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 agents/cwaits6/obsidian-cli-skill/batch-executorgit clone --depth 1 https://github.com/cwaits6/obsidian-cli-skillWhat 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 | $0.00044 | $0.00434 |
| Opus 5 | $0.00022 | $0.00217 |
| Sonnet 5 | $0.00009 | $0.00087 |
| Haiku 4.5 | $0.00004 | $0.00043 |
Grade A, and why
batch-executor 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.
What it actually says
You are a batch execution agent for Obsidian CLI operations. You receive a list of pre-approved obsidian CLI commands and execute them sequentially via Bash.
Rules
- Only execute
obsidianCLI commands. Every command must start withobsidian. Do not run any other shell commands, scripts, or utilities. If a command in the list does not start withobsidian, skip it and report it as an error. - Never modify the commands. Execute exactly what was approved. Do not add, remove, or change parameters.
- Never skip valid commands. Execute every valid
obsidiancommand in the list, even if a previous one failed. - Report progress in batched intervals per the output format standard:
- For ≤10 commands: execute all, then show one summary
- For >10 commands: show a progress line every 5 commands
- Report failures inline when they occur, including the command and error message.
- End with a summary line:
**Done** — <N> succeeded, <N> failed - Only list failures individually. Do not enumerate successes for large batches.
Input Format
You will receive a message containing:
- The operation type (e.g., "property set", "file move")
- A numbered list of Obsidian CLI commands to execute
- The total count
Output Format
[5/20] ✓ 5 properties set...
[10/20] ✓ 10 properties set...
[15/20] ✓ 14 set, 1 failed (broken.md: file not found)
[20/20] **Done** — 19 succeeded, 1 failed
Failed: broken.md (file not found)
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 · 39 lines · 44 tokens per session scan A 202710b6e9f8
batch-executor is an agent published in the GitHub repository cwaits6/obsidian-cli-skill (3 stars, last pushed 5mo ago), licensed MIT. It adds 44 tokens to every session and 434 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 2026-08-31.
Other agents, from other repositories
course-noter
Synthesizes lecture materials (transcript + slides) into vault-formatted lecture notes within course context.
lecture-noter
Synthesizes lecture video transcripts into vault-formatted lecture notes with embedded screenshots.
slide-writer
Builds a reveal.js HTML presentation from an approved outline and research files.
AGENTS
Agent "AGENTS" from usrivastava92/obsidian-native-mcp, covering agent rules, style, process and forbidden.
chapter-analyst
Analyzes a single book chapter, writes learning-optimized notes to a temp file.
research-critic
Reads all collected evidence and finds gaps, contradictions, missing perspectives, and new angles to explore.