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 agentmods add skills/docxology/template/publishingnpx 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.svg" alt="Measured on agentmods" 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 | $0.00127 | $0.02444 |
| Opus 5 | $0.00063 | $0.01222 |
| Sonnet 5 | $0.00025 | $0.00489 |
| Haiku 4.5 | $0.00013 | $0.00244 |
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 yesterday.
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 — 284 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) and platforms.py / api.py remain for backwards compatibility.
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 4.2 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
- abstract_plaintext.py 8.1 KB runs code
- AGENTS.md 37 KB
- announcement.py 2.1 KB runs code
- api.py 491 B runs code
- archival_cli.py 3.2 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 5.7 KB runs code
- archival/providers.py 17 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 3.3 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 18 KB runs code
- export_bundle.py 12 KB runs code
- github/__init__.py 119 B runs code
- github/AGENTS.md 844 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_export_cli.py 3.7 KB runs code
- metadata_export.py 14 KB runs code
- metadata_from_config.py 11 KB runs code
- metadata_package.py 22 KB runs code
- metadata_stage.py 1.9 KB runs code
- metadata.py 764 B runs code
- 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 2.9 KB runs code
- platforms.py 2.3 KB runs code
- preflight.py 15 KB runs code
- publication_ledger.py 4.0 KB runs code
- publish_cli.py 2.0 KB runs code
- pypi_release.py 4.4 KB runs code
- pypi/__init__.py 771 B runs code
- pypi/adapter.py 6.5 KB runs code
- pypi/AGENTS.md 2.0 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.
- yesterday First seen · 284 lines · 127 tokens per session scan A 4d30aeda3b49
infrastructure-publishing is a skill published in the GitHub repository docxology/template (19 stars, last pushed today), licensed Apache-2.0. It adds 127 tokens to every session and 2,444 once invoked, about $0.0006 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 2026-09-03.
Other skills, from other repositories
release
Execute the weekly release checklist for any uFawkes repo. Use when an increment is ready to ship. Implements the write-once-ship-four-times pattern: README → CHANGELOG → GitHub Release → dev.to → LinkedIn → ufawkes.dev.
ship
Use when a change is ready to land. Runs the full sequence — branch, quality gate, commit, push, PR — so nothing gets skipped.
skill-skill
Use this skill when the user has a working AI rule or skill file and wants to package and publish it as a GitHub repository end to end. Trigger when the user says 'I have a skill, help me publish it', 'turn my prompt into a GitHub repo', 'publish my Cursor rule', 'put this skill on GitHub end to end', 'walk me through…
share-a-library
Use when a managed library is ready to publish to GitHub and hand to teammates as an install command. Run the GitHub publishing steps, then return the exact shareable install command.
planning-with-files
Persistent file-based planning for multi-step AI-agent work. Keeps taskplan.md, findings.md, and progress.md on disk; lifecycle hooks inject selected project planning context. Automatic recovery reads project planning files only. Explicit session-catchup.py --metadata reads same-project local agent session records and…
shep-kit:commit-pr
Use when ready to commit, push, and create a PR with CI verification. Triggers include "commit and pr", "push pr", "create pr", "ship it", or when implementation is complete and needs CI validation. Watches CI and auto-fixes failures. Part of the Shep autonomous SDLC platform — https://shep.bot.