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 methodology-reviewgit 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/methodology-review)<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.
<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>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 | $0.00018 | $0.00697 |
| Opus 5.5 | $0.00007 | $0.00279 |
| Sonnet 5.5 | $0.00004 | $0.00139 |
| Haiku 4.5 | $0.00002 | $0.00070 |
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.
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, andqa-report.mdif present.
Procedure:
- Load context and required artifacts.
- Compare the final report against the research contract.
- Audit search breadth and source diversity.
- Audit evidence reasoning and conflict handling.
- Classify findings as blocking or nonblocking.
- Write
review-report.md. - Call
SubmitGateVerdictformethodology_review.
Checks:
-
Research question fit
- Does the final report answer the contracted question?
- Are audience and decision intent respected?
-
Search breadth
- Were multiple query families used?
- Were primary/official/academic sources considered where appropriate?
- Were negative/conflicting sources searched?
-
Source quality
- Are sources credible for the claims they support?
- Is there overreliance on secondary, outdated, vendor, or low-quality sources?
-
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?
-
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_statusandclaim_support_allowedinsources.jsonl. - Any final claim or evidence item citing a source whose
claim_support_allowedis false. - Any source registry using invalid retrieval status aliases such as
success,fail,fetched, orfetch_failedinstead ofretrieved,partially_retrieved, orinaccessible. - 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, orreject - findings: mark blocking accurately.
- evidence: cite review report sections and artifact paths.
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 · 101 lines · 18 tokens per session scan A 1d0f2973352d
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.
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…