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/jpeseWang/solo-dev-workflowWrote 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/jpesewang/solo-dev-workflow/review)<a href="https://agentmods.dev/commands/jpesewang/solo-dev-workflow/review"><img src="https://agentmods.dev/badge/commands/jpesewang/solo-dev-workflow/review/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/jpesewang/solo-dev-workflow/review"><img src="https://agentmods.dev/badge/commands/jpesewang/solo-dev-workflow/review.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 | $0.01286 |
| Opus 5.5 | $0.00000 | $0.00514 |
| Sonnet 5.5 | $0.00000 | $0.00257 |
| Haiku 4.5 | $0.00000 | $0.00129 |
Grade A, and why
review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review my changes
Self-review the uncommitted diff from three angles before committing. Findings only — no auto-fix unless asked.
A second pair of eyes on the code you just wrote, before /commit. The risk in solo work
is that nobody else ever reads the diff — this command is that reader. Output is a concrete
findings list; you decide what to fix.
Input: an optional scope.
- none → the uncommitted diff (staged + unstaged + untracked)
staged→ only staged changesHEAD~N→ the last N commits on this branch<sha>..<sha>→ a specific range
Step 1 — Gather the diff
ARG="${1:-}"
if [ -z "$ARG" ]; then
SCOPE="uncommitted"
git diff --staged > /tmp/review.patch
git diff >> /tmp/review.patch
for f in $(git ls-files --others --exclude-standard); do
printf -- '--- /dev/null\n+++ b/%s\n' "$f" >> /tmp/review.patch
sed 's/^/+/' "$f" >> /tmp/review.patch
done
elif [ "$ARG" = "staged" ]; then
SCOPE="staged"; git diff --staged > /tmp/review.patch
elif [[ "$ARG" =~ ^HEAD~ ]]; then
SCOPE="$ARG"; git diff "$ARG..HEAD" > /tmp/review.patch
else
SCOPE="$ARG"; git diff "$ARG" > /tmp/review.patch
fi
echo "[SCOPE] $SCOPE"
If the diff is empty: print No changes to review. and stop.
For any file changed by more than ~20 lines, read the whole file, not just the patch. Reviewing a patch without context produces false positives.
Step 2 — Review from three angles
Examine the diff three times, each with a different hat. (If your tool can run sub-agents in parallel, run these three concurrently; otherwise do them in sequence.) Every finding must carry file:line + why it's a problem + a concrete fix.
1. Logic auditor — find real bugs: null/undefined dereferences, unhandled edge cases (empty/zero/negative/boundary), races and stale closures, swallowed or missing error handling, off-by-one, wrong state updates, type assertions that can be false at runtime.
2. Design critic — find architecture/consistency issues:
names that fight the codebase convention, logic duplicated from elsewhere (grep to confirm),
business logic stuffed into a UI/handler layer, a new pattern that clashes with the existing
one in the same area, leaky module boundaries, weak types (any, casts hiding a real type).
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.
- 2mo ago First seen · 126 lines · 0 tokens per session scan A 4f6750d7dc69
review is a command published in the GitHub repository jpeseWang/solo-dev-workflow (2 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,286 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
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.
refactor
Systematic code refactoring with smart scope detection.
init
Install the formatters this repository needs, with every command visible before it runs.
spec-trace-requirements
You are verifying that implementation changes trace back to specification requirements.
merge-conflict-analysis
You are analyzing merge conflicts for PR #${{ pr-number }}.
boot
Start a new PromptKit prompt assembly session (alias for /bootstrap).