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.
npx skills add GongShichen/LuminaCode --skill research-reportgit clone --depth 1 https://github.com/GongShichen/LuminaCodeWrote 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/skills/gongshichen/luminacode/research-report)<a href="https://agentmods.dev/skills/gongshichen/luminacode/research-report"><img src="https://agentmods.dev/badge/skills/gongshichen/luminacode/research-report/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/gongshichen/luminacode/research-report"><img src="https://agentmods.dev/badge/skills/gongshichen/luminacode/research-report.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00017 | $0.00613 |
| Opus 5.5 | $0.00007 | $0.00245 |
| Sonnet 5.5 | $0.00003 | $0.00123 |
| Haiku 4.5 | $0.00002 | $0.00061 |
Grade A, and why
Research Report 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 2mo 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
Write a final report that is useful and traceable.
Inputs:
- Research contract.
sources.jsonl.evidence-matrix.jsonl.conflicts-and-limitations.md.- Gate findings, if any.
Procedure:
-
Confirm readiness
- Required artifacts exist.
- Evidence matrix covers each subquestion.
- Major claims have source IDs.
- Known conflicts are documented.
-
Structure the report
- Executive answer.
- Scope and method.
- Findings by subquestion.
- Comparative table when useful.
- Engineering/product/research implications when relevant.
- Limitations and open questions.
- Source list.
- Before writing the full file, decide the section outline and source IDs for each section. Keep this planning short; the deliverable is the file, not an extended drafting conversation.
-
Citation style
- Cite source IDs inline, for example
[S003]. - Do not cite search result snippets.
- Do not cite inaccessible sources for claims.
- Cite source IDs inline, for example
-
Claim discipline
- Use strong language only for high-confidence evidence.
- Use caveats for medium/low-confidence evidence.
- Avoid claims not represented in evidence matrix.
Output template:
# Final Research Report
## Executive Answer
...
## Scope and Method
- Research question:
- Search/fetch tools:
- Source classes:
## Findings
### 1. Subquestion
- Finding: ... [S001, S004]
- Confidence:
- Caveats:
## Comparison / Synthesis
...
## Engineering or Decision Implications
...
## Conflicts and Limitations
...
## Sources
- [S001] Title, authors/org, date, URL/arXiv ID.
## Evidence Index
| Evidence ID | Claim / finding | Source IDs | Confidence |
|-------------|-----------------|------------|------------|
| E001 | ... | S001, S004 | high |
Completion criteria:
- A reader can trace key claims to source IDs and evidence IDs from inside
final-report.md. - The report includes both a source index and an evidence index; do not rely on separate JSONL files alone for traceability.
- The report states what is known, uncertain, and not covered.
- The final answer can point to this file without additional explanation.
Long-report execution rule:
- Prefer one complete
write_filecall forfinal-report.md. - If the report is too large to draft confidently in one pass, write a concise but complete version first, then perform one improvement pass. Do not repeatedly ask Team Leader for retry unless a concrete artifact or evidence gap exists.
- Do not spend a long hidden planning phase before any visible output. Emit a short progress statement, then write the file.
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.
- 2mo ago First seen · 96 lines · 17 tokens per session scan A 1a437fec662b
Research Report is a skill published in the GitHub repository GongShichen/LuminaCode (9 stars, last pushed 4d ago), licensed Apache-2.0. It adds 17 tokens to every session and 613 once invoked, about $0.0001 per session on Opus 5.5. 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 skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…