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/dsnger/dev-workflow-kit/process-pr-reviewgit clone --depth 1 https://github.com/dsnger/dev-workflow-kitWhat 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 | $0.00014 | $0.03002 |
| Opus 5 | $0.00007 | $0.01501 |
| Sonnet 5 | $0.00003 | $0.00600 |
| Haiku 4.5 | $0.00001 | $0.00300 |
Grade A, and why
process-pr-review 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 2d 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 — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Process the reviewer comments on PR $ARGUMENTS (no number given → the PR of the
current branch, via gh pr view).
Target model: Claude via Claude Code.
Step 0 — Load this project's bot matrix
Read docs/pr-review-bots.md. Its Routing lists are the authority — the table
beside them is descriptive, recording where each bot's findings have been seen and how
you know it has finished. A bot sits in one of three categories: wait for it (it has
a completion signal you can block on), process it opportunistically (it produces
real findings but nothing proves it has finished), or ignore it. A bot's channel can vary between PRs, so a row may
honestly read inconsistent; that is an observation, never a routing instruction.
Getting this wrong is expensive in both directions: waiting on a channel a bot never uses hangs the loop forever, and treating a findings source as context silently drops real findings.
If docs/pr-review-bots.md is missing: do not guess the matrix. Run
gh pr view --json comments,reviews to see which bots have actually posted on this
PR, process only what is visibly there, and tell the user to run
/dev-workflow:workflow-init (or write the file by hand) so the next run can wait
on the right bot.
Step 1 — Check CI first
gh pr checks. The required, branch-protected quality check must be green — a red
required check makes the PR unmergeable regardless of review outcomes, and the
failure is itself a finding to process. If it is red, fix the failing step before
processing bot comments. If it is still running, note it and proceed — re-verify at
the end.
Step 2 — Wait for the findings bots
Block only on the bots under Wait for, using the completion signal its row names — which may be a status check rather than a comment, since a bot that finds nothing can finish without posting at all. Waiting for a post from a zero-finding bot hangs.
Then, without blocking, read whatever each Process opportunistically bot has posted at that moment — both channels, inline comments and the PR-level summary body. If one posts after you have begun, handle it as a follow-up rather than waiting for it up front.
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.
- 2d ago First seen · 212 lines · 14 tokens per session scan A ad1d4218db2e
process-pr-review is a command published in the GitHub repository dsnger/dev-workflow-kit (5 stars, last pushed 6d ago), licensed MIT. It adds 14 tokens to every session and 3,002 once invoked, about $0.0001 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 commands, from other repositories
brooks-audit
Run a Brooks-Lint architecture audit.
simplify
The over-engineering review: five tags (delete, stdlib, native, yagni, shrink), a mandatory replacement per finding, and a real null result when there is nothing to cut.
git
The pre-finish status: branch, hygiene findings, message checks, workflow lint, template state.
init
Install the formatters this repository needs, with every command visible before it runs.
VibeGuard: ExecPlan
Long-term task execution plan — generates self-contained execution documents from SPEC, supports cross-session recovery.
VibeGuard: Review
Structured code review - first run the guard to obtain the baseline, then review according to security → logic → quality → performance priority.