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.
git clone --depth 1 https://github.com/AlterLab-IEU/AlterLab-Academic-SkillsWrote 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/commands/alterlab-ieu/alterlab-academic-skills/cite-check)<a href="https://agentmods.dev/commands/alterlab-ieu/alterlab-academic-skills/cite-check"><img src="https://agentmods.dev/badge/commands/alterlab-ieu/alterlab-academic-skills/cite-check/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/commands/alterlab-ieu/alterlab-academic-skills/cite-check"><img src="https://agentmods.dev/badge/commands/alterlab-ieu/alterlab-academic-skills/cite-check.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 | $0.00056 | $0.00622 |
| Opus 5.5 | $0.00022 | $0.00249 |
| Sonnet 5.5 | $0.00011 | $0.00124 |
| Haiku 4.5 | $0.00006 | $0.00062 |
Grade A, and why
cite-check 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 1mo 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.
What it actually says
Cite-check the citations in: $ARGUMENTS
Use the alterlab-citation-verifier skill. Decide each verdict from the script
output and retrieved records, not from whether a reference looks plausible or
familiar: a model's memory shares the training data that produces fabricated
references, so it cannot confirm them.
Steps:
- Collect — Parse the references from $ARGUMENTS (a
.bibfile, a manuscript path, or a pasted list). If nothing was given, ask for the references or file. - Existence check — Run
scripts/verify_citations.pyover the references. It resolves each one against Crossref, OpenAlex, Semantic Scholar, and arXiv (no API key required; optionalOPENALEX_API_KEY/S2_API_KEYraise rate limits), checks DOI registration at doi.org, matches title and authors with the difflibSequenceMatcherratio (≥ 0.70), and maps each entry to the TF / PAC / IH / PH taxonomy. - Retraction screen — Surface every
RETRACTEDflag (Crossrefupdated-by/update-tonotices, including Retraction Watch data, or OpenAlexis_retracted) and any expression of concern. - Claim faithfulness — Where a sentence is tied to a citation, run
scripts/claim_faithfulness.pyon the (claim, DOI) pair; reportcontradictas SH and escalateunsupportedclaims (the abstract does not establish them) to the--tier llmjudge or full-text reading. - Report — A per-citation table: verdict code (
verified/TF/PAC/IH/PH/SH/unverified), flags, the source that confirmed it, and the matched DOI/ID. Summarize how many of N citations could not be verified and why (source_status).
If the network or a source is unavailable, say so explicitly: the script returns
unverified rather than a pass. For those entries, run the WebSearch fallback from
the SKILL.md "Graceful Degradation and the Fallback" section (three distinct
queries); anything still not found is reported as TF (NOT_FOUND), never as
"difficult to verify".
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.
- 1mo ago Changed · +8 lines 35cb8885e536
- 1mo ago First seen · 34 lines · 56 tokens per session scan A 813daf4c6bc7
cite-check is a command published in the GitHub repository AlterLab-IEU/AlterLab-Academic-Skills (78 stars, last pushed yesterday), licensed MIT. It adds 56 tokens to every session and 622 once invoked, about $0.0002 per session on Opus 5.5. 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 commands, from other repositories
ars-abstract
ARS academic-paper abstract-only mode — bilingual abstract + keywords.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
speckit.bug.fix
Apply the remediation from a bug assessment and record what was changed.