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 htlin222/research-guardian-skill --skill research-guardiangit clone --depth 1 https://github.com/htlin222/research-guardian-skillWrote 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/htlin222/research-guardian-skill/research-guardian)<a href="https://agentmods.dev/skills/htlin222/research-guardian-skill/research-guardian"><img src="https://agentmods.dev/badge/skills/htlin222/research-guardian-skill/research-guardian/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/htlin222/research-guardian-skill/research-guardian"><img src="https://agentmods.dev/badge/skills/htlin222/research-guardian-skill/research-guardian.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 | $0.00222 | $0.06337 |
| Opus 5 | $0.00111 | $0.03168 |
| Sonnet 5 | $0.00044 | $0.01267 |
| Haiku 4.5 | $0.00022 | $0.00634 |
Grade A, and why
research-guardian 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 12d 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
60 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/critique-synthesis.md 1.4 KB
- references/experiment-checklist.md 4.6 KB
- references/experiment/figures-tables.md 1.4 KB
- references/experiment/math-symbol.md 1.1 KB
- references/experiment/ml-experiment.md 3.6 KB
- references/experiment/observational.md 2.6 KB
- references/experiment/qualitative.md 3.5 KB
- references/experiment/rct.md 2.4 KB
- references/extensibility-guide.md 8.3 KB
- references/hypothesis-validation.md 3.9 KB
- references/hypothesis/biomedical.md 3.9 KB
- references/hypothesis/cs-ml.md 3.7 KB
- references/hypothesis/social-science.md 3.7 KB
- references/ingestion/metadata-validation.md 1.1 KB
- references/ingestion/paper-parser.md 1.6 KB
- references/issue-schema.md 8.7 KB
- references/literature-verification.md 5.9 KB
- references/literature/biomedical.md 2.4 KB
- references/literature/cs-ml.md 1.7 KB
- references/literature/gap-framing.md 1.4 KB
- references/literature/social-science.md 1.6 KB
- references/logic-fallacy-chain.md 16 KB
- references/logic/layer1-formal.md 2.8 KB
- references/logic/layer2-causal.md 3.1 KB
- references/logic/layer3-statistical.md 2.9 KB
- references/logic/layer4-argument.md 3.1 KB
- references/logic/layer5-research.md 3.7 KB
- references/metrics/experiment-benchmarks.md 1.0 KB
- references/metrics/hypothesis-benchmarks.md 1.2 KB
- references/metrics/literature-benchmarks.md 1.2 KB
- references/metrics/result-benchmarks.md 1.2 KB
- references/metrics/writing-benchmarks.md 1.3 KB
- references/modes/audit-mode.md 1.9 KB
- references/modes/batch-review.md 1.2 KB
- references/modes/compare-papers.md 1.6 KB
- references/parallel-execution.md 10 KB
- references/performance-metrics.md 9.4 KB
- references/quick-modes.md 12 KB
- references/red-flag-synthesis.md 1.5 KB
- references/result-integrity.md 5.8 KB
- references/result/bayesian.md 3.0 KB
- references/result/frequentist.md 3.3 KB
- references/result/ml-metrics.md 2.7 KB
- references/result/qualitative.md 2.6 KB
- references/subagent-evaluation.md 9.9 KB
- references/subagent/strategy-a-isolation.md 2.3 KB
- references/subagent/strategy-b-rotation.md 1.7 KB
- references/subagent/strategy-c-adversarial.md 3.4 KB
- references/surpass/counter-arguments.md 2.0 KB
- references/surpass/fix-examples.md 2.9 KB
- references/surpass/rejection-risk.md 2.3 KB
- references/surpass/reviewer-personas.md 3.1 KB
- references/surpass/version-diff.md 1.4 KB
- references/writing-verification.md 6.8 KB
- references/writing/abstract-validation.md 1.5 KB
- references/writing/conference.md 2.6 KB
- references/writing/journal.md 2.3 KB
- references/writing/language-quality.md 1.5 KB
- references/writing/preprint.md 2.7 KB
- references/writing/structure-check.md 1.8 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.
- 12d ago First seen · 405 lines · 222 tokens per session scan A 49962c412837
research-guardian is a skill published in the GitHub repository htlin222/research-guardian-skill (5 stars, last pushed 4mo ago), with no licence file. It adds 222 tokens to every session and 6,337 once invoked, about $0.0011 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
quantum-qiskit
Reference qiskit 2.x patterns for variational quantum machine learning. Covers data-encoding feature maps, variational quantum classifier (VQC) training, variational quantum eigensolver (VQE) for chemistry, matrix-product-state circuits, and noise model integration. Use when writing Python code that imports qiskit…
flux-analyzer
Analyse FBA flux distributions to extract biological insights. Covers gene essentiality, phenotypic phase planes, flux sampling, pathway-level aggregation, secretion product prediction, and production of publication- quality figures.
fba-simulator
Run Flux Balance Analysis (FBA) and related constraint-based simulations using COBRApy. Covers standard FBA, parsimonious FBA (pFBA), Flux Variability Analysis (FVA), loopless FBA, gene/reaction knockouts, and carbon source swapping. Outputs flux distributions and CSV files.
gsmm-validator
Validate a COBRApy genome-scale metabolic model for mass/charge balance, stoichiometric consistency, biomass producibility, dead-end metabolites, thermodynamic loops, and GPR rule formatting. Outputs a structured validation report with errors and warnings.
metabolic-study-planner
Plan publishable constraint-based metabolic modelling studies when the user has a broad biological or metabolic-engineering topic but no concrete dataset, organism, model, or hypothesis. Selects feasible BiGG/COBRA models, objectives, perturbations, analyses, metrics, figures, and risk controls before FBA code is…
gsmm-builder
Build or load a genome-scale metabolic model (GSMM) using COBRApy. Covers loading from BIGG, constructing minimal models from scratch, setting medium constraints, and exporting validated .json model files.