guidance

Guidance for running AI-agent command-line tools in containers with shared API keys and persistent login storage.

In plain words
What is it for?
Configuring OpenAI, Anthropic, Gemini, and related CLI access, preserving login state, and understanding the container’s security boundary.
Why use it?
It explains how authentication survives container rebuilds and warns that every process inside the container can access the injected keys.

Agent

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 agents/morimorijap/sunaba-cli/guidance
Clone the repo
git clone --depth 1 https://github.com/morimorijap/sunaba-cli
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 310 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 $0.00000 $0.00310
Opus 5 $0.00000 $0.00155
Sonnet 5 $0.00000 $0.00062
Haiku 4.5 $0.00000 $0.00031

Measured yesterday against content hash de8998f2b543, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

guidance 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 yesterday.

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/sunaba_cli/templates/agents/fragments/agents/guidance.md · 30 lines

What it actually says

Agents stack

The agents stack injects host API keys into the container and persists CLI auth state in named volumes.

What you get

  • OPENAI_API_KEY, ANTHROPIC_API_KEY, GEMINI_API_KEY pulled from the host's environment (must be set on the host before container start).
  • ~/.claude/, ~/.codex/, ~/.gemini/ are named-volume mounts so OAuth and session state survive a container rebuild. The Antigravity CLI (agy, formerly Gemini CLI) nests its state under ~/.gemini/antigravity-cli/, so the same volume covers it.

Honest limits

  • Once the keys are injected, any process in the container — every AI agent included — can read them via environment variables. There is no isolation between an agent's tool runtime and your OPENAI_API_KEY.
  • The container is the trust boundary against the host. It is not a trust boundary against the agents you run inside it.

Conventions

  • Never paste real API keys into source files. The host env vars + the persistent CLI auth volumes are sufficient.
  • If you need a "key behind a proxy" pattern (so the agent never sees the upstream key directly), see the upcoming --stack secrets and the Azure Foundry → APIM → Gemini → Cosmos pattern.
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. yesterday First seen · 30 lines · 0 tokens per session scan A de8998f2b543

Subscribe to this mod's changes

guidance is an agent published in the GitHub repository morimorijap/sunaba-cli (3 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 310 tokens. 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 2026-08-31.

Related

Other agents, from other repositories

hlasm-assembler-specialist

IBM High-Level Assembler (HLASM) specialist for z/OS. Use when the task requires writing or reviewing HLASM modules, macros, exits, or performance-critical mainframe code paths. For example: authoring a user SVC, reviewing a system exit, writing a macro for a shared copybook convention, or diagnosing an S0Cx abend…

josstei/maestro-orchestrate · 306 tokens

cloud_architect

Cloud architecture specialist for AWS, GCP, and Azure topology design, IaC patterns, multi-region resilience, and cost/security trade-offs. Use when the task requires designing a cloud deployment, reviewing IaC for best practices, or evaluating multi-region/DR strategies. For example: choosing between ECS and EKS…

josstei/maestro-orchestrate · 83 tokens

wtfp-research-synthesizer

Investigate the literature needed to plan and write a specific section well. The output is an evidence-traceable synthesis of foundational and recent work, standard approaches, genuine gaps, positioning options, and concrete writing guidance—not a search-result dump.

akougkas/wtf-p · 57 tokens

continuity-checker

Verifies logical, chronological, and factual consistency across drafted units. Flags contradictions, timeline issues, and character state drift.

hannsxpeter/scriveno · 29 tokens

AGENTS

Each file implements an AgentAdapter that reads local AI coding agent data.

eat-pray-ai/wingman · 0 tokens

observer

Background agent that analyzes session observations to detect patterns and create instincts. Uses Haiku for cost-efficiency. v2.1 adds project-scoped instincts.

x-cmd/skill · 33 tokens