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 referencegit 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/reference)<a href="https://agentmods.dev/skills/docxology/template/reference"><img src="https://agentmods.dev/badge/skills/docxology/template/reference/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/reference"><img src="https://agentmods.dev/badge/skills/docxology/template/reference.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00131 | $0.01348 |
| Opus 5 | $0.00066 | $0.00674 |
| Sonnet 5 | $0.00026 | $0.00270 |
| Haiku 4.5 | $0.00013 | $0.00135 |
Grade A, and why
infrastructure-reference 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 5d 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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reference Module
Bibliographic-reference workflows for the template's two-layer architecture.
Output is byte-compatible with the existing
projects/templates/template_code_project/manuscript/references.bib format and round-trips
through the parser without semantic loss.
citation — BibTeX read/write/convert
from infrastructure.reference.citation import (
BibEntry, BibDatabase,
parse_bibfile, parse_bibtex, BibParseError,
render_entry, render_database, render_entries, write_bibfile,
paper_to_bibentry, generate_citation_key,
escape_latex, unescape_latex,
)
Read & validate an existing .bib
db = parse_bibfile("projects/templates/template_code_project/manuscript/references.bib")
print(len(db), "entries")
boyd = db.find("boyd2004convex")
assert boyd.entry_type == "article"
assert boyd.get("author") == "Boyd, Stephen and Vandenberghe, Lieven"
Build entries programmatically
from collections import OrderedDict
entry = BibEntry(
entry_type="article",
citation_key="smith2024example",
fields=OrderedDict([
("title", "An Example Paper"),
("author", "Smith, Alice and Jones, Bob"),
("journal", "Cambridge UP"),
("year", "2024"),
("pages", "1-10"), # auto-normalised to "1--10"
("doi", "10.1234/example"),
]),
)
print(render_entry(entry))
Output (matches the exemplar exactly):
@article{smith2024example,
title={An Example Paper},
author={Smith, Alice and Jones, Bob},
journal={Cambridge UP},
year={2024},
pages={1--10},
doi={10.1234/example}
}
Convert a literature search result to BibTeX
from infrastructure.search.literature import LiteratureClient, SearchQuery, ArxivBackend
from infrastructure.reference.citation import paper_to_bibentry, render_database
from infrastructure.reference.citation.models import BibDatabase
result = LiteratureClient([ArxivBackend()]).search(SearchQuery(text="adam optimizer"))
db = BibDatabase()
for paper in result.papers:
db.add(paper_to_bibentry(paper))
write_bibfile("output/references.bib", db)
What ships with it
24 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 1.2 KB runs code
- AGENTS.md 7.3 KB
- citation/__init__.py 1.7 KB runs code
- citation/__main__.py 180 B runs code
- citation/AGENTS.md 2.3 KB
- citation/bibtex_parser.py 8.7 KB runs code
- citation/bibtex_writer.py 5.7 KB runs code
- citation/cli.py 5.3 KB runs code
- citation/converter.py 5.8 KB runs code
- citation/escape.py 2.4 KB runs code
- citation/models.py 5.7 KB runs code
- citation/README.md 1.6 KB
- citation/SKILL.md 3.7 KB
- README.md 3.1 KB
- verification/__init__.py 1.8 KB runs code
- verification/__main__.py 183 B runs code
- verification/AGENTS.md 2.1 KB
- verification/cache.py 4.5 KB runs code
- verification/cli.py 5.2 KB runs code
- verification/models.py 5.4 KB runs code
- verification/README.md 1.5 KB
- verification/resolver.py 13 KB runs code
- verification/SKILL.md 3.0 KB
- verification/verifier.py 8.8 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.
- 5d ago First seen · 144 lines · 131 tokens per session scan A efdee73b72a7
infrastructure-reference is a skill published in the GitHub repository docxology/template (19 stars, last pushed today), licensed Apache-2.0. It adds 131 tokens to every session and 1,348 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 2026-09-03.
Other skills, from other repositories
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…
aerospace-engineering-technician
Use when a task needs the judgment of an Aerospace Engineering and Operations Technologist/Technician — verifying an installed fastener's preload against a drawing's torque callout via the T=K·D·F relationship, reducing strain-gauge data from a structural proof-load test into stress and checking it against an…
agricultural-sciences-professor
Use when a task needs the judgment of a tenure-track or tenured Agricultural Sciences faculty member at a land-grant university — deciding whether to submit a grant this cycle versus wait, allocating time across the teaching/research/extension appointment split, diagnosing a stalled graduate student or field trial, or…
aviation-inspector
Use when a task needs the judgment of an Aviation Inspector — determining whether an air carrier's fleet is in compliance with an Airworthiness Directive across a maintenance-records sample, deciding where the FAA's compliance-and-enforcement ladder places a finding (compliance action vs. Letter of Correction vs.…
compensation-benefits-specialist
Use when a task needs the judgment of a Compensation, Benefits, and Job Analysis Specialist — market-pricing a job against salary survey data, scoring a job through a point-factor or IPE job evaluation, running a pay-equity regression or cohort analysis, building or refreshing a salary structure and compa-ratio bands…
actor
Use when a task needs the judgment of a professional Actor — breaking down sides for a self-tape audition, preparing a character choice for rehearsal, deciding between two conflicting bookings, reading a contract offer for scale vs. scale-plus terms, or diagnosing why callbacks aren't converting to bookings.