oracle
Use the @steipete/oracle CLI to bundle a prompt plus the right files and get a second-model review (API or browser) for debugging, refactors, design checks, or cross-validation.
Best use case
oracle is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Use the @steipete/oracle CLI to bundle a prompt plus the right files and get a second-model review (API or browser) for debugging, refactors, design checks, or cross-validation.
Teams using oracle should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/oracle/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How oracle Compares
| Feature / Agent | oracle | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Use the @steipete/oracle CLI to bundle a prompt plus the right files and get a second-model review (API or browser) for debugging, refactors, design checks, or cross-validation.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
SKILL.md Source
# Oracle (CLI) — 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 outputs as advisory: verify against the codebase + tests.
## Main use case (browser, GPT‑5.2 Pro)
Default workflow here: `--engine browser` with GPT‑5.2 Pro in ChatGPT. This is the “human in the loop” path: it can take ~10 minutes to ~1 hour; expect a stored session you can reattach to.
Recommended defaults:
- Engine: browser (`--engine browser`)
- Model: GPT‑5.2 Pro (either `--model gpt-5.2-pro` or a ChatGPT picker label like `--model "5.2 Pro"`)
- Attachments: directories/globs + excludes; avoid secrets.
## Golden path (fast + reliable)
1. Pick a tight file set (fewest files that still contain the truth).
2. Preview what you’re about to send (`--dry-run` + `--files-report` when needed).
3. Run in browser mode for the usual GPT‑5.2 Pro ChatGPT 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)
- Show help (once/session):
- `npx -y @steipete/oracle --help`
- Preview (no tokens):
- `npx -y @steipete/oracle --dry-run summary -p "<task>" --file "src/**" --file "!**/*.test.*"`
- `npx -y @steipete/oracle --dry-run full -p "<task>" --file "src/**"`
- Token/cost sanity:
- `npx -y @steipete/oracle --dry-run summary --files-report -p "<task>" --file "src/**"`
- Browser run (main path; long-running is normal):
- `npx -y @steipete/oracle --engine browser --model gpt-5.2-pro -p "<task>" --file "src/**"`
- Manual paste fallback (assemble bundle):
- Store bundles in git-tracked `tmp/` locations so they can be reused by automations later:
- If the work is tied to a dossier under `docs/04-projects/.../<dossier>/`: write to `<dossier>/tmp-oracle/`.
- Otherwise: write to `docs/98-tmp/oracle/`.
- `npx -y @steipete/oracle --render --copy -p "<task>" --file "src/**"`
- Note: `--copy` is a hidden alias for `--copy-markdown`.
- Save-to-file (recommended so it can be committed):
- Dossier work:
- `mkdir -p "<dossier>/tmp-oracle" && npx -y @steipete/oracle --render -p "<task>" --file "src/**" > "<dossier>/tmp-oracle/oracle-bundle_<slug>.md"`
- Non-dossier work:
- `mkdir -p docs/98-tmp/oracle && npx -y @steipete/oracle --render -p "<task>" --file "src/**" > "docs/98-tmp/oracle/oracle-bundle_<slug>.md"`
## Attaching files (`--file`)
`--file` accepts files, directories, and globs. You can pass it multiple times; entries can be comma-separated.
- Include:
- `--file "src/**"` (directory glob)
- `--file src/index.ts` (literal file)
- `--file docs --file README.md` (literal directory + file)
- Exclude (prefix with `!`):
- `--file "src/**" --file "!src/**/*.test.ts" --file "!**/*.snap"`
- Defaults (important behavior from the implementation):
- Default-ignored dirs: `node_modules`, `dist`, `coverage`, `.git`, `.turbo`, `.next`, `build`, `tmp` (skipped unless you explicitly pass them as literal dirs/files).
- Honors `.gitignore` when expanding globs.
- Does not follow symlinks (glob expansion uses `followSymbolicLinks: false`).
- Dotfiles are filtered unless you explicitly opt in with a pattern that includes a dot-segment (e.g. `--file ".github/**"`).
- Hard cap: files > 1 MB are rejected (split files or narrow the match).
## Budget + observability
- Target: keep total input under ~196k tokens.
- Use `--files-report` (and/or `--dry-run json`) to spot the token hogs before spending.
- If you need hidden/advanced knobs: `npx -y @steipete/oracle --help --verbose`.
## Engines (API vs browser)
- Auto-pick: uses `api` when `OPENAI_API_KEY` is set, otherwise `browser`.
- Browser engine supports GPT + Gemini only; use `--engine api` for Claude/Grok/Codex or multi-model runs.
- **API runs require explicit user consent** before starting because they incur usage costs.
- Browser attachments:
- `--browser-attachments auto|never|always` (auto pastes inline up to ~60k chars then uploads).
