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 docxology/template --skill publishinggit clone --depth 1 https://github.com/docxology/templateWrote 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/docxology/template/publishing)<a href="https://agentmods.dev/skills/docxology/template/publishing"><img src="https://agentmods.dev/badge/skills/docxology/template/publishing/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/docxology/template/publishing"><img src="https://agentmods.dev/badge/skills/docxology/template/publishing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Data Exfiltration · line 72 Data is uploaded to cloud storage (S3 / GCS / Azure Blob). This may be a legitimate backup or exfiltration to an external bucket. Manual review is recommended.Fix: Verify the destination bucket is trusted and owned by you. Never upload credentials, secrets, or workspace contents to external or unverified cloud storage.
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 | $0.00127 | $0.02544 |
| Opus 5.5 | $0.00051 | $0.01018 |
| Sonnet 5.5 | $0.00025 | $0.00509 |
| Haiku 4.5 | $0.00013 | $0.00254 |
Grade A, and why
infrastructure-publishing 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 10d 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 — 291 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Publishing Module
Academic publishing and dissemination tools for research projects.
For the release-operator workflow, start with
docs/guides/publication-runbook.md.
It is the front door for standalone public GitHub mirrors, real Zenodo DOI
minting, new-version releases, optional mirrors, status blocks, and archival
handoff.
Platform subpackages
| Path | Use when |
|---|---|
infrastructure.publishing.zenodo |
Zenodo deposit, upload, publish, DOI |
infrastructure.publishing.github |
GitHub release + assets |
infrastructure.publishing.arxiv |
arXiv tarball from manuscript tree |
infrastructure.publishing.pypi |
PyPI / TestPyPI package distribution |
infrastructure.publishing.static_site |
GitHub Pages, Cloudflare Pages, or Netlify deployment |
infrastructure.publishing.archival |
IPFS Pinata, Web3.Storage, Software Heritage, Zenodo mirror |
infrastructure.publishing.registry |
Enumerate or look up all platform adapters |
Root exports (infrastructure.publishing) resolve directly to the canonical subpackages; import clients and adapters from their implementation homes.
Publication metadata
from infrastructure.publishing import PublicationMetadata, extract_publication_metadata
metadata = extract_publication_metadata([Path("manuscript/01_introduction.md")])
The publication: block in manuscript/config.yaml records durable identifiers
(doi, version_doi, version_record, github_repository, repository_url).
The publication.published_artifacts key — a {platform_name: durable_url} map —
records artifacts published outside those fields (e.g. an IPFS CID or a
HuggingFace dataset URL) and is consumed by status_report.py to mark those
platforms as published.
Citation generation
The Python API exposes BibTeX, APA, and MLA helpers. The
infrastructure.publishing.cli generate-citation command currently exposes
BibTeX only.
from infrastructure.publishing import (
generate_citation_bibtex,
generate_citation_apa,
generate_citation_mla,
)
bibtex = generate_citation_bibtex(metadata)
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.
- __init__.py 4.1 KB runs code
- __main__.py 162 B runs code
- _adapter_http.py 1.8 KB runs code
- _metadata_extraction.py 4.8 KB runs code
- _metadata_reporting.py 5.9 KB runs code
- _repro_bundle_verify.py 15 KB runs code
- _standalone_export.py 3.6 KB runs code
- _standalone_git.py 17 KB runs code
- _standalone_provider_admission.py 7.3 KB runs code
- abstract_plaintext.py 8.4 KB runs code
- AGENTS.md 40 KB
- announcement.py 2.1 KB runs code
- archival_cli.py 5.7 KB runs code
- archival/__init__.py 1.6 KB runs code
- archival/AGENTS.md 3.3 KB
- archival/models.py 4.3 KB runs code
- archival/orchestrate.py 7.0 KB runs code
- archival/providers.py 23 KB runs code
- archival/README.md 2.9 KB
- arxiv/__init__.py 134 B runs code
- arxiv/AGENTS.md 1.8 KB
- arxiv/README.md 3.4 KB
- arxiv/submission.py 13 KB runs code
- checklist.py 3.0 KB runs code
- citations.py 5.0 KB runs code
- cli.py 10 KB runs code
- config_doi.py 8.2 KB runs code
- credential_check.py 10 KB runs code
- deposit_filename.py 5.5 KB runs code
- executable_bundle.py 20 KB runs code
- export_bundle.py 20 KB runs code
- github/__init__.py 119 B runs code
- github/AGENTS.md 840 B
- github/README.md 396 B
- github/release.py 2.4 KB runs code
- http_constants.py 140 B runs code
- huggingface/__init__.py 306 B runs code
- huggingface/adapter.py 12 KB runs code
- huggingface/AGENTS.md 1.1 KB
- huggingface/models.py 2.0 KB runs code
- huggingface/README.md 3.1 KB
- metadata/__init__.py 1.1 KB runs code
- metadata/AGENTS.md 1.8 KB
- metadata/metadata_export_cli.py 3.7 KB runs code
- metadata/metadata_export.py 14 KB runs code
- metadata/metadata_from_config.py 11 KB runs code
- metadata/metadata_stage.py 1.9 KB runs code
- metadata/README.md 579 B
- models.py 1.2 KB runs code
- osf/__init__.py 196 B runs code
- osf/adapter.py 7.1 KB runs code
- osf/AGENTS.md 1.2 KB
- osf/models.py 2.1 KB runs code
- osf/README.md 2.6 KB
- package.py 2.0 KB runs code
- preflight.py 15 KB runs code
- publication_ledger.py 4.0 KB runs code
- publication_tree.py 30 KB runs code
- publish_cli.py 2.0 KB runs code
- pypi_release.py 34 KB runs code
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.
- 10d ago Changed · -3 lines 8213edbdc31d
- 1mo ago Changed · +10 lines 39db4c8207d6
- 1mo ago First seen · 284 lines · 127 tokens per session scan A 4d30aeda3b49
infrastructure-publishing is a skill published in the GitHub repository docxology/template (20 stars, last pushed 2d ago), licensed Apache-2.0. It adds 127 tokens to every session and 2,544 once invoked, about $0.0005 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 skills, from other repositories
skill-skill
Create, revise, validate, package, or publish AI skills and rule files. Use as the main entry for the user's skill-authoring workflow, including creating a new SKILL.md, improving an existing rule, and preparing a skill repository. Choose only the requested stage; ordinary product code or content work is outside this…
ship
Use when a change is ready to land. Runs the full sequence — branch, quality gate, commit, push, PR — so nothing gets skipped.
git-workflow-and-versioning
Structures git workflow practices. Use when making any code change. Use when committing, branching, resolving conflicts, splitting uncommitted work in a messy working tree into clean atomic commits, opening or reviewing a pull request (PR), pushing to a remote, or when you need to organize work across multiple…
finishing-a-development-branch
A process for finishing a completed development branch. A branch is a separate line of code changes that can later be merged or submitted as a pull request.
release-rollback
Roll a release back for real when post-deploy regression goes red — apc release rollback flips the current version to pulled and the last good version back to current in the release ledger, and (with --mirror) repoints the bare mirror ref. Behind an approval gate; with no previous good version it BLOCKS instead of…
release-tag
Cut a release tag behind a real tier gate and cloud approval readback. The approval, task, approved commit, and resulting tag are bound; self-approval and HEAD drift fail closed. Prod prefixes remain refused.