frames-keys

A command-line tool for storing and managing provider API keys in the macOS Keychain, which is Apple's protected password store.

In plain words
What is it for?
It helps add, update, list, test or remove API keys used by image and video creation providers.
Why use it?
It keeps secret key values out of normal output and lets you check whether a stored key works without displaying it.

Command for Claude Code

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 commands/pushingsquares/pushing-creation/frames-keys
Clone the repo
git clone --depth 1 https://github.com/PUSHINGSQUARES/pushing-creation

Made for: Claude Code.

Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 315 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 $0.00013 $0.00315
Opus 5 $0.00006 $0.00158
Sonnet 5 $0.00003 $0.00063
Haiku 4.5 $0.00001 $0.00032

Measured 2d ago against content hash 1f7b3c62e32f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

frames-keys 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 2d 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.

.claude/commands/frames-keys.md · 49 lines

What it actually says

Manage provider API keys stored in macOS Keychain by running bin/frames-keys.

Subcommands

Run bin/frames-keys with one of these subcommands based on what the user asks:

frames-keys add Add or update a key. Runs an interactive prompt (hidden input). Use this when the user wants to add a new provider or update an existing key.

bin/frames-keys add gemini

frames-keys list List all pushing-creation Keychain entries by service name. No values are shown.

bin/frames-keys list

frames-keys test Make a live ping to verify the key works. Prints [ok] or [fail] with a scrubbed reason.

bin/frames-keys test gemini

frames-keys remove Delete a key from Keychain.

bin/frames-keys remove gemini

When the user just types /frames-keys

Show them this menu and ask what they want to do:

  • add -- store a new provider key
  • list -- see what keys are stored
  • test -- verify a key works
  • remove -- delete a key

Do NOT print or echo any key values. The CLI handles all scrubbing.

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. 2d ago First seen · 49 lines · 13 tokens per session scan A 1f7b3c62e32f

Subscribe to this mod's changes

frames-keys is a command published in the GitHub repository PUSHINGSQUARES/pushing-creation (9 stars, last pushed 3mo ago), licensed MIT. It adds 13 tokens to every session and 315 once invoked, about $0.0001 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 2026-08-31.