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-contractgit 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-contract)<a href="https://agentmods.dev/skills/rafmacalaba/armada/armada-contract"><img src="https://agentmods.dev/badge/skills/rafmacalaba/armada/armada-contract/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-contract"><img src="https://agentmods.dev/badge/skills/rafmacalaba/armada/armada-contract.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 | $0.00363 |
| Opus 5.5 | $0.00013 | $0.00145 |
| Sonnet 5.5 | $0.00007 | $0.00073 |
| Haiku 4.5 | $0.00003 | $0.00036 |
Grade A, and why
armada-contract 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 co-writing an armada contract. The contract is the single source of truth for what to build.
Process
- Ask the user what they want to build. One question at a time.
- After each answer, reflect it back and ask the next logical question.
- Cover: goal, stack constraints, phases, per-phase success criteria, final criteria.
- Phases declare dependencies. Independent phases can run in parallel.
- Success criteria must be demonstrable: a test run, a screenshot, or both.
- When the user is satisfied, write
armada/REQUIREMENTS.mdwith the contract. - The contract must carry
Status: DRAFTuntil the user explicitly approves it. - Once approved, change status to
Status: APPROVED. No implementation starts before approval.
Contract template
# Contract: <feature name>
Status: DRAFT
Commodore: <model>
Stack: <stack>
## Goal
...
## Phases (dependency-ordered)
### Phase 1 -- <name> (no deps)
- [ ] <task>
- [ ] ...
- **Success criteria:** ...
### Phase 2 -- <name> (depends on Phase 1)
- [ ] ...
- **Success criteria:** ...
## Final success criteria
1. ...
2. ...
Rules
- Never start implementation against a DRAFT contract.
- Keep it simple: small phases, clear criteria, no overengineering.
- If the user wants a different feature later, use a separate contract file.
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 · 51 lines · 33 tokens per session scan A 4b76a5a6315a
armada-contract 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 363 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
repo-hygiene
Use when the scheduled repo-hygiene workflow runs from GitHub Actions (or an operator dry-run) to scan the repository for small, certain docs/test/code hygiene issues and fix them as one batched branch.
test-failure-explorer
Import and query an existing Vitest 3.2 JSON report to explore test failures, file-level errors and original diagnostic evidence.
requirements-writer
Use when converting PM intake into a slice SPEC.md with observable acceptance outcomes, explicit scope, and advisory sibling build dependencies.
orchestration-team
Use when coordinating assignments, selected review boundaries, or blocked work across a rig.
oversight-team
Use when you are a seat on the oversight pod (a standing monitor-mode rig that keeps OTHER rigs healthy), configuring or running the drift detectors, or choosing whether to intervene vs escalate. Covers the pull-not-poll posture, the v0 detectors (premature-park, process-drift, off-task, token-burn), the intervention…
find-simplifications
Use for a periodic repo-wide sweep of qwen-code for accumulated excess surface — dead components and files, orphaned locale keys, exports nothing consumes, added-then-removed scaffolding — filing candidates on a tracking issue and landing only what a maintainer has said yes to. Repo-wide and evidence-first; every…