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 sramji/awesome-superpowers --skill finishing-with-reviewgit clone --depth 1 https://github.com/sramji/awesome-superpowersWrote 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/sramji/awesome-superpowers/finishing-with-review)<a href="https://agentmods.dev/skills/sramji/awesome-superpowers/finishing-with-review"><img src="https://agentmods.dev/badge/skills/sramji/awesome-superpowers/finishing-with-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/skills/sramji/awesome-superpowers/finishing-with-review"><img src="https://agentmods.dev/badge/skills/sramji/awesome-superpowers/finishing-with-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 | $0.00042 | $0.01588 |
| Opus 5 | $0.00021 | $0.00794 |
| Sonnet 5 | $0.00008 | $0.00318 |
| Haiku 4.5 | $0.00004 | $0.00159 |
Grade A, and why
finishing-with-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 12d 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.
Finishing With Review
Overview
Review-gated branch completion. Every branch gets reviewed before it merges — no exceptions.
Announce at start: "I'm using the finishing-with-review skill to review and complete this work."
Core principle: Implement → Review → Reflect → Finish. Code review happens while the code is fresh and there's still willingness to change it.
The Process
digraph finishing_with_review {
rankdir=TB;
request1 [label="Step 1: Request Code Review" shape=box];
receive1 [label="Step 2: Receive Code Review\n+ implement fixes" shape=box];
significant [label="Changes significant?" shape=diamond];
request2 [label="Step 1 (repeat):\nRequest Code Review" shape=box];
receive2 [label="Step 2 (repeat):\nReceive Code Review" shape=box];
reflect [label="Step 4: End-of-Session\nReflection" shape=box];
finish [label="Step 5: Finish Branch" shape=doublecircle];
request1 -> receive1;
receive1 -> significant;
significant -> request2 [label="yes"];
significant -> reflect [label="no"];
request2 -> receive2;
receive2 -> reflect;
reflect -> finish;
}
Step 1: Request Code Review
Invoke superpowers:requesting-code-review.
- Get the git range. Resolve the base branch robustly — this works on a fresh
repo with no remote, on
master/main/trunk, and warns rather than producing a garbage range if nothing resolves:
# >>> base-branch-detection >>>
set -euo pipefail
resolve_base_ref() {
# Echo a ref usable DIRECTLY in `git merge-base` — a remote-tracking ref when
# one exists (so a clone with origin/main but no local main still works), else
# a local branch. Never strips the remote prefix off a ref that needs it.
# Tier 1: the remote's declared default branch (remote-tracking ref, e.g. origin/main).
if git symbolic-ref -q refs/remotes/origin/HEAD >/dev/null 2>&1; then
git symbolic-ref --short refs/remotes/origin/HEAD
return 0
fi
# Tier 2: the current branch's configured upstream (remote-tracking ref).
if git rev-parse -q --verify '@{upstream}' >/dev/null 2>&1; then
git rev-parse --abbrev-ref '@{upstream}'
return 0
fi
# Tier 3: a conventional LOCAL branch, if one exists.
local b
for b in main master trunk; do
if git rev-parse -q --verify "refs/heads/$b" >/dev/null 2>&1; then echo "$b"; return 0; fi
done
return 1
}
# Guard every command substitution explicitly — `BASE_SHA=$(failing-cmd)` does NOT
# trip `set -e`, so a bad merge-base would otherwise leave BASE_SHA empty silently.
BASE_REF=""
if BASE_REF=$(resolve_base_ref) && [ -n "$BASE_REF" ] \
&& BASE_SHA=$(git merge-base HEAD "$BASE_REF" 2>/dev/null) && [ -n "$BASE_SHA" ]; then
: # resolved cleanly; BASE_REF + BASE_SHA are valid
else
echo "WARNING: could not resolve a base branch (BASE_REF='${BASE_REF:-<none>}'); review the full working tree manually." >&2
BASE_REF="${BASE_REF:-<none>}"
BASE_SHA=$(git rev-parse HEAD) # degrade safely: empty range, reviewer is warned
fi
HEAD_SHA=$(git rev-parse HEAD)
# <<< base-branch-detection <<<
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.
- 12d ago First seen · 161 lines · 42 tokens per session scan A 2728faee06b6
finishing-with-review is a skill published in the GitHub repository sramji/awesome-superpowers (3 stars, last pushed 2mo ago), licensed MIT. It adds 42 tokens to every session and 1,588 once invoked, about $0.0002 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
requesting-code-review
Use when completing tasks, implementing major features, or before merging to verify work meets requirements.
finishing-a-development-branch
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work.
receiving-code-review
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation.
using-git-worktrees
Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback.
requesting-code-review
Use when completing tasks, implementing major features, or before merging to verify work meets requirements.
comet-github-pr-review
A read-only review process for pull requests in Comet's GitHub repositories. A pull request is a proposed code change; the review checks its current code, related issue, comments, merge status, and automated checks.