SkillAgentSearch skills...

actera-connect

Connect this Codex installation to an Actera agent through administrator browser approval, or with a setup code from Actera.

Install / Use

npx skills add hashgraph-online/awesome-codex-plugins --skill actera-connect

Installs into whichever agent you are using.

About this skill
📄

SKILL.md

Installable skill definition

Quality Score

85/100

Supported Platforms

OpenAI Codex

Our assessment of actera-connect

actera-connect scores 85/100 on our quality scale, 2722nd of 4,716 Development & Engineering skills we index.

Its SKILL.md is 2.6 KB long, written without headings and no code examples: a solid amount of guidance for an agent.

With 1,075 GitHub stars, it is one of the more widely adopted skills in the catalogue.

Substance
26/30
Structure
0/20
Description
15/15
Adoption
13/20
Freshness
15/15

Maintenance, license and trust

  • The repository was last updated about 2 months ago, so actera-connect is actively maintained.
  • It is released under the Apache-2.0 license, a permissive license that allows use, modification and commercial use with attribution.
  • Its trust signals score 100/100, with no cautions. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

actera-connect compared with similar skills

All 4 of these similar skills score higher than actera-connect; compare them before choosing.

SkillScoreStarsUpdatedFormat
actera-connect (this skill)by hashgraph-online851.1k56d agoSKILL.md
taste-skillby Leonxlnx100118.9k11d agoCLAUDE.md
Agent-Reachby Panniantong100113.3k12d agoCLAUDE.md
hyperframesby heygen-com10087.1ktodayCLAUDE.md
ai-job-searchby ai-job-search-dev10072.6ktodayCLAUDE.md

Frequently asked questions

How do I install actera-connect?
Run npx skills add hashgraph-online/awesome-codex-plugins --skill actera-connect. The install tabs above show the steps for each supported agent.
Which AI agents does actera-connect work with?
It is written for OpenAI Codex, as a SKILL.md file. Other agents that read the same format can often use it too.
Is actera-connect safe to use?
It is Apache-2.0-licensed and scores 100/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is actera-connect still maintained?
The repository was last updated about 2 months ago, so actera-connect is actively maintained.

name: actera-connect description: Connect this Codex installation to an Actera agent through administrator browser approval, or with a setup code from Actera.

Connect Actera without asking for or displaying a machine key.

The Actera plugin's command line is bin/actera-hook.mjs in the plugin folder, two levels above the folder that holds this SKILL.md. Run it with Node.js using its absolute path, from a terminal command with a ten-minute timeout. Keep it attached until it prints its result.

  • If the person gave a setup code from Actera (16 letters and digits, usually in four groups such as 7AHV-F8T0-M349-HPF7), run node "<plugin folder>/bin/actera-hook.mjs" connect --setup-code <code>. It connects to the agent an administrator made the code for, with no browser page. A code works once and expires after 30 minutes; if it fails, tell the person to get a new code from Actera.
  • Otherwise run node "<plugin folder>/bin/actera-hook.mjs" connect. It opens an Actera page in the browser and waits for an administrator to approve the connection. Tell the person to check that the code on that page matches the one the command prints. The page suggests a new agent named Codex; an administrator can rename it or choose an existing agent.
  • Add --reconnect only when the person asks to reconnect.

The plugin includes its Actera API endpoint. Do not ask for an API URL, agent ID, key, policies or fallback behavior. Never request, print or pass a machine key.

Before connecting, tell the person what the plugin sends: each tool call's name and inputs, after it redacts sensitive fields and scans for secrets with the bundled Gitleaks. Detection is best effort; ordinary commands and file paths stay visible. Prompts and tool output are not sent.

After it connects, report the mode and the evaluation-failure choice the command printed. Monitoring (the default) records every tool call and never blocks. Enforcing blocks what policies deny and holds calls that need approval until a reviewer decides in Actera, Slack or email, or in Codex: the first held call offers to link Codex to the person's Actera account, after which Codex asks them to allow or deny each held call. $actera-mode changes either setting.

Then tell the person the one step Codex needs from them: open /hooks in Codex, trust the two Actera hooks, and start a new session. Codex does not run a plugin's hooks until they are trusted, and asks again after every plugin update. Until then no tool call is checked. $actera-status shows whether the hooks have run. Do not describe connecting alone as proof that tool calls reach Actera.

Related Skills

View on GitHub
GitHub Stars1.1k
CategoryDevelopment
Updated1mo ago
Forks294

Languages

Python

Trust signals

100/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

No cautions