Skip to content
OpenSmartRoute
Skillv1.0.0

examples

Project Agent Memory

by Hmbown(0) 0 installs
Free
Sign in to install

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

See reviews

About

Imported from Hmbown/rlmagents (libs/rlmagents/examples/AGENTS.md). Install upstream with npx skills add Hmbown/rlmagents --skill examples. Copyright stays with the author.

Project Agent Memory

RLM Workflow

  • Use isolated RLM contexts for all medium and large inputs.
  • For large files, call load_file_context before analysis.
  • Use search_context, peek_context, and chunk_context to inspect targeted regions.
  • Use rg_search(..., load_context_id=...) for repo-wide scans before deep analysis.
  • Use exec_python for deterministic extraction and calculations.
  • Use get_evidence and finalize for evidence-backed outputs.

Context Window Guardrails

  • Do not paste long file contents into chat responses.
  • Keep tool-output previews short.
  • Summarize long reasoning trails with summarize_so_far(clear_history=True).

Style

  • Be direct and concise.
  • Report blockers with exact commands, paths, and error messages.

Use it

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

yaml
targets:
  - https://api.opensmartroute.ai/api/v1/registry/hmbown-rlmagents-examples/manifest   # or paste the manifest below

Manifest

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

hmbown-rlmagents-examples.ocm.jsonjson
{
  "ocm": "1",
  "id": "hmbown-rlmagents-examples",
  "kind": "skill",
  "name": "examples",
  "description": "Project Agent Memory",
  "publisher": "Hmbown",
  "version": "1.0.0",
  "capabilities": {
    "domains": [
      "general"
    ],
    "tags": [
      "skill-md",
      "github-agents"
    ],
    "languages": [
      "en"
    ]
  },
  "quality_prior": 0.6,
  "examples": [
    "Project Agent Memory"
  ],
  "primary": false,
  "metadata": {
    "source": {
      "provider": "github-agents",
      "repository": "https://github.com/Hmbown/rlmagents",
      "path": "libs/rlmagents/examples/AGENTS.md",
      "ref": "d98f0f710d343654c4828b2acfa48d909736266f",
      "url": "https://github.com/Hmbown/rlmagents/blob/d98f0f710d343654c4828b2acfa48d909736266f/libs/rlmagents/examples/AGENTS.md",
      "key": "Hmbown/rlmagents/libs/rlmagents/examples/AGENTS.md"
    }
  },
  "instructions": "# Project Agent Memory\n\n## RLM Workflow\n\n- Use isolated RLM contexts for all medium and large inputs.\n- For large files, call `load_file_context` before analysis.\n- Use `search_context`, `peek_context`, and `chunk_context` to inspect targeted regions.\n- Use `rg_search(..., load_context_id=...)` for repo-wide scans before deep analysis.\n- Use `exec_python` for deterministic extraction and calculations.\n- Use `get_evidence` and `finalize` for evidence-backed outputs.\n\n## Context Window Guardrails\n\n- Do not paste long file contents into chat responses.\n- Keep tool-output previews short.\n- Summari",
  "cost": {
    "context_tokens": 192
  }
}

Fetch it by URL: GET /api/v1/registry/hmbown-rlmagents-examples/manifest?version=1.0.0

Reviews

Star ratings from people who tried it. One review per account; edit yours any time.

No reviews yet. Install it, try it, and be the first to rate it.