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/dsswift/ionWrote 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/dsswift/ion/resolve-dependabot-prs)<a href="https://agentmods.dev/commands/dsswift/ion/resolve-dependabot-prs"><img src="https://agentmods.dev/badge/commands/dsswift/ion/resolve-dependabot-prs/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/dsswift/ion/resolve-dependabot-prs"><img src="https://agentmods.dev/badge/commands/dsswift/ion/resolve-dependabot-prs.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 | $0.00035 | $0.02273 |
| Opus 5.5 | $0.00014 | $0.00909 |
| Sonnet 5.5 | $0.00007 | $0.00455 |
| Haiku 4.5 | $0.00003 | $0.00227 |
Grade A, and why
resolve-dependabot-prs 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 20d 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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are running the /resolve-dependabot-prs command. Your job is a two-phase workflow:
- Analyze (read-only) — enumerate the repo's open Dependabot PRs, assess each (scope, bump, CI, risk), decide a merge/close order, and emit a terse summary table to the user.
- Plan (enter planning mode) — write a resolution plan whose steps ARE the executable sequence (rebase → merge → optional follow-up PR → resume the chain → close-for-High), ordered per the analysis. The user reviews and approves the plan through the normal plan-approval flow; the agent executes it afterward.
The user drives the loop and approves the plan. This command does not merge, rebase, close, comment, commit, or push anything. It analyzes, summarizes, and produces a reviewable plan.
Hard rules.
- During the analysis pass and during planning: no merge, no rebase, no
gh pr comment, no commit, no push, no source edits. Analysis is read-only; planning only writes the plan file. - User-facing output is intentionally terse: a single "Running the Dependabot PR analysis…" notice, then the summary table, then the short special-case blurb. No lecture. No per-PR prose for trivial bumps. The plan artifact carries all execution detail.
- The actual rebase / merge / close / follow-up steps are written into the plan, not performed by this command. They execute only after the user approves the plan.
- If there are zero open Dependabot PRs, report "No open Dependabot PRs." and stop — do not enter planning mode.
Step 0: Announce
Emit exactly one short line to the user before doing the work:
Running the Dependabot PR analysis…
Do not narrate each command as you run it. The next thing the user should see is the summary table.
Step 1: Enumerate open Dependabot PRs
gh pr list --author "app/dependabot" --state open --json number,title,headRefName,labels,createdAt,url
Belt-and-suspenders: the Dependabot author handle can differ across repos. Also enumerate by the dependencies label and union the results:
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.
- 20d ago Changed · +1 lines 6b60997a55ab
- 1mo ago Changed · +1 lines 3f855691a523
- 1mo ago First seen · 159 lines · 35 tokens per session scan A c7127c653469
resolve-dependabot-prs is a command published in the GitHub repository dsswift/ion (4 stars, last pushed today), licensed MIT. It adds 35 tokens to every session and 2,273 once invoked, about $0.0001 per session on Opus 5.5. 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 commands, from other repositories
code-review
Review the current branch changes for bugs and style issues.
pr-manager
Comprehensive pull request management with ruv-swarm coordination for automated reviews, testing, and merge workflows.
pr-enhance
Command "pr-enhance" from shyftlabs/continuum, covering pr-enhance, usage, options, examples and enhance pr.
review-branch
Review the current branch's diff against base by dispatching atomic-reviewer. No orchestration loop, no spec required — pre-flight before /commit pr or /commit merge.
commit
Stage, commit, and optionally ship further. Pass an escalation token (push, pr, merge, squash, squash merge) to skip the prompt. With no token, commits then asks how far to ship. Delegates message format to the atomic-git-discipline skill.
pr-ready
Run the project's pre-commit review loop to determine whether the current branch is ready to push — lint, tests, parallel pr-review-toolkit agents plus an over-engineering audit, fix-and-re-run until convergence.