages, and interruptions. Covers the hot-potato terminal-turn-rule (active work ends by passing the ball, not by going…
development-team
Use when a development pod begins or hands off implementation, QA, or design work.
swarm-plan
Full execution protocol for MODE: PLAN -- plan creation, external plan ingestion, QA gate persistence, task granularity, and traceability checks.