Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/xiaweiyi713/citeguardnpx agentmods add skills/xiaweiyi713/citeguard/citeguard-maintainWrote 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-maintain)<a href="https://agentmods.dev/skills/xiaweiyi713/citeguard/citeguard-maintain"><img src="https://agentmods.dev/badge/skills/xiaweiyi713/citeguard/citeguard-maintain/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-maintain"><img src="https://agentmods.dev/badge/skills/xiaweiyi713/citeguard/citeguard-maintain.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 | $0.00060 | $0.00688 |
| Opus 5 | $0.00030 | $0.00344 |
| Sonnet 5 | $0.00012 | $0.00138 |
| Haiku 4.5 | $0.00006 | $0.00069 |
Grade A, and why
citeguard-maintain 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Maintain CiteGuard
Keep repository-only evaluation and release work separate from the installed
citeguard-verify user skill.
Evaluation workflow
-
Validate the user-skill trigger set, then score decisions captured from the target agent/client:
python scripts/eval_skill_trigger.py --validate-only python scripts/eval_skill_trigger.py --write-template /tmp/citeguard-trigger-predictions.json # Fill each triggered value after running the request through the target agent. python scripts/eval_skill_trigger.py --predictions /tmp/citeguard-trigger-predictions.json -
Audit label maturity:
python scripts/prepare_support_label_sidecar.py --audit -
Follow
review_plan.next_phaseand generate blinded packets with the returned command template. Never expose hidden gold labels or predictions to reviewers. -
Record packet id, digest, reviewer identity, evidence scope, and whether full text was needed.
-
Resolve dual-review disagreements before raising release thresholds.
-
Run deterministic reports on the test split only after calibration choices are frozen.
For the strict publish-gate packet sizes and independent first/second-review
commands, follow docs/support_labeling_guidelines.md; do not invent or copy
labels to satisfy thresholds.
Use python scripts/eval_support.py --help and
python scripts/prepare_support_label_sidecar.py --help for current arguments;
do not copy stale command shapes into this skill.
Release workflow
Run, in order:
python -m unittest discover -s tests -v
python scripts/smoke_package.py --install-mode wheel
python scripts/smoke_package.py --install-mode sdist
python -m pip install -e ".[models]"
python scripts/automated_release_review.py --output automated-release-review.json
python scripts/release_package_gate.py --release-claim-mode software --automated-review-report automated-release-review.json
Also validate server.json, run the MCP stdio smoke in a Python 3.10+
environment, and test the exact published-package command used by registry
clients. Build from a clean copy so stale build/lib files cannot enter wheels.
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.
- 11d ago First seen · 78 lines · 60 tokens per session scan A 428a7d604eeb
citeguard-maintain is a skill published in the GitHub repository xiaweiyi713/citeguard (1 stars, last pushed 21d ago), licensed MIT. It adds 60 tokens to every session and 688 once invoked, about $0.0003 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…
nature-academic-search
An academic-paper search skill finds and checks research papers, preprints, clinical-trial records, and citations across sources such as PubMed, arXiv, Crossref, and OpenAlex. It can also work with identifiers such as DOI, PMID, and trial IDs.
bibverify
Verify, repair, explain, and generate BibTeX references with Bibverify's DOI-first CLI and MCP tools.
literature-search
Use this Skill when the user needs to search academic literature, collect papers for a systematic review, or find the latest research on any topic. Covers cross-database search via OpenAlex API, Semantic Scholar API, and arXiv API, with deduplication, citation snowballing, BibTeX export, and annual trend visualization.
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.
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.