armada-context-budget

armada-context-budget is a skill for Claude Code, Codex from rafmacalaba/armada. It costs 35 tokens per session (263 once invoked), scanned A, original, MIT.

A set of rules for keeping AI-agent responses and working context short. A sub-agent is an AI helper assigned a specific part of a larger task.

In plain words
What is it for?
Use it when coordinating sub-agents or working on code tasks where concise responses, focused file reading, and evidence-based reviews matter.
Why use it?
It reduces unnecessary reading and explanation when the available context is limited. It encourages decisions supported by diffs and test results.

Skill for Claude CodeCodex

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

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-context-budget
Any agent
npx skills add rafmacalaba/armada --skill armada-context-budget
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-context-budget

README.md
[![agentmods](https://agentmods.dev/badge/skills/rafmacalaba/armada/armada-context-budget.svg)](https://agentmods.dev/skills/rafmacalaba/armada/armada-context-budget)
Your own site
<a href="https://agentmods.dev/skills/rafmacalaba/armada/armada-context-budget"><img src="https://agentmods.dev/badge/skills/rafmacalaba/armada/armada-context-budget.svg" alt="Measured on agentmods" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 263 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00035 $0.00263
Opus 5 $0.00017 $0.00131
Sonnet 5 $0.00007 $0.00053
Haiku 4.5 $0.00003 $0.00026

Measured 6d ago against content hash d0cb152b5412, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

armada-context-budget 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 6d 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-context-budget/SKILL.md · 19 lines

What it actually says

Armada: Context Budget

Token context is finite and expensive. Every word you type costs the fleet. Be terse. Lead with the decision. Never narrate. This is for all subagents, always.

Rules

  1. Read diffs, not whole source trees. Use git diff and test output for evidence; do not read files you do not need to change.
  2. One-line answers where possible. Lead with the decision or verdict, then supporting detail only when needed.
  3. Use path:line references instead of prose descriptions. Example: src/skills/index.js:42 not "in the skills index file around line 42."
  4. No narration, no recap, no pleasantries, no filler words. Skip articles where meaning is clear.
  5. Do not micro-manage. Dispatch a subagent with a task spec and trust it. Review evidence, not process.

Example: "PASS. Tests green. Diff: +210/-0. All 9 skills registered." — not "I have completed the work and all tests are passing."

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. 6d ago First seen · 19 lines · 0 tokens per session scan A d0cb152b5412

Subscribe to this mod's changes

armada-context-budget is a skill published in the GitHub repository rafmacalaba/armada (95 stars, last pushed 8d ago), licensed MIT. It adds 35 tokens to every session and 263 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.

Related

Other skills, from other repositories

swarm-pr-review

Run a graph-guided, tool-augmented PR review using context packing, parallel exploration, mandatory repository-agnostic risk-family coverage with dispatch scaled to diff size and risk, independent reviewer validation, critic challenge, and metrics writeback. Use for deep pull request review with low false-positive…

ZaxbyHub/opencode-swarm · 91 tokens

swarm-plan

Full execution protocol for MODE: PLAN -- plan creation, external plan ingestion, QA gate persistence, task granularity, and traceability checks.

ZaxbyHub/opencode-swarm · 32 tokens

loop

Full execution protocol for MODE: LOOP — the compound-engineering loop: brainstorm → plan → build → review → improve, iterating under defense-in-depth stop conditions with generator/critic separation, durable resumable state, and mandatory compounding learning capture. Loaded on demand by the architect when the loop…

ZaxbyHub/opencode-swarm · 72 tokens

council

Full execution protocol for MODE: COUNCIL -- General Council research, parallel member dispatch, disagreement handling, and synthesis.

ZaxbyHub/opencode-swarm · 28 tokens

deep-research

Full execution protocol for MODE: DEEPRESEARCH — orchestrator-worker deep research over external sources: decompose, iterative websearch/webfetch retrieval, parallel sme synthesis, dual-reviewer claim verification, critic challenge of high-stakes claims, and a cited report. Loaded on demand by the architect when the…

ZaxbyHub/opencode-swarm · 82 tokens

safe-extraction

Apply when extracting code from a large monolith file into submodules. Covers barrel re-exports, internals DI seam proxy patterns, CI invariant allowlist updates, and cross-file test verification. Prevents CI failures, broken imports, and test regressions from code extraction.

ZaxbyHub/opencode-swarm · 60 tokens