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 commands/djrhails/dotfiles/merge-dependabotgit clone --depth 1 https://github.com/DJRHails/dotfilesWrote 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/djrhails/dotfiles/merge-dependabot)<a href="https://agentmods.dev/commands/djrhails/dotfiles/merge-dependabot"><img src="https://agentmods.dev/badge/commands/djrhails/dotfiles/merge-dependabot.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 | $0.00000 | $0.04624 |
| Opus 5 | $0.00000 | $0.02312 |
| Sonnet 5 | $0.00000 | $0.00925 |
| Haiku 4.5 | $0.00000 | $0.00462 |
Grade A, and why
merge-dependabot 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 4d 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 — 590 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Merge Dependabot PRs
@source https://github.com/trailofbits/claude-code-config @description Evaluate and merge dependabot PRs with parallel builds, dependency-aware batching, and transitive dep analysis. @arguments $REPO: GitHub org/repo (e.g., trailofbits/algo). $OPTIONS: Optional flags — "--skip-config-audit" skips Phase 0 (use in batch runs where config audit is a separate pass).
Clone $REPO if not already available locally:
gh repo clone $REPO /tmp/depbot-eval-$(echo "$REPO" | tr '/' '-') -- --depth=50 2>/dev/null || \
(cd /tmp/depbot-eval-$(echo "$REPO" | tr '/' '-') && git fetch origin)
Work from /tmp/depbot-eval-{repo-slug} for all subsequent phases.
Shared-repo guard: before anything that posts to GitHub
(approving, commenting, opening PRs, or merging), determine
whether $REPO is a solo personal repo — owned by
github.com/DJRHails with no other collaborators (check:
gh api repos/<owner>/<repo>/collaborators --jq length returns 1).
On solo personal repos, run fully autonomously. On any other repo (a
shared org, or any repo with other collaborators), pause before
each such action, post a short summary of what you are about to
send or merge, and wait for explicit user confirmation. --admin
merges are allowed only on solo personal repos — never pass
--admin on a shared repo.
Execute every phase below sequentially without pausing for confirmation, except where the shared-repo guard requires it.
Turn Budget Management
If you are running as a background agent with a max_turns cap:
- At 75% of turns used: Stop launching new evaluations. Merge any PRs already evaluated as PASS. Skip Phase 5's detailed reports — print only the summary table.
- At 90% of turns used: Immediately print whatever summary you have and stop. Do not start new evaluations or re-tests.
- Prioritize merging over analysis. If you must choose between thorough analysis of the last PR and merging already-evaluated PASS PRs, merge first.
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.
- 4d ago First seen · 590 lines · 0 tokens per session scan A 23e8fa7efc3f
merge-dependabot is a command published in the GitHub repository DJRHails/dotfiles (2 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,624 tokens. 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 commands, from other repositories
commit
Follow the Commit messages rule in the repository AGENTS.md when present; otherwise use the Conventional Commits 1.0.0 summary below.
team
Route a task to the right AI team + member (two-level team→member selection).
sync
Stage, commit, and push pending changes via the gss skill in one guided flow.
ssh-find
Find an SSH host on the local network and update /.ssh/config with its current IP.
gss
Git Safe Sync (gss) status and help.
push-commit
Create a new commit from the current repo changes and push it.