oracle is agent-read markdown (skill) from trpc-group/trpc-agent-go: Best practices for using the oracle CLI (prompt + file bundling, engines, sessions, and file attachment patterns)..
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
# oracle — best use
Oracle bundles your prompt + selected files into one “one-shot” request so another model can answer with real repo context (API or browser automation). Treat output as advisory: verify against code + tests.
## Main use case (browser, GPT‑5.2 Pro)
Default workflow here: `--engine browser` with GPT‑5.2 Pro in ChatGPT. This is the common “long think” path: ~10 minutes to ~1 hour is normal; expect a stored session you can reattach to.
Recommended defaults:
- Engine: browser (`--engine browser`)
- Model: GPT‑5.2 Pro (`--model gpt-5.2-pro` or `--model "5.2 Pro"`)
## Golden path
1. Pick a tight file set (fewest files that still contain the truth).
2. Preview payload + token spend (`--dry-run` + `--files-report`).
3. Use browser mode for the usual GPT‑5.2 Pro workflow; use API only when you explicitly want it.
4. If the run detaches/timeouts: reattach to the stored session (don’t re-run).
## Commands (preferred)
- Help:
- `oracle --help`
- If the binary isn’t installed: `npx -y @steipete/oracle --help` (avoid `pnpx` here; sqlite bindings).
- Preview (no tokens):
- `oracle --dry-run summary -p "<task>" --file "src/**" --file "!**/*.test.*"`
…
Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
GET https://markdownregistry.com/api/v1/artifacts/art_yg6sbhtw5zkt3xsh
GET https://markdownregistry.com/api/v1/resolve?ref=trpc-group/trpc-agent-go/oracle
GET https://markdownregistry.com/api/v1/blob/903a053178a3d2e7786f2036c8e151c40052184b6355614bc0aefdcc965d245e
Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
trpc-group/trpc-agent-go · examples/agui/server/skill_artifacts/skills/artifact_demo/SKILL.md · Demo skill that writes an output file and persists it as an artifact.
trpc-group/trpc-agent-go · examples/dynamicworkflow/skills/skills/fanout-analysis/SKILL.md · Use this workflow recipe when a question benefits from several independent perspectives followed by a single…
trpc-group/trpc-agent-go · examples/dynamicworkflow/skills/skills/quality-loop/SKILL.md · Use this workflow recipe when a draft, plan, proposal, or other deliverable should be independently reviewed and…
trpc-group/trpc-agent-go · examples/mcpbroker/basic/skills/remote-http-mcp/SKILL.md · Connect to a remote streamable HTTP MCP service that exposes announcements and FAQ tools.
trpc-group/trpc-agent-go · examples/skilldynamicschema/skills/plan_route/SKILL.md · Plan a route and return distance + ETA (schema + deterministic result).
bitterbot-ai/bitterbot-desktop · skills/oracle/SKILL.md · Best practices for using the oracle CLI (prompt + file bundling, engines, sessions, and file attachment patterns).
qwerfunch/cladding · plugins/antigravity/skills/oracle/SKILL.md · Author an IMPL-BLIND spec-conformance oracle for an acceptance criterion the policy worklist (`clad oracle --required`)…
qwerfunch/cladding · skills/oracle/SKILL.md · Author an IMPL-BLIND spec-conformance oracle for an acceptance criterion the policy worklist (`clad oracle --required`)…
qwerfunch/cladding · plugins/codex/skills/oracle/SKILL.md · Author an IMPL-BLIND spec-conformance oracle for an acceptance criterion the policy worklist (`clad oracle --required`)…
