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 Cloudgeni-ai/opengeni --skill secretsgit clone --depth 1 https://github.com/Cloudgeni-ai/opengeniWrote 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/cloudgeni-ai/opengeni/secrets)<a href="https://agentmods.dev/skills/cloudgeni-ai/opengeni/secrets"><img src="https://agentmods.dev/badge/skills/cloudgeni-ai/opengeni/secrets/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/cloudgeni-ai/opengeni/secrets"><img src="https://agentmods.dev/badge/skills/cloudgeni-ai/opengeni/secrets.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 | $0.00033 | $0.00976 |
| Opus 5.5 | $0.00013 | $0.00390 |
| Sonnet 5.5 | $0.00007 | $0.00195 |
| Haiku 4.5 | $0.00003 | $0.00098 |
Grade A, and why
secrets 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.
How it starts
The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Secrets: sign in and use credentials yourself
Use references instead of viewing values. Sign in, create accounts when the task allows it, enroll 2FA, fetch codes and solve CAPTCHAs yourself.
References
| Write | Resolves to |
|---|---|
{{secret:Item}} |
the primary field (password of a login, value of an API key) |
{{secret:Item/field}} |
one field, such as {{secret:GitHub/username}} |
{{secret:Vault/Item/field}} |
a field in a named vault |
{{secret:Item/otp}} |
the current TOTP code, computed when the action runs |
{{secret:Item/field#previous}} |
the version before the current one |
{{secretfile:Item}} |
a temporary file path holding the value (shell commands) |
\{{secret:Item}} |
the literal text, left unresolved |
A reference resolves wherever it is used: shell commands, typing, file writes
and every tool call, including built-in tools. To hand one on for later
work (a schedule prompt, a message to another session, a goal, a note or
comment), escape it as \{{secret:Item}}; it arrives as {{secret:Item}}.
The secret_* tools take references as names and never resolve them.
Tools
secret_search: metadata and references, never values. No filters lists all; page one lists vaults. FollownextCursorwith unchanged filters. Checkcompleteand freshness before inferring absence.refresh: truerequests fresh inventory without bypassing rate limits.secret_save: each field takesvalue,generate,fromReferenceorrestoreVersion. Generate new passwords.secret_move: move or copy to another vault.secret_delete: archive an item.secret_get: plaintext withsecrets:read, only if references cannot work.
Login ladder
Go down the list and stop at the first rung that gets you in. None of these needs the user's permission.
- Reuse a saved browser session (browser identity or
browser_auth). - Sign in with a saved login:
{{secret:Item/username}},{{secret:Item}}, then{{secret:Item/otp}}at the code prompt. - After signing in, enroll your own TOTP so the next login needs no one.
- Get email or SMS codes and magic links through connected mail or messaging tools.
- No account and the task allows creating one: create it, saving a generated
password with
secret_savebefore you submit the form. - Only the user has it: ask with a secret card.
- Hand the browser to the user only for a push approval or a hardware key.
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday First seen · 88 lines · 33 tokens per session scan A 034a8209b185
secrets is a skill published in the GitHub repository Cloudgeni-ai/opengeni (205 stars, last pushed today), licensed Apache-2.0. It adds 33 tokens to every session and 976 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 2026-10-21.
Other skills, from other repositories
playwright
Use when the task requires capturing or automating a real browser from the terminal.
effect-v4
Write, review, or upgrade Effect v4 code in the Composio CLI, cli-keyring, and json-schema-to-effect-schema packages, all pinned exactly to [email protected] — Context.Service and explicit layers, Schema.TaggedError and typed recovery, the effect/cli command surface, and the vendored effect source oracle. Use when writing…
stripe-projects
Use after E2B sandbox/API access has been provisioned through Stripe Projects and the user needs to use the resulting E2B API key with the E2B CLI, JavaScript SDK, Python SDK, or Code Interpreter SDK.
ax-cpp-gen
Use when writing C++ code with axllm for AxGen programs, forward calls, indexed multi-sampling, result pickers, streaming, tools, assertions, traces, usage, and output parsing.
ax-java-gen
Use when writing Java code with dev.axllm:ax for AxGen programs, forward calls, indexed multi-sampling, result pickers, streaming, tools, assertions, traces, usage, and output parsing.
ax-go-flow
Use when writing Go code with github.com/ax-llm/ax/packages/go for flows, nodes, program graphs, nested programs, dynamic options, caching, and optimizer components.