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 skills add nweii/agent-stuff --skill obsidian-log-commitsgit clone --depth 1 https://github.com/nweii/agent-stuffWrote 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/nweii/agent-stuff/obsidian-log-commits)<a href="https://agentmods.dev/skills/nweii/agent-stuff/obsidian-log-commits"><img src="https://agentmods.dev/badge/skills/nweii/agent-stuff/obsidian-log-commits.svg" alt="Measured on agentmods" 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 | $0.00063 | $0.00817 |
| Opus 5 | $0.00032 | $0.00409 |
| Sonnet 5 | $0.00013 | $0.00163 |
| Haiku 4.5 | $0.00006 | $0.00082 |
Grade A, and why
obsidian-log-commits 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 7d 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fetches GitHub commits for the target date, filters to meaningful work, and inserts bullets into the ## Log section of the corresponding daily note.
1. Determine target date
- If
$ARGUMENTSprovides a date (YYYY-MM-DD), use it. - Otherwise default to today.
- Identify the corresponding daily note path:
01-Days/YYYY-MM-DD-ShortDayName.md(e.g.01-Days/2026-04-02-Thu.md).
2. Discover repos to check
Use the GitHub CLI or API to discover repos dynamically rather than relying on a hardcoded list:
- List personal repos:
gh repo list <username> --limit 50 - List orgs:
gh api /user/orgs→ for each org, list repos:gh repo list <org> --limit 50
Check all discovered repos for commits on the target date. Run in parallel where possible.
3. Filter commits
Keep only commits that represent real intentional work. Discard:
- Automated or scheduled commits — messages matching patterns like
vault backup:,daily config backup,chore: daily,Merge pull request(unless the PR merge message itself is meaningful) - Dependency bumps with no context (e.g. bare
chore(deps): bump X)
Group remaining commits by repo.
4. Synthesize log bullets
For each repo with meaningful commits, write one bullet summarizing the day's work in that repo. Do not list every commit message verbatim — synthesize into a brief, readable description.
Format: - [wikilinks if applicable] — [description]
Wikilinks: If you can identify a project note in the vault that corresponds to this repo (from CLAUDE.md context, STATUS.md, or note titles), include it as a wikilink. If the repo maps to multiple project notes, include both. If you can't identify a match, omit wikilinks and just describe the work.
Example:
- [[Project Alpha]] / [[Work notes]] — routing architecture refactor, component extraction, form modularization
- [[My side project]] — added new skill
5. Insert into the daily note
Read the daily note. Locate the ## Log - [DayName] section. Insert the bullets at the end of that section, immediately before the next ## heading (or before EOF if no subsequent heading exists). Do not append to the end of the file.
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.
- 7d ago First seen · 72 lines · 63 tokens per session scan A 3b6c3c8f0aa5
obsidian-log-commits is a skill published in the GitHub repository nweii/agent-stuff (9 stars, last pushed 19d ago), licensed MIT. It adds 63 tokens to every session and 817 once invoked, about $0.0003 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 skills, from other repositories
checkpoint-management
Git-backed state management for safe rollback. Create and restore checkpoints with tagged commits and metadata tracking.
review-gate
Use before an agent-produced diff is committed, pushed, opened as a PR, merged, landed, or applied to user files when explicit implementation approval is missing. Trigger for review gate, review pack, approve before landing, diff first then land, human approval, merge gate, commit gate, push gate, or PR readiness.…
push-all
Use when the user explicitly asks to stage all current changes, create a commit, and push to the remote after safety checks.
night-watch
Autonomous maintenance (dep updates, dead code, small refactors) in isolated branch, off-hours. Triggers: night watch, autonomous maintenance, dep updates.
what-did-i-get-done
Summarize authored commits over a user-specified time period into a concise update.
claude-code-bash-patterns
Claude Code Bash tool patterns with hooks, automation, git workflows. Use for PreToolUse hooks, command chaining, CLI orchestration, custom commands, or encountering bash permissions, command failures, security guards, hook configurations.