- Remote browser host (signed-in machine runs automation):
- Host: `oracle serve --host 0.0.0.0 --port 9473 --token <secret>`
- Client: `oracle --engine browser --remote-host <host:port> --remote-token <secret> -p "<task>" --file "src/**"`
## Sessions + slugs (don’t lose work)
- Stored under `~/.oracle/sessions` (override with `ORACLE_HOME_DIR`).
- Runs may detach or take a long time (browser + GPT‑5.2 Pro often does). If the CLI times out: don’t re-run; reattach.
- List: `oracle status --hours 72`
- Attach: `oracle session <id> --render`
- Use `--slug "<3-5 words>"` to keep session IDs readable.
- Duplicate prompt guard exists; use `--force` only when you truly want a fresh run.
## Prompt template (high signal)
Oracle starts with **zero** project knowledge. Assume the model cannot infer your stack, build tooling, conventions, or “obvious” paths. Include:
- Project briefing (stack + build/test commands + platform constraints).
- “Where things live” (key directories, entrypoints, config files, dependency boundaries).
- Exact question + what you tried + the error text (verbatim).
- Constraints (“don’t change X”, “must keep public API”, “perf budget”, etc).
- Desired output (“return patch plan + tests”, “list risky assumptions”, “give 3 options with tradeoffs”).
### “Exhaustive prompt” pattern (for later restoration)
When you know this will be a long investigation, write a prompt that can stand alone later:
- Top: 6–30 sentence project briefing + current goal.
- Middle: concrete repro steps + exact errors + what you already tried.
- Bottom: attach *all* context files needed so a fresh model can fully understand (entrypoints, configs, key modules, docs).
If you need to reproduce the same context later, re-run with the same prompt + `--file …` set (Oracle runs are one-shot; the model doesn’t remember prior runs).
## Safety
- Don’t attach secrets by default (`.env`, key files, auth tokens). Redact aggressively; share only what’s required.
- Prefer “just enough context”: fewer files + better prompt beats whole-repo dumps.Related Skills
performance-oracle
Use this agent when you need to analyze code for performance issues, optimize algorithms, identify bottlenecks, or ensure scalability. This includes reviewing database queries, memory usage, caching strategies, and overall system performance. The agent should be invoked after implementing features or when performance concerns arise.\n\n.
skill-creator
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
modular-skills-architect
Map and refactor an agent context ecosystem: skills, commands/workflows, hooks, agent files, AGENTS.md templates, and docs. Output system map, module/dependency design, Register updates, and a concrete split/consolidate/rename/delete plan. Use when routing or ownership is messy.
heal-skill
This skill should be used when fixing incorrect SKILL.md files with outdated instructions or APIs.
create-agent-skills
Expert guidance for creating, writing, and refining Claude Code Skills. Use when working with SKILL.md files, authoring new skills, improving existing skills, or understanding skill structure and best practices.
agent-native-audit
Comprehensive agent-native architecture audit with scored principles and multi-slice review. Use for system-wide health checks or periodic audits.
write-judge-prompt
Design LLM-as-Judge evaluators for subjective criteria that code-based checks cannot handle. Use when a failure mode requires interpretation (tone, faithfulness, relevance, completeness). Do NOT use when the failure mode can be checked with code (regex, schema validation, execution tests). Do NOT use when you need to validate or calibrate the judge — use validate-evaluator instead.
validate-evaluator
Calibrate an LLM judge against human labels using data splits, TPR/TNR, and bias correction. Use after writing a judge prompt (write-judge-prompt) when you need to verify alignment before trusting its outputs. Do NOT use for code-based evaluators (those are deterministic; test with standard unit tests).
generate-synthetic-data
Create diverse synthetic test inputs for LLM pipeline evaluation using dimension-based tuple generation. Use when bootstrapping an eval dataset, when real user data is sparse, or when stress-testing specific failure hypotheses. Do NOT use when you already have 100+ representative real traces (use stratified sampling instead), or when the task is collecting production logs.
evaluate-rag
Guides evaluation of RAG pipeline retrieval and generation quality. Use when evaluating a retrieval-augmented generation system, measuring retrieval quality, assessing generation faithfulness or relevance, generating synthetic QA pairs for retrieval testing, or optimizing chunking strategies.
eval-audit
Audit an LLM eval pipeline and surface problems: missing error analysis, unvalidated judges, vanity metrics, etc. Use when inheriting an eval system, when unsure whether evals are trustworthy, or as a starting point when no eval infrastructure exists. Do NOT use when the goal is to build a new evaluator from scratch (use error-analysis, write-judge-prompt, or validate-evaluator instead).
error-analysis
Help the user systematically identify and categorize failure modes in an LLM pipeline by reading traces. Use when starting a new eval project, after significant pipeline changes (new features, model switches, prompt rewrites), when production metrics drop, or after incidents.