Methodology Review

Methodology Review is a skill for Claude Code from GongShichen/LuminaCode. It costs 18 tokens per session (697 once invoked), scanned A, original, Apache-2.0.

A review of how research was done, including the range of sources, possible bias, and how strongly the evidence supports the conclusions.

In plain words
What is it for?
Assessing research plans, source selection, bias risks, and the strength of reported findings.
Why use it?
It shows whether a conclusion is well supported or rests on a narrow or unreliable method.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

Good fit Assessing research plans, source selection, bias risks, and the strength of reported findings.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/gongshichen/luminacode/methodology-review
Install

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.

Any agent
npx skills add GongShichen/LuminaCode --skill methodology-review
Clone the repo
git clone --depth 1 https://github.com/GongShichen/LuminaCode

Made for: Claude Code.

Wrote 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.

agentmods badge for Methodology Review

README.md
[![agentmods](https://agentmods.dev/badge/skills/gongshichen/luminacode/methodology-review/github.svg)](https://agentmods.dev/skills/gongshichen/luminacode/methodology-review)
Your own site
<a href="https://agentmods.dev/skills/gongshichen/luminacode/methodology-review"><img src="https://agentmods.dev/badge/skills/gongshichen/luminacode/methodology-review/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.

agentmods 80×15 button for Methodology Review

Your own site · 80×15
<a href="https://agentmods.dev/skills/gongshichen/luminacode/methodology-review"><img src="https://agentmods.dev/badge/skills/gongshichen/luminacode/methodology-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 697 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00018 $0.00697
Opus 5.5 $0.00007 $0.00279
Sonnet 5.5 $0.00004 $0.00139
Haiku 4.5 $0.00002 $0.00070

Measured 2mo ago against content hash 1d0f2973352d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Methodology Review 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.

.Lumina/TEAM/deep-research/reviewer/skills/methodology-review/SKILL.md · 101 lines

What it actually says

Review whether the research process supports the answer.

Before reviewing:

  • Call GetTeamContext.
  • Use runtime contract as authoritative.
  • Read research-plan.md, sources.jsonl, evidence-matrix.jsonl, conflicts-and-limitations.md, final-report.md, and qa-report.md if present.

Procedure:

  1. Load context and required artifacts.
  2. Compare the final report against the research contract.
  3. Audit search breadth and source diversity.
  4. Audit evidence reasoning and conflict handling.
  5. Classify findings as blocking or nonblocking.
  6. Write review-report.md.
  7. Call SubmitGateVerdict for methodology_review.

Checks:

  1. Research question fit

    • Does the final report answer the contracted question?
    • Are audience and decision intent respected?
  2. Search breadth

    • Were multiple query families used?
    • Were primary/official/academic sources considered where appropriate?
    • Were negative/conflicting sources searched?
  3. Source quality

    • Are sources credible for the claims they support?
    • Is there overreliance on secondary, outdated, vendor, or low-quality sources?
  4. Evidence reasoning

    • Are conclusions proportional to evidence confidence?
    • Are conflicts acknowledged?
    • Are limitations visible enough for the user?
    • Does every key claim rest on retrieved source content rather than snippets, model memory, or unretrieved metadata?
  5. Reproducibility

    • Can another agent understand what was searched, fetched, and used?
    • Are source IDs and artifacts stable?

Blocking findings:

  • Conclusion stronger than evidence.
  • Missing major source class.
  • Missing conflict/limitation handling.
  • Search strategy too narrow.
  • QA failed or was skipped when required.
  • Report would mislead a decision maker.
  • Any final claim based on training knowledge, model memory, snippets, inaccessible sources, or undocumented fallback retrieval.
  • Any final claim or evidence item citing a source without retrieval_status and claim_support_allowed in sources.jsonl.
  • Any final claim or evidence item citing a source whose claim_support_allowed is false.
  • Any source registry using invalid retrieval status aliases such as success, fail, fetched, or fetch_failed instead of retrieved, partially_retrieved, or inaccessible.
  • Any workflow that skips Source Reader and treats Search Strategist candidates as registered evidence.

Output:

Write review-report.md:

# Methodology Review

## Verdict
pass|accepted_with_notes|reject

## Method Review
- Question fit:
- Search breadth:
- Source quality:
- Evidence reasoning:
- Reproducibility:

## Findings
### Blocking
- ...
### Nonblocking
- ...

## Deferral Candidates
- Finding:
  - Why safe to defer:
  - Suggested follow-up:

Then call SubmitGateVerdict:

  • gate/check name: methodology_review
  • status: pass, accepted_with_notes, or reject
  • findings: mark blocking accurately.
  • evidence: cite review report sections and artifact paths.
Changes

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.

  1. 2mo ago First seen · 101 lines · 18 tokens per session scan A 1d0f2973352d

Subscribe to this mod's changes

Methodology Review is a skill published in the GitHub repository GongShichen/LuminaCode (9 stars, last pushed 4d ago), licensed Apache-2.0. It adds 18 tokens to every session and 697 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.

Related

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…

microsoft/ai-agents-for-beginners · 200 tokens

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

vercel/next.js · 95 tokens

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.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens

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…

vercel/next.js · 83 tokens