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 joshua-zyy/academic-paper-writer --skill academic-citationgit clone --depth 1 https://github.com/joshua-zyy/academic-paper-writerWrote 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/joshua-zyy/academic-paper-writer/academic-citation)<a href="https://agentmods.dev/skills/joshua-zyy/academic-paper-writer/academic-citation"><img src="https://agentmods.dev/badge/skills/joshua-zyy/academic-paper-writer/academic-citation/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/joshua-zyy/academic-paper-writer/academic-citation"><img src="https://agentmods.dev/badge/skills/joshua-zyy/academic-paper-writer/academic-citation.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 | $0.00146 | $0.01017 |
| Opus 5 | $0.00073 | $0.00508 |
| Sonnet 5 | $0.00029 | $0.00203 |
| Haiku 4.5 | $0.00015 | $0.00102 |
Grade A, and why
academic-citation 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 13d 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Academic Citation
将此 skill 视为"文献取证代理"，而不是搜索结果搬运器。
Router Protocol
- Read
manifest.yaml. It declaresalways_loadfiles,axes, andreferences.on_demand. - Read every file listed under
always_load. These are the skill's binding rules — not reference material. - Apply the loaded material as constraints:
stance.mddefines non-negotiable rules, source/inference boundary, and scope.red-lines.mddefines absolute prohibitions. Do not negotiate these.output-contract.mddefines deliverables per mode.anti-patterns.mddefines known failure modes and their correct alternatives.
- If the user wants to use a local literature library, first distinguish:
local_ref_md_dir: an existing Markdown library containing_index_ref.json.local_ref_pdf_dir: a PDF directory, or any local library directory that lacks_index_ref.json.
- For
local_ref_pdf_dir, stop before citation search. Tell the user to register a MinerU API token, setMINERU_API_TOKEN, runscripts/convert-pdfs-to-md.py, and return only after they confirm PDF→MD completion. Do not proceed to local reading until the generated MD directory has_index_ref.json. - Detect the workflow using the manifest's
workflowaxis. Literature reading output must separate source quotes from agent inference; onlysource: 原文orsource: 图片content may be used as citation evidence. - Echo the selected mode to the user before executing.
- Reach for
references/only when the manifest'sreferences.on_demandcondition is satisfied.
Modes
| Mode | Use when |
|---|---|
full-citation-pass |
Complete coverage for a full paper or core section |
targeted-citation-search |
Specific claim, section, or topic |
exemplar-set-only |
Build Exemplar Set only, not full citation list |
citation-verification |
Verify metadata of existing candidate list |
local-citation-pass |
Local MD library first, then web supplement |
citation-verification-with-reading |
Full-text reading after paper draft completion |
What ships with it
14 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.
- agents/citation_agent.md 8.9 KB
- agents/literature-reader-agent.md 11 KB
- manifest.yaml 1.8 KB
- references/citation-mapping.md 2.1 KB
- references/search-strategy.md 2.9 KB
- references/verification-protocol.md 2.8 KB
- references/workflow-citation-pass.md 6.0 KB
- scripts/citation_audit.py 3.5 KB runs code
- scripts/convert_pdfs_to_md_mineru_api.py 23 KB runs code
- scripts/convert-pdfs-to-md.py 2.2 KB runs code
- static/core/anti-patterns.md 603 B
- static/core/output-contract.md 1.1 KB
- static/core/red-lines.md 391 B
- static/core/stance.md 3.5 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.
- 13d ago First seen · 65 lines · 146 tokens per session scan A e873c4e03d7a
academic-citation is a skill published in the GitHub repository joshua-zyy/academic-paper-writer (110 stars, last pushed 2mo ago), licensed MIT. It adds 146 tokens to every session and 1,017 once invoked, about $0.0007 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 2026-08-30.
Other skills, from other repositories
anti-defensive-writing-en
Stops defensive writing across the entire paper lifecycle — writing, revising, cutting, and organizing experiments. Treats the paper as a press conference, not a project summary, lab log, or self-audit: identify the single most publishable strength of the work and build the most favorable, complete, and persuasive…
anti-defensive-writing
A Chinese-language writing guide for presenting a research paper around its strongest supported contribution. It treats the paper as a focused academic presentation rather than a project diary or complete lab record.
light-paper-writing
A research-paper writing workflow that links each important claim to evidence and checks whether the wording matches the strength of that evidence.
light-result-analysis
A research-results review workflow that explains what experiment results may mean and how strongly they support each claim. It uses statistical checks such as effect sizes, confidence intervals, and corrections for testing many hypotheses.
light-figure
A research-figure workflow for planning and creating publication-ready charts and diagrams. It connects each figure to a paper claim and checks that the visual presentation does not misrepresent the data.
light-research-plan
A research-planning guide for turning an approved idea into a reproducible experiment plan. It defines what to compare, what to measure, when to stop, and how to record seeds, environments, versions, and data splits.