init-agent
Skill18 starsChanged 58 days agoMITView on GitHub
Configure or rotate provider credentials used by AI Workflow harness profiles. Emits a paste-template for the providers those profiles use. Use for "set up claude", "set up codex", "rotate anthropic key", or "configure agent credentials".
- Reads credentials
2 other projects use a version of this.
Adopted by
Most recently taken up by
- vlad-ryzhkov/ai-context-engineering-for-frontendtheir own version, first seen Nov 15, 2026
- strobelpierre/init-agenttheir own version, first seen Nov 8, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- vlad-ryzhkov/ai-context-engineering-for-frontend★ 2same name
- strobelpierre/init-agent★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository13 other files it gives its agents.
- AGENTS.mdAGENTS.md
- packages/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- packages/CLAUDE.mdCLAUDE.md
- artur-releaseSkill
- gate-ladderSkill
- init-envSkill
- init-jiraSkill
- init-neonSkill
- init-slackSkill
- init-vcsSkill
- new-integrationSkill
- ai-workflow-reviewSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 27
Ask: *"Do your harness profiles use Claude, Codex, or both?"*
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Initialize Agent Credentials
Harness Profiles own the provider and model. This skill asks which providers the deployment's harness profiles use, then emits credentials only. The credentials required are those of the providers your harness profiles use: an Anthropic key for Claude profiles, and a Codex API key or OAuth token for Codex profiles.
Canonical reference: SETUP.md section 2.4 holds the facts and constraints for the agent runtime. This skill is the procedure; when the two disagree, SETUP.md wins and this skill gets updated.
If you want full project setup (Jira + VCS + Agent + Slack + Neon + deploy), invoke
init-envinstead. This skill only handles the agent runtime.
Precondition
apps/worker/.vercel/project.json must exist: the worker is linked from apps/worker (SETUP.md section 3), and this skill's commands run there. If missing:
ERROR: no Vercel project linked. Run `vercel link` first, or invoke `init-env`
for the full first-time setup.Halt.
Step 1: Identify profile providers
Ask: "Do your harness profiles use Claude, Codex, or both?"
Provider and model changes belong on the Harness Profiles page. If no profile uses a previously configured provider, the user should remove that provider's credentials from Vercel. Print a one-line warning.
Step 2: Emit paste-template
Claude branch
Walk the user through https://console.anthropic.com/settings/keys to create an API key. Codex OAuth is documented in references/oauth-alternative.md.
Collect:
ANTHROPIC_API_KEY(starts withsk-ant-; a Claude Code OAuth tokensk-ant-oat...also works)
Emit:
ANTHROPIC_API_KEY=<value>Codex branch (default API key, OAuth alternative)
Walk the user through https://platform.openai.com/api-keys to create an API key. OAuth via CODEX_CHATGPT_OAUTH_TOKEN is documented in references/oauth-alternative.md.
Collect:
CODEX_API_KEY
Emit:
CODEX_API_KEY=<value>For deployments whose profiles use both providers, emit both credential lines. The user can choose the OAuth alternative instead of the Codex API key.
Step 3: Done
Tell the user to paste into Vercel Project Settings, Environment Variables for all three environments, save, and reply when done. Credentials are not checked at boot: a missing one surfaces when an agent block using that provider runs, or when the scheduled capability refresh (/cron/harness-capabilities) reports discovery not ready. With no authored profile the built-in builtin-codex profile runs, so a Claude-only deployment needs a Claude profile pinned on its agent blocks.
Don'ts
- Don't emit both API key and OAuth token. Pick one. The runbook explains the swap if the user wants OAuth.
- Don't print the key after collecting it. Reference by name only.
- Don't emit provider or model settings. Harness Profiles own both.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.