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 xiaweiyi713/citeguard --skill citeguard-verifygit clone --depth 1 https://github.com/xiaweiyi713/citeguardWrote 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/xiaweiyi713/citeguard/citeguard-verify)<a href="https://agentmods.dev/skills/xiaweiyi713/citeguard/citeguard-verify"><img src="https://agentmods.dev/badge/skills/xiaweiyi713/citeguard/citeguard-verify/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/xiaweiyi713/citeguard/citeguard-verify"><img src="https://agentmods.dev/badge/skills/xiaweiyi713/citeguard/citeguard-verify.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 | $0.00092 | $0.01645 |
| Opus 5 | $0.00046 | $0.00822 |
| Sonnet 5 | $0.00018 | $0.00329 |
| Haiku 4.5 | $0.00009 | $0.00164 |
Grade A, and why
citeguard-verify 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 — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verify citations with CiteGuard
Use the CiteGuard MCP tools as the source of verification results. Never infer that a paper exists or supports a claim from memory alone.
Start safely
- Call
citeguard_status_toolonce before the first check in a task. - Continue existence and metadata checks when deep models are unavailable.
- If
support_models.engine=heuristic_fallback, label claim-support results as degraded and suggestpython -m pip install "citationguard[models]"followed byciteguard models warmup. - If source health or the cache is misconfigured, report the structured error and recovery action before interpreting results.
- Run
check_sources=trueonly for setup or outage diagnosis, not before every citation.
If the MCP server or skill is missing, suggest:
python -m pip install citationguard
citeguard skill install --client codex
The MCP stdio command is citeguard-mcp. Source checkouts may use
python -m pip install -e ..
Choose the narrowest tool
| Request | Tool |
|---|---|
| One reference or identifier | verify_citation_tool |
| Many references | audit_citations_tool |
| One claim and one citation | check_claim_support_tool |
| One claim and several citations | check_claim_support_set_tool |
| Many claim/citation rows | audit_claim_support_tool |
| Possible contrary literature | search_counterevidence_tool |
Prefer DOI or arXiv identifiers, then structured metadata, then raw_text.
Preserve input order and original indexes in every batch report. Batches are
limited to 100 rows; split larger inputs into stable, numbered chunks. Use
max_workers from 1 to 16 when latency matters. Read batch_execution as a
completion snapshot; MCP does not stream intermediate progress.
Read references/tool-payloads.md for exact call shapes. Read references/result-policy.md before handling outages, ambiguity, claim support, or filtered batch results.
What ships with it
3 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.
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 · 160 lines · 92 tokens per session scan A 9a5db38b9b48
citeguard-verify is a skill published in the GitHub repository xiaweiyi713/citeguard (1 stars, last pushed 21d ago), licensed MIT. It adds 92 tokens to every session and 1,645 once invoked, about $0.0005 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
academic-research
Nested swiss-knife reference for academic literature work — find papers, fetch full-text PDFs, trace citations, write LaTeX manuscripts. First action for any "get me this paper" request: python3 /scripts/fetchpaper.py — walks arXiv → Unpaywall → Europe PMC → CORE → in-house publisher-page extraction…
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.