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/Agentic-Assets/corbis-literature-starter-kitWrote 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/agentic-assets/corbis-literature-starter-kit/brainstorm)<a href="https://agentmods.dev/commands/agentic-assets/corbis-literature-starter-kit/brainstorm"><img src="https://agentmods.dev/badge/commands/agentic-assets/corbis-literature-starter-kit/brainstorm.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 | $0.00014 | $0.00196 |
| Opus 5 | $0.00007 | $0.00098 |
| Sonnet 5 | $0.00003 | $0.00039 |
| Haiku 4.5 | $0.00001 | $0.00020 |
Grade A, and why
brainstorm 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 8d 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.
What it actually says
Run the research-idea-generator skill on this topic:
$ARGUMENTS
Steps:
- Map the landscape with 3-4 Corbis searches (top cited, recent work, surveys).
- Apply all 10 idea-generation lenses to the topic area.
- For each lens, generate 1-2 candidate ideas and verify novelty via
search_papers. - Quick-screen each candidate (question, lens, closest paper, importance, risk, viability).
- Rank by (impact potential) x (feasibility). Select top 10.
- Produce the Idea Menu (10 ranked ideas).
- Expand the top 3 into Idea Sketches (mechanism, bridge, data, contribution tier).
- Recommend which idea to screen first with
/idea.
Produce a complete Idea Menu with Idea Sketches for the top 3.
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.
- 8d ago First seen · 20 lines · 14 tokens per session scan A 9ead1db95b47
brainstorm is a command published in the GitHub repository Agentic-Assets/corbis-literature-starter-kit (11 stars, last pushed 4mo ago), licensed MIT. It adds 14 tokens to every session and 196 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
xray
Multi-dimensional paper audit — spawns 5 parallel sub-agents to check numerical accuracy, terminology consistency, code-paper alignment, citation accuracy, and evaluation integrity.
fortify
Select strongest ablations and anticipate reviewer questions. Reads paper and experiment results to prepare for peer review.
factcheck
Verify BibTeX entries and cited claims against DBLP and web sources. Checks author names, venues, years, and specific numerical claims.
gaps
Literature gap analysis with web confirmation. Takes a research topic or question and maps existing work to find what's missing.
paper-trail-review
Review and arbitrate problematic references (cascade-exhausted, unresolved UID, awaiting OCR). Generates an up-to-date report, walks through cases by category, and applies arbitration decisions to the registry.
paper-trail-audit-article
Per-citation audit of an academic article (LaTeX or Markdown). Produces RECEIPTS.md classifying each citation as VALID/ADJUST/INVALID/UNVERIFIABLE. Optional --warn inserts inline warnings in a .bak copy of the source.