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 yogsoth-ai/de-anthropocentric-research-engine --skill comparison-designgit clone --depth 1 https://github.com/yogsoth-ai/de-anthropocentric-research-engineWrote 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/yogsoth-ai/de-anthropocentric-research-engine/comparison-design)<a href="https://agentmods.dev/skills/yogsoth-ai/de-anthropocentric-research-engine/comparison-design"><img src="https://agentmods.dev/badge/skills/yogsoth-ai/de-anthropocentric-research-engine/comparison-design/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/yogsoth-ai/de-anthropocentric-research-engine/comparison-design"><img src="https://agentmods.dev/badge/skills/yogsoth-ai/de-anthropocentric-research-engine/comparison-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 59 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
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 | $0.00013 | $0.00695 |
| Opus 5 | $0.00006 | $0.00347 |
| Sonnet 5 | $0.00003 | $0.00139 |
| Haiku 4.5 | $0.00001 | $0.00069 |
Grade A, and why
comparison-design 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 9d 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Strategy: Comparison Design
Question: How much better is our method than the baseline?
Methodology
- Fair Comparison Protocol (Bouthillier 2021): Control all confounds, same compute budget, same tuning effort.
- Multi-Baseline Comparison: Compare against multiple baselines (SOTA, simple, ablated).
- Multi-Dataset Evaluation: Test across diverse datasets to avoid dataset-specific overfitting.
- Bayesian Comparison (Benavoli 2017): Posterior probability of superiority, not just p-values.
- Bootstrap/Permutation Tests: Non-parametric significance without distributional assumptions.
Execution Flow
- baseline-selection → Select appropriate baselines (SOTA, simple, oracle)
- metric-specification → Define primary metric and secondary metrics
- sample-size-estimation → Power analysis for detecting meaningful differences
- seed-protocol-design → Ensure fair random initialization across methods
- environment-specification → Lock environment to prevent confounds
- reproducibility-protocol (tactic) → Ensure all results are reproducible
- statistical-method-selection (tactic) → Choose Bayesian or frequentist comparison
Budget Gate
| Comparison Scope | Baselines | Datasets | Seeds | Min Runs |
|---|---|---|---|---|
| Minimal | 1 SOTA + 1 simple | 1 | 3 | 6 |
| Standard | 2-3 baselines | 2-3 | 5 | 30-45 |
| Comprehensive | 4+ baselines | 3-5 | 5-10 | 100+ |
| Publication-ready | All relevant | 5+ | 10+ | 200+ |
Available Tactics
Optional, no fixed order; the final leaf is always a sop.
| Tactic | When to use |
|---|---|
| reproducibility-protocol | Ensure experiment reproducibility through systematic environment and seed control |
| statistical-method-selection | Select appropriate statistical methods for experiment analysis |
Available SOPs
Optional, no fixed order; the final leaf is always a sop.
| SOP | When to use |
|---|---|
| baseline-selection | Select appropriate baselines for experimental comparison |
| environment-specification | SOP: define complete experiment environment specification |
| metric-specification | Define experiment metrics and significance standards |
| sample-size-estimation | SOP: power analysis and required experiment count estimation |
| seed-protocol-design | SOP: design random seed strategy for reproducibility |
What ships with it
1 file 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.
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.
- 9d ago First seen · 83 lines · 13 tokens per session scan A 5d42a1e1c594
comparison-design is a skill published in the GitHub repository yogsoth-ai/de-anthropocentric-research-engine (464 stars, last pushed today), licensed Apache-2.0. It adds 13 tokens to every session and 695 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 2026-09-03.
Other skills, from other repositories
convex-verify
Prove a Convex feature works — seed, drive as multiple mocked users via convex-test, assert behavior including the negative authz cases (wrong user refused, data-scope enforced).
data-quality-frameworks
Implement data quality validation with Great Expectations, dbt tests, and data contracts. Use when building data quality pipelines, implementing validation rules, or establishing data contracts.
qa/e2e-playwright
A method for writing Playwright end-to-end tests, which automate a browser to verify complete user journeys. It covers setup, reusable page objects, login reuse, API mocking, visual checks, multiple browsers and screen sizes, CI, and debugging.
qa/test-strategy
A testing strategy based on the testing pyramid: many small unit tests, fewer integration tests, and a smaller set of end-to-end tests that follow real user journeys. It also defines checks for security, boundaries, permissions, and business consistency.
Deep Research
Produce a deep, structured research report on a topic: decompose into key dimensions, analyze each with evidence and reasoning, synthesize cross-cutting insights, and surface open questions. Use for deep research, analysis, and literature/landscape reviews.
skillgrade-setup
Sets up and runs skillgrade evaluation pipelines for Agent Skills. Use when initializing eval configurations, running trials, reviewing results, or integrating with CI. Don't use for writing grader scripts, general test authoring, or non-agentic documentation.