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 Vambrocop/EvidenceForge --skill umbrella-review-skepticgit clone --depth 1 https://github.com/Vambrocop/EvidenceForgeWrote 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/vambrocop/evidenceforge/umbrella-review-skeptic)<a href="https://agentmods.dev/skills/vambrocop/evidenceforge/umbrella-review-skeptic"><img src="https://agentmods.dev/badge/skills/vambrocop/evidenceforge/umbrella-review-skeptic/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/vambrocop/evidenceforge/umbrella-review-skeptic"><img src="https://agentmods.dev/badge/skills/vambrocop/evidenceforge/umbrella-review-skeptic.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 | $0.00075 | $0.00848 |
| Opus 5 | $0.00037 | $0.00424 |
| Sonnet 5 | $0.00015 | $0.00170 |
| Haiku 4.5 | $0.00007 | $0.00085 |
Grade A, and why
umbrella-review-skeptic 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 11d 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Umbrella Review Skeptic
Use this skill when the evidence base already contains reviews or meta-analyses and the user wants to synthesize the syntheses.
Core Principle
Do not simply average meta-analyses. Existing reviews often reuse the same primary studies, use different inclusion rules, and report non-comparable pooled effects.
Intake
Identify:
- included reviews/meta-analyses;
- review questions;
- search dates;
- primary studies included in each review;
- pooled effects and metrics;
- quality assessment method;
- overlap among reviews;
- whether a second-order statistical synthesis is planned.
Load:
references/overlap-and-quality.mdfor overlap and quality checks.references/second-order-decision-rules.mdwhen deciding whether review-level pooling is defensible.references/agricultural-diversification-second-order-meta.mdfor long-term agricultural diversification, ecosystem-service, profitability, and yield trade-off synthesis.
Workflow
- Classify the project: umbrella review, review of reviews, or second-order meta-analysis.
- Extract review-level characteristics.
- Build a primary-study by review matrix.
- Assess overlap and duplicate evidence.
- Assess review quality and search currency.
- Compare effect metrics and inclusion criteria.
- Apply AMSTAR 2 / ROBIS-style review appraisal logic where appropriate.
- Decide: narrative umbrella synthesis, evidence map, or second-order pooling.
- If pooling, state dependence assumptions and model choice.
- Report discordance and certainty.
Use templates/overlap-matrix.md for overlap tracking.
Use templates/second-order-temporal-tradeoff-audit.md and templates/review-level-effect-schema.csv for review-level temporal meta-regression and yield-service trade-off audits.
Use templates/second-order-r-package-ledger.csv when extracting software packages and model roles from a second-order meta-analysis.
Use templates/osf-r-dependency-inventory.csv when auditing OSF/GitHub R scripts beyond the packages named in the paper.
Use templates/second-order-quality-scorecard.csv, templates/second-order-model-spec-ledger.csv, and templates/agricultural-diversification-taxonomy.csv when adapting agricultural diversification second-order meta-analysis protocols.
Use templates/second-order-peer-review-readiness-checklist.csv before submission or revision to anticipate reviewer concerns about second-order environmental meta-analyses.
What ships with it
12 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/agricultural-diversification-second-order-meta.md 15 KB
- references/overlap-and-quality.md 1.5 KB
- references/second-order-decision-rules.md 1.7 KB
- templates/agricultural-diversification-taxonomy.csv 3.3 KB
- templates/osf-r-dependency-inventory.csv 4.5 KB
- templates/overlap-matrix.md 280 B
- templates/review-level-effect-schema.csv 1.9 KB
- templates/second-order-model-spec-ledger.csv 1.1 KB
- templates/second-order-peer-review-readiness-checklist.csv 3.6 KB
- templates/second-order-quality-scorecard.csv 1.4 KB
- templates/second-order-r-package-ledger.csv 1.4 KB
- templates/second-order-temporal-tradeoff-audit.md 2.1 KB
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.
- 11d ago First seen · 104 lines · 75 tokens per session scan A 6fe883c9d18e
umbrella-review-skeptic is a skill published in the GitHub repository Vambrocop/EvidenceForge (5 stars, last pushed 1mo ago), licensed MIT. It adds 75 tokens to every session and 848 once invoked, about $0.0004 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 skills, from other repositories
easymeta
A workflow for systematic reviews, evidence maps, and meta-analyses in medicine, public health, and natural or environmental sciences.
systematic-review
Use this Skill when conducting a systematic literature review following PRISMA 2020: PICO framework, database search strategy, title/abstract screening, full-text eligibility, data extraction, and GRADE evidence grading.
systematic-review-epi
Use this Skill for systematic reviews: meta-regression, publication bias tests (Egger, funnel plot), GRADE evidence synthesis, and forest plots.
create-pr
Creates a GitHub PR with a Linear-ticket-prefixed title and a decision-led, narrative description for prisma-next. Use when the user wants to create a pull request, open a PR, or submit changes for review.
contrib-pr
Open a high-quality external contributor PR against prisma/orm. Use when the user is an outside contributor (not a Prisma maintainer) and wants to submit a change as a pull request from a fork. Encodes the contribution flow from CONTRIBUTING.md so the resulting PR passes review on the first round.
github-review-iteration
Orchestrates a GitHub PR review loop by delegating triage and implementation to dedicated sub-agents, then repeating until actionable review items are cleared. Use when the user says “address PR review”, “triage review comments”, or “iterate until review is clean”.