sefi-agents

Name: sefi-agents
Author: xsefirosus

Collaboration Instructions

by xsefirosus(0) 0 installs

Free

Free account. Installing gives you the manifest plus copy-paste snippets.

See reviews

About

Imported from xsefirosus/sefi-agents (AGENTS.md). Install upstream with npx skills add xsefirosus/sefi-agents. Copyright stays with the author.

Collaboration Instructions

Treat a user's request as authorization for the directly related work needed to finish it well. This includes consistency fixes, documentation updates, tests, validation, and release bookkeeping that accurately reflect the requested change.
Make reasonable, low-risk decisions within that scope. Report what changed and any material tradeoff clearly when handing the work back.
Ask before changing the product's intended behavior beyond the request, redesigning an architecture, adding a dependency or service, changing permissions or credentials, or taking an irreversible external action not already requested.
If you find an unrelated risk, defect, or improvement, briefly explain it and recommend a next step. Do not let it block the requested work unless it makes that work unsafe.

Use it

Copy one of these into your project. Installing also returns the manifest and these snippets.

# after Install: the listing is in your workspace's routing pool - a plan picks it for its slot
curl -s -X POST https://api.opensmartroute.ai/api/v1/route -H 'Authorization: Bearer $OSR_API_KEY' -H 'Content-Type: application/json' -d '{"text": "...", "plan": true}'

Installed into a catalogue, chosen by a router

Install sefi-agents and it becomes one more candidate the router can pick - when it fits.

A listing is a routing target with a manifest: what it does, which domains it covers, what it costs and who publishes it. Once installed it sits beside your own models and tools, is scored like any other candidate for each request, and shows up in the trace when it wins. Ratings come from workspaces that installed it, one per account.

Photo: RDNE Stock project

Manifest

An Open Capability Manifest: the router reads it to know what this does, what it costs and when to pick it.

xsefirosus-sefi-agents-sefi-agents.ocm.jsonjson

{
  "ocm": "1",
  "id": "xsefirosus-sefi-agents-sefi-agents",
  "kind": "skill",
  "name": "sefi-agents",
  "description": "Collaboration Instructions",
  "publisher": "xsefirosus",
  "version": "1.0.0",
  "capabilities": {
    "domains": [
      "general"
    ],
    "tags": [
      "skill-md",
      "github-agents"
    ],
    "languages": [
      "en"
    ]
  },
  "quality_prior": 0.6,
  "examples": [
    "Collaboration Instructions"
  ],
  "primary": false,
  "metadata": {
    "source": {
      "provider": "github-agents",
      "repository": "https://github.com/xsefirosus/sefi-agents",
      "path": "AGENTS.md",
      "ref": "328c7c2852a5c7b42c6e650ea040f7b5546cce6a",
      "url": "https://github.com/xsefirosus/sefi-agents/blob/328c7c2852a5c7b42c6e650ea040f7b5546cce6a/AGENTS.md",
      "key": "xsefirosus/sefi-agents/AGENTS.md"
    }
  },
  "instructions": "# Collaboration Instructions\n\n- Treat a user's request as authorization for the directly related work needed to finish it\n  well. This includes consistency fixes, documentation updates, tests, validation, and\n  release bookkeeping that accurately reflect the requested change.\n- Make reasonable, low-risk decisions within that scope. Report what changed and any\n  material tradeoff clearly when handing the work back.\n- Ask before changing the product's intended behavior beyond the request, redesigning an\n  architecture, adding a dependency or service, changing permissions or credentials, or\n  tak",
  "cost": {
    "context_tokens": 209
  }
}

Fetch it by URL: GET /api/v1/registry/xsefirosus-sefi-agents-sefi-agents/manifest?version=1.0.0

About

Collaboration Instructions

Use it

Install sefi-agents and it becomes one more candidate the router can pick - when it fits.

Manifest

Reviews