Borrowing it
Nothing to install: this file belongs to ABO896/obsidian-university-workflow. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ABO896/obsidian-university-workflow/main/.claude/commands/improve-templates.mdgit clone --depth 1 https://github.com/ABO896/obsidian-university-workflowWrote 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/commands/abo896/obsidian-university-workflow/improve-templates)<a href="https://agentmods.dev/commands/abo896/obsidian-university-workflow/improve-templates"><img src="https://agentmods.dev/badge/commands/abo896/obsidian-university-workflow/improve-templates/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/commands/abo896/obsidian-university-workflow/improve-templates"><img src="https://agentmods.dev/badge/commands/abo896/obsidian-university-workflow/improve-templates.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00048 | $0.01055 |
| Opus 5 | $0.00024 | $0.00528 |
| Sonnet 5 | $0.00010 | $0.00211 |
| Haiku 4.5 | $0.00005 | $0.00105 |
Grade A, and why
improve-templates 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are about to do a deep audit and improvement pass on this Obsidian Templater project. Follow every phase in order. Do not skip phases. Do not write any template code until Phase 2.
Phase 1 — Understand the Project
Read and analyse the entire project thoroughly:
- Read
CLAUDE.mdif it exists - Use Glob to find every file in the vault (
**/*.md,**/*.js,**/*.ts) - Read every template file (look in folders named
Templates,templates,_templatesor similar) - Read every user script (
.jsfiles in the scripts folder configured in Templater settings) - Read the README or any docs files
- Identify:
- The purpose and goal of this vault/project
- The folder structure and how it's organised
- Every template and what it does
- Every Templater user script and what it does
- Any patterns, workflows, or conventions used across templates
- Anything that looks broken, inconsistent, or overly complex
Summarise your findings before moving to Phase 2.
Phase 2 — Read the Full Templater Documentation
Read .claude/skills/templater-docs/templater-api.md in full using the Read tool.
Do not skip sections. Pay attention to:
- Every module:
tp.date,tp.file,tp.frontmatter,tp.system,tp.web,tp.app,tp.config,tp.hooks,tp.obsidian,tp.user - All function signatures and optional arguments
- All command types:
<% %>,<%* %>,<%+ %>and whitespace control-%><%- - User script patterns (CommonJS exports, passing
tpas argument) - The
tRoutput variable and how to use it - The
tp.hooks.on_all_templates_executedpattern - Dynamic commands and their known limitations
Do not proceed to Phase 3 until you have read the full PDF.
Phase 3 — Audit All Templates
Go through every template one by one. For each template, check:
Raw JS that should be Templater API:
- Any
new Date()→ should betp.date.now() - Any
window.prompt()orprompt()→ should beawait tp.system.prompt() - Any
fetch()or manual HTTP → should beawait tp.web.request() - Any manual frontmatter parsing → should be
tp.frontmatter.key - Any
app.*calls → should usetp.app.* - Any
moment()calls that could betp.date.*
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 First seen · 110 lines · 48 tokens per session scan A f6cf33001676
improve-templates is a command published in the GitHub repository ABO896/obsidian-university-workflow (23 stars, last pushed 1mo ago), licensed MIT. It adds 48 tokens to every session and 1,055 once invoked, about $0.0002 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 2026-08-30.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.