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.
git clone --depth 1 https://github.com/cwaits6/obsidian-cli-skillWrote 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/cwaits6/obsidian-cli-skill/obsidian-qa)<a href="https://agentmods.dev/commands/cwaits6/obsidian-cli-skill/obsidian-qa"><img src="https://agentmods.dev/badge/commands/cwaits6/obsidian-cli-skill/obsidian-qa/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/cwaits6/obsidian-cli-skill/obsidian-qa"><img src="https://agentmods.dev/badge/commands/cwaits6/obsidian-cli-skill/obsidian-qa.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 | $0.00000 | $0.02070 |
| Opus 5.5 | $0.00000 | $0.00828 |
| Sonnet 5.5 | $0.00000 | $0.00414 |
| Haiku 4.5 | $0.00000 | $0.00207 |
Grade B, and why
obsidian-qa scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
SKILL_VERSION=$(grep '"version"' ~/.claude/plugins/marketplaces/obsidian-cli-skill/plugins/obsidian-cli/.claude-plugin/plugin.json 2>/dev/null | head -1 | grep -o '"[^"]*"' | tail -1 | tr -d '"' || echo "unknown") How it starts
The opening of the file, as written. The whole thing — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run the full Obsidian CLI QA harness. Tests run directly against the registered test vault so the Obsidian CLI can operate against it. Results are snapshotted into a timestamped report dir at the end, then the fixture is restored via git.
Run only after the latest skill version is installed.
Setup
TIMESTAMP=$(date +%Y-%m-%d-%H%M)
REPORT_DIR="$(pwd)/qa/reports/qa-$TIMESTAMP"
mkdir -p "$REPORT_DIR"
VAULT_PATH="$(pwd)/qa/fixtures/test_vault"
CONFIG_PATH="$(pwd)/qa/fixtures/config.yaml"
SKILL_VERSION=$(grep '"version"' ~/.claude/plugins/marketplaces/obsidian-cli-skill/plugins/obsidian-cli/.claude-plugin/plugin.json 2>/dev/null | head -1 | grep -o '"[^"]*"' | tail -1 | tr -d '"' || echo "unknown")
Copy the example config and set vault_path to the test vault:
cp plugins/obsidian-cli/config.yaml.example "$CONFIG_PATH"
# Set vault_path to VAULT_PATH in config.yaml
The fixture vault at qa/fixtures/test_vault is registered with Obsidian, so CLI commands
will actually persist to disk. All tests modify this vault directly. After the run, the fixture
is restored.
Phase 1 — Parallel Tests
Launch all of the following in parallel using the Task tool with general-purpose subagents.
Each subagent invokes the obsidian-cli skill, auto-approves any proposals, and returns a
completion marker with a brief summary.
These tests touch different parts of the vault and can safely run at the same time.
T1 — Enrich Inbox
Invoke the obsidian-cli skill:
"Set frontmatter on everything in my Inbox folder — assign type and topic based on each note's content. My config is at
<CONFIG_PATH>"
Auto-approve the proposal. If any CLI command fails, do not write files directly — report the
exact CLI error and return [T1_FAIL]. Return [T1_COMPLETE] only if all changes were applied
via the Obsidian CLI, with each file and the type/topic assigned.
T2 — Create Daily Template
Invoke the obsidian-cli skill:
"Create a daily note template with date, tags, and a section for notes of the day. My vault is at
<VAULT_PATH>"
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 · 244 lines · 0 tokens per session scan B 362ec450feb7
obsidian-qa is a command published in the GitHub repository cwaits6/obsidian-cli-skill (3 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,070 tokens. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
fec-plan
Unified front-end planning entrance - implementation/architecture plan or testing strategy. The implementation path is taken by default; when the user clearly wants test plan, coverage matrix, test layering, risk-to-test, etc., the complete test strategy is output.
fec-tdd
Use front-end TDD workflow to implement functions, fix bugs, or refactor logic: first write failing tests, then implement minimal code, and then refactor.
bug
Reproduce then TDD-fix a ready-for-agent bug ticket in this checkout. Web bugs get a browser repro first.
qa
Smoke or browser-walk a running app. Report only. Do not implement. Do not merge.
ttest
CLI testing in isolated tmux sessions.
tt
CLI testing in isolated tmux sessions, short for /ar:ttest.