Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/llv22/AutoResearchWithEyesWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/llv22/autoresearchwitheyes/autor.idea-discovery)<a href="https://agentmods.dev/commands/llv22/autoresearchwitheyes/autor.idea-discovery"><img src="https://agentmods.dev/badge/commands/llv22/autoresearchwitheyes/autor.idea-discovery.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00061 | $0.03034 |
| Opus 5 | $0.00030 | $0.01517 |
| Sonnet 5 | $0.00012 | $0.00607 |
| Haiku 4.5 | $0.00006 | $0.00303 |
Grade A, and why
autor.idea-discovery scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 300 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workflow 1: Idea Discovery Pipeline
Orchestrate a complete idea discovery workflow for: $ARGUMENTS
Output Directory
All intermediate and final results are saved to a dedicated output folder:
- Default: If the input is a file path like
path/to/spec.md, the output folder ispath/to/autor.idea_discovery/ - Override: Append
— output: path/to/output/to the arguments - Plain text input: Output folder is
./autor.idea_discovery/in the current working directory
The output folder is self-contained — it includes the input spec, live status, and all generated results:
task_spec.md— Copy of the input spec (preserved for reproducibility)task_status.md— Live pipeline status, decisions, and idea rankings with links to IDEA_REPORT sectionsLITERATURE_SURVEY.md— Literature landscape summary (Phase 1)IDEA_REPORT.md— Final ranked idea report (Phase 5)REVIEW_*.md— External reviewer feedback (Phase 4)- Any pilot experiment logs (Phase 2, if applicable)
Overview
This skill chains four sub-skills into a single automated pipeline:
/research-lit → /idea-creator → /novelty-check → research-reviewer agent
(survey) (brainstorm) (verify novel) (critical feedback)
Each phase builds on the previous one's output. The final deliverable is a validated OUTPUT_DIR/IDEA_REPORT.md with ranked ideas, pilot results, and a suggested execution plan. All files are saved to OUTPUT_DIR (see Output Directory).
Constants
All constants (PILOT_MAX_HOURS, PILOT_TIMEOUT_HOURS, MAX_PILOT_IDEAS, MAX_TOTAL_GPU_HOURS, AUTO_PROCEED, REVIEWER_MODEL) are defined in the project's CLAUDE.md. Read them from there before proceeding.
Override inline, e.g.,
/autor.idea-discovery "topic" — pilot budget: 4h per idea, 20h totalor/autor.idea-discovery "topic" — wait for my approval at each step.
Pipeline
Phase 0: Argument & Output Resolution
Before starting the pipeline, determine whether $ARGUMENTS is a file path or a plain text direction, and resolve the output directory.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 7d ago First seen · 300 lines · 61 tokens per session scan A bd1430c3cfa5
autor.idea-discovery is a command published in the GitHub repository llv22/AutoResearchWithEyes (5 stars, last pushed 1mo ago), licensed MIT. It adds 61 tokens to every session and 3,034 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.