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 23blocks-OS/ai-maestro-plugins --skill aim-secret-managementgit clone --depth 1 https://github.com/23blocks-OS/ai-maestro-pluginsWrote 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/23blocks-os/ai-maestro-plugins/aim-secret-management)<a href="https://agentmods.dev/skills/23blocks-os/ai-maestro-plugins/aim-secret-management"><img src="https://agentmods.dev/badge/skills/23blocks-os/ai-maestro-plugins/aim-secret-management/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/23blocks-os/ai-maestro-plugins/aim-secret-management"><img src="https://agentmods.dev/badge/skills/23blocks-os/ai-maestro-plugins/aim-secret-management.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00082 | $0.00687 |
| Opus 5.5 | $0.00033 | $0.00275 |
| Sonnet 5.5 | $0.00016 | $0.00137 |
| Haiku 4.5 | $0.00008 | $0.00069 |
Grade A, and why
aim-secret-management 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Credentials without seeing them
Secrets live in a local vault, by name. You use them by name and never receive the value, so it stays out of the model, the transcript and your memory.
Ask for one
aim-secret has OPENAI_API_KEY || aim-secret request OPENAI_API_KEY --note "for the embedding job"
request returns at once. The user gets a card in the AI Maestro chat with the name filled in and a masked field (in Claude Code with the secrets mod, the request_secret tool opens a form in the terminal instead). End your turn after calling it: you get a message when the value is stored or declined. If it is declined, carry on without it and do not ask again unless you cannot go on.
Use it
aim-secret exec --use OPENAI_API_KEY -- python embed.py
aim-secret exec --use AWS_ACCESS_KEY_ID --use AWS_SECRET_ACCESS_KEY -- aws s3 ls
aim-secret exec --use MY_KEY_NAME=OPENAI_API_KEY -- node job.js
The value is placed in that one command's environment. Anything the command prints has it replaced by [secret:NAME], which is correct. The last form maps the secret OPENAI_API_KEY to the environment variable MY_KEY_NAME.
Names
Capital letters, digits and underscores, starting with a letter, using the provider's usual variable name (OPENAI_API_KEY, GITHUB_TOKEN). aim-secret list prints names only. Reuse an existing name rather than adding a second one for the same credential.
If a value shows up in the conversation
The user pasted a key or password, or a command printed one. Do not repeat it, copy it into a file or command, or act on it from the chat. Tell the user it is now in the transcript, so it is worth rotating, and run aim-secret request so they can store it properly.
What you do not do
- Read the vault, Keychain entries or
~/.aimaestro/vault, or print the environment of the command you ran throughexec. - Write a secret into a file, a commit, a log or a message. Put
--use NAMEon the command that needs it. - Run
aim-secret set. It is for the person, at a terminal.
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.
- 9d ago First seen · 51 lines · 82 tokens per session scan A 84b39125123b
aim-secret-management is a skill published in the GitHub repository 23blocks-OS/ai-maestro-plugins (11 stars, last pushed today), licensed MIT. It adds 82 tokens to every session and 687 once invoked, about $0.0003 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 2026-10-11.
Other skills, from other repositories
memory-search
Runs read-only SQL over the local EvoFlux session database (evoflux.db) for structured analysis that ordinary recall cannot answer, such as aggregating tool failures across sessions, filtering turns by role, agent, or time range, reconstructing a complete execution chain, or checking a remembered claim against what a…
Read, create and manipulate PDF files — extract text and tables, merge, split, rotate, reorder and delete pages, read and fill AcroForm fields, add or strip metadata, encrypt and decrypt, and generate new PDFs from HTML or from scratch. Also covers rasterising pages to images so a PDF can actually be looked at, and…
intelligent-ui
Helps agents choose prose, native controls, dashboards, motion, or 3D from the user's goal. Use when a user asks to explain, teach, compare, or present information visually, asks you to choose a format, requests a video or code-authored animation as the deliverable, or an interactive artifact may improve understanding…
diagram-design
Creates polished, accessible SVG diagrams as EvoFlux Work widgets or project files. Use when a user asks to design, draw, redraw, or polish a software architecture, data flow, API sequence, state machine, ER model, deployment, service journey, or process diagram, or asks to turn Mermaid, draw.io, or Excalidraw content…
agents
Guidance for AI coding agents working on the adeptability (adept) codebase. Humans: see README.md for usage and CONTRIBUTING.md for the contributor workflow.
authoring-adept-agents
Write a good, portable adept agent (subagent): trigger-shaped description, one job per agent, generator/evaluator separation, explicit boundaries, restricted tools. Apply when creating or editing an agent file or running adept agent add.