Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/docxology/templatenpx agentmods add skills/docxology/template/projectWrote 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/project)<a href="https://agentmods.dev/skills/docxology/template/project"><img src="https://agentmods.dev/badge/skills/docxology/template/project/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/project"><img src="https://agentmods.dev/badge/skills/docxology/template/project.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 | $0.00040 | $0.00910 |
| Opus 5.5 | $0.00016 | $0.00364 |
| Sonnet 5.5 | $0.00008 | $0.00182 |
| Haiku 4.5 | $0.00004 | $0.00091 |
Grade A, and why
infrastructure-project 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 6d 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Module
Multi-project discovery, validation, and metadata management.
Project Discovery (discovery.py)
from infrastructure.project import discover_projects, ProjectInfo
# Discover all valid projects in the repository
projects = discover_projects(repo_root)
for project in projects:
print(f"{project.name}: {project.path}")
print(f" Has tests: {project.has_tests}")
print(f" Has manuscript: {project.has_manuscript}")
Structure Validation
from infrastructure.project import validate_project_structure
# Validate that a project has all required directories
is_valid, message = validate_project_structure(project_path)
Required directories:
src/— Project source codetests/— Test suite
Optional (recommended) directories:
scripts/— Analysis scripts (thin orchestrators)manuscript/— Markdown manuscript sections
Metadata Extraction
from infrastructure.project import get_project_metadata
# Extract project metadata from pyproject.toml and/or manuscript/config.yaml
metadata = get_project_metadata(project_path)
print(metadata.get("title"), metadata["version"], metadata["authors"])
Optional CodeGraph Helpers
CodeGraph is a local-only agent navigation index. Use these helpers to print safe commands and verify that a template-root index did not include private symlinked projects:
from pathlib import Path
from infrastructure.project import build_codegraph_init_command, verify_codegraph_scope_payload
print(build_codegraph_init_command(Path(".")).display)
offenders = verify_codegraph_scope_payload(codegraph_files_json)
The index directory .codegraph/ is generated local state and must remain
untracked.
Rendered vs Non-Rendered Subfolders
- Rendered:
projects/templates/(public exemplars) and optionalprojects/active/(hot-seat) — discovered and executed by infrastructure when present. - Non-rendered:
projects/working/, optionalprojects/ongoing/, andprojects/archive/are preserved for explicit qualified commands and excluded from default discovery.
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 4.4 KB runs code
- acceptance_fixture_preparation.py 29 KB runs code
- acceptance_payload.py 6.3 KB runs code
- AGENTS.md 35 KB
- codegraph.py 4.8 KB runs code
- codeowners.py 3.5 KB runs code
- copy_exemplar.py 23 KB runs code
- discovery.py 8.5 KB runs code
- domain_profile.py 5.4 KB runs code
- drift/__init__.py 483 B runs code
- drift/AGENTS.md 4.7 KB
- drift/checks_boundary.py 3.4 KB runs code
- drift/checks_docs_counts.py 11 KB runs code
- drift/checks_exemplar.py 21 KB runs code
- drift/checks_forkability.py 3.9 KB runs code
- drift/checks_publication_validators.py 11 KB runs code
- drift/checks_publication.py 31 KB runs code
- drift/checks.py 2.8 KB runs code
- drift/models.py 895 B runs code
- drift/orchestrator.py 7.5 KB runs code
- drift/README.md 3.0 KB
- drift/registry.py 3.2 KB runs code
- drift/runner.py 2.0 KB runs code
- exemplar_roster.py 11 KB runs code
- experiment_plan.py 6.0 KB runs code
- git_guards.py 21 KB runs code
- info.py 3.9 KB runs code
- installed_acceptance_artifacts.py 18 KB runs code
- installed_acceptance_runtime.py 8.1 KB runs code
- installed_acceptance_validation.py 18 KB runs code
- installed_acceptance_worker.py 15 KB runs code
- installed_acceptance.py 8.3 KB runs code
- installed_domain_acceptance.py 8.7 KB runs code
- installed_reference_oracle.py 5.9 KB runs code
- linking.py 4.5 KB runs code
- locked_dependency_export.py 7.5 KB runs code
- manuscript/98_symbols_glossary.md 189 B
- manuscript/AGENTS.md 1.2 KB
- manuscript/README.md 1.1 KB
- metadata.py 3.4 KB runs code
- native_format_library_custody.py 13 KB runs code
- native_linux_calibre_custody.py 13 KB runs code
- native_reader_runtime_custody.py 15 KB runs code
- package_discovery.py 1.2 KB runs code
- project_info.py 2.5 KB runs code
- promotion/__init__.py 1.1 KB runs code
- promotion/__main__.py 192 B runs code
- promotion/AGENTS.md 1.1 KB
- promotion/attestation.py 3.6 KB runs code
- promotion/cli.py 2.0 KB runs code
- promotion/composite.py 5.0 KB runs code
- promotion/models.py 2.7 KB runs code
- promotion/README.md 1.0 KB
- promotion/security_gate.py 9.6 KB runs code
- public_acceptance_auxiliary_bootstrap.py 4.2 KB runs code
- public_acceptance_auxiliary_cli.py 6.1 KB runs code
- public_acceptance_auxiliary_domains.py 34 KB runs code
- public_acceptance_auxiliary_native.py 28 KB runs code
- public_acceptance_auxiliary_parallel.py 5.7 KB runs code
- public_acceptance_auxiliary_pipeline_environment.py 8.0 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.
- 6d ago Changed 1e56f2f4d7fb
- 1mo ago First seen · 137 lines · 40 tokens per session scan A 1643edeafa2d
infrastructure-project is a skill published in the GitHub repository docxology/template (20 stars, last pushed yesterday), licensed Apache-2.0. It adds 40 tokens to every session and 910 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 2026-08-30.
Other skills, from other repositories
construction-trades-supervisor
Use when a task needs the judgment of a Construction Trades Supervisor (foreman) — allocating a crew's daily task assignments against a labor-unit budget, deciding whether today's scope requires a formally designated OSHA competent person, arbitrating a trade-sequencing conflict between crews needing the same physical…
architectural-engineering-manager
Use when a task needs the judgment of an Architecture/Engineering firm or department manager — pricing a project fee (lump sum vs. hourly vs. % of construction cost), staffing a project against backlog, evaluating scope creep on a fixed-fee job, managing professional liability exposure, or deciding whether to pursue a…
biomass-power-plant-manager
Use when a task needs the judgment of a Biomass Power Plant Manager — running a biomass-fired power generation facility, managing fuel supply logistics and quality variability, evaluating combustion/efficiency problems, or balancing generation output against fuel cost and emissions constraints.
chief-executive
Use when a task needs the judgment of a CEO/chief executive — setting company strategy, allocating scarce resources (capital, headcount, attention) across competing priorities, making a call that only the top of the org can make, or communicating direction to the board, investors, or the whole company.
clinical-research-coordinator
Use when a task needs the judgment of a Clinical Research Coordinator — managing patient recruitment/enrollment against a trial's screen-fail rate, handling a protocol deviation, tracking informed consent and regulatory documentation, or coordinating a multi-visit study schedule against patient retention risk.
compensation-benefits-manager
Use when a task needs the judgment of a Compensation and Benefits Manager — designing or evaluating a pay structure/leveling system, benchmarking compensation against market, deciding on a benefits package tradeoff, or auditing for pay equity issues. Narrower and more specialized than the broader hr-people-manager…