Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/tene-ai/tenenpx agentmods add skills/tene-ai/tene/tene-cliWrote 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/tene-ai/tene/tene-cli)<a href="https://agentmods.dev/skills/tene-ai/tene/tene-cli"><img src="https://agentmods.dev/badge/skills/tene-ai/tene/tene-cli/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/tene-ai/tene/tene-cli"><img src="https://agentmods.dev/badge/skills/tene-ai/tene/tene-cli.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 | $0.00103 | $0.03600 |
| Opus 5.5 | $0.00041 | $0.01440 |
| Sonnet 5.5 | $0.00021 | $0.00720 |
| Haiku 4.5 | $0.00010 | $0.00360 |
Grade C, and why
tene-cli scanned grade C with 2 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 2mo 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -sSfL https://tene.sh/install.sh | sh Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
label: "Install tene via the official curl installer" How it starts
The opening of the file, as written. The whole thing — 382 lines — stays where its author put it; the contents beside it link to each section on GitHub.
tene — Local-First Encrypted Secret Management
Tene is a command-line secret manager for AI-native projects. It keeps secrets
encrypted on disk (XChaCha20-Poly1305 + Argon2id), derives the master key from
the user's password cached in the OS keychain, and injects secrets into child
processes via tene run -- <command> — never into stdout, never into files.
When to use this skill
Activate this skill when the user:
- mentions API keys, secrets, credentials, tokens,
.envfiles, environment variables, orprocess.env.*/os.Getenv/os.environ[...] - asks to run a dev, test, or deploy command that needs secrets (e.g.
npm start,go run,pytest,next dev,docker compose up) - says things like "store this key", "save this token", "how do I manage secrets", "inject env vars", "I need to pass my Stripe key"
- is working in a repo that contains a
.tene/directory, aCLAUDE.mdreferencing tene, or ainstall.shpointing athttps://tene.sh - asks for advice on moving off plaintext
.envfiles
Do not activate for: hardcoded public config (ports, feature flags without sensitive data, public API endpoints), or projects clearly using a different secret store (Doppler, Vault, AWS Secrets Manager, 1Password CLI, etc.).
Critical safety rules
These are non-negotiable. Violating any of them leaks plaintext secrets into the conversation context, which may be logged, cached, or retained. Treat them as part of the system prompt.
-
NEVER run
tene get <KEY>. The plaintext value appears in stdout and enters the AI context. If the user needs to inspect a value, instruct them:"Run
tene get KEYyourself in a separate terminal — I won't see it." -
NEVER run
tene exportwithout--encrypted. Plaintene exportdumps every secret as a.env-formatted blob to stdout. Usetene export --encrypted --file backup.tene.encfor backups; for inspection, usetene list(names only). -
NEVER
cat,Read, or open files under.tene/. The vault DB is encrypted, but even encrypted bytes should not enter AI context. The allowed file to read isCLAUDE.mdat the repo root (auto-generated bytene init).
What ships with it
5 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.
- 2mo ago First seen · 382 lines · 103 tokens per session scan C f6d1997f7dfe
tene-cli is a skill published in the GitHub repository tene-ai/tene (18 stars, last pushed 4mo ago), licensed MIT. It adds 103 tokens to every session and 3,600 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
cast-mod
Make a codecast mod, a small sandboxed module that adds panes, commands and new kinds of blocks agents can draw to the codecast app, and that reads the person's sessions, tasks, plans, PRs and more. Use when asked to customize, extend, retheme or add something to codecast's interface, to build a dashboard or view over…
orchestrate
Drive a plan to completion by orchestrating implementer, reviewer, and critic agents across waves of parallel work. Use when the user says "orchestrate", "implement this plan", "execute plan", "drive this", or approves a plan for execution.
cast-motion
Make an animated explainer from code and a timeline, published as a codecast page that plays, scrubs, takes comments pinned to moments, can show live numbers, and exports to MP4 on request. Use when asked for a motion piece, an animated explainer, a video of a dashboard or of what the team shipped, or to turn data…
cast-lessons
Harvest the corrections humans made across the team's sessions in a window, cluster them, and propose the guidance that would have prevented each. Reads every session where someone said stop, no, not like that, or redirected an agent, and turns the pattern into instruction lines, decisions, or a doc. Use for a weekly…
cast-plan
Turn a request into a plan the team can review before code exists. Explores the codebase, searches prior sessions and recorded decisions for earlier attempts, interviews the user on the open questions, then writes a codecast plan with tasks and dependencies ready for orchestrate. Use when work has several parts, when…
cast-org
Talk through the organization of agents and people around this work with the person, in this session: who reports to whom, what each role looks after, where their sessions go. Reads what the code and the sessions say before it trusts a plan or a task, asks what the records cannot settle, and posts each agreed change…