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/comprehensive-assessmentWrote 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/comprehensive-assessment)<a href="https://agentmods.dev/skills/docxology/template/comprehensive-assessment"><img src="https://agentmods.dev/badge/skills/docxology/template/comprehensive-assessment/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/comprehensive-assessment"><img src="https://agentmods.dev/badge/skills/docxology/template/comprehensive-assessment.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 | $0.00077 | $0.00875 |
| Opus 5.5 | $0.00031 | $0.00350 |
| Sonnet 5.5 | $0.00015 | $0.00175 |
| Haiku 4.5 | $0.00008 | $0.00088 |
Grade A, and why
template-comprehensive-assessment 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 1mo 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Comprehensive assessment
Natural invoke
- "Audit the whole repo for template_active_inference, template_autoresearch_project, template_code_project, template_prose_project, and template_template" (example names only — the authoritative public roster is
docs/_generated/active_projects.md) - "Full health check — tests, docs, manuscript, pipeline"
- "What's broken across all active projects?"
Inputs to confirm
- Project(s) — names from
docs/_generated/active_projects.mdor "all active". - Scope — single project vs multi-project (one pytest process per project test dir).
Workflow
Work through:
-
Tests — appropriate pytest invocations; one project test dir per project. Coverage: infra ≥60%, project ≥90% unless CI exception. No mocks (
docs/rules/testing_standards.md). -
Architecture — thin orchestrators in
scripts/; algorithms inprojects/<n>/src/orinfrastructure/. No cross-project imports. -
Documentation — meaningful dirs have accurate AGENTS.md + README.md; links resolve; link
_generated/active_projects.md, do not duplicate roster. -
Manuscript — Pandoc-crossref +
.bib→docs/guides/manuscript-semantics.md. Registrylabels.yaml+[[FIG:]]→ manuscript-cross-references. Validate markdown; PDF/logs if outputs exist. -
Pipeline — core vs full DAG, optional LLM stages, copy to
output/<name>/per CLAUDE.md / RUN_GUIDE.
Deliverables
- Executive summary (pass/fail per area).
- Concrete issues: path, symptom, suggested fix.
- Commands run + raw exit status.
- Do not invent coverage percentages.
Verification commands
uv sync
uv run pytest projects/<project>/tests/ --cov=projects/<project>/src --cov-fail-under=90 -q
uv run pytest tests/infra_tests/ --cov=infrastructure --cov-fail-under=60 -q
uv run python scripts/pipeline/stage_01_test.py --project <project>
uv run python -m infrastructure.validation.cli markdown projects/<project>/manuscript/
uv run python -m infrastructure.validation.cli prerender projects/<project>/manuscript --repo-root .
What ships with it
5 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.
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.
- 1mo ago First seen · 79 lines · 77 tokens per session scan A 946a5cbc111a
template-comprehensive-assessment is a skill published in the GitHub repository docxology/template (20 stars, last pushed today), licensed Apache-2.0. It adds 77 tokens to every session and 875 once invoked, about $0.0003 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
shipjaw-challenge
Optional full adversarial ritual for locking a Shipjaw phase plan, ADR, or tech/product decision — durable challenge-report.md via proposer vs challenger (prefer a separate subagent). Use when the user runs /shipjaw-challenge, challenge this plan, wants a written challenge report, locking a meaty phase, contester ce…
karpathy-guidelines
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.
improve-codebase-architecture
Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
adr-review
Review an ADR the user has written in docs/adr/. Use when the user says an ADR is ready for review or asks for feedback on a decision record. Never use this to write or rewrite an ADR for them.
code-review
Use before merging a diff. A structured review pass for correctness bugs, safety issues, and needless complexity.
review-work
Post-implementation gate review: run manual QA on the real surface yourself, then launch ONE gate reviewer (never a panel) to audit goal, constraints, code quality, security, missed context, and QA evidence. Use before a PR handoff or when the user explicitly asks to review completed work.