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 baristaze/swe_guidelines --skill reviewgit clone --depth 1 https://github.com/baristaze/swe_guidelinesWrote 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/baristaze/swe_guidelines/review)<a href="https://agentmods.dev/skills/baristaze/swe_guidelines/review"><img src="https://agentmods.dev/badge/skills/baristaze/swe_guidelines/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/baristaze/swe_guidelines/review"><img src="https://agentmods.dev/badge/skills/baristaze/swe_guidelines/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 | $0.00033 | $0.02654 |
| Opus 5.5 | $0.00013 | $0.01062 |
| Sonnet 5.5 | $0.00007 | $0.00531 |
| Haiku 4.5 | $0.00003 | $0.00265 |
Grade A, and why
arch-review-{group} 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.
Copies of this mod
7 near-identical copies found in the catalogue:
- arch-review-storage — 97% identical, 14 lines differ
- arch-review-contracts — 92% identical, 14 lines differ
- arch-review-om — 92% identical, 14 lines differ
- arch-review-delivery — 91% identical, 14 lines differ
- arch-review-async — 91% identical, 14 lines differ
- arch-review-context — 89% identical, 14 lines differ
- arch-review-network — 89% identical, 14 lines differ
How it starts
The opening of the file, as written. The whole thing — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.
arch-review-{group}
Judge the code from one perspective only: the lenses in
../../lenses/{group}.md. Other perspectives have their own skills; do
not borrow their rules, and do not flag anything a lens in this file
does not name. The guideline itself is at ../../architecture.md when a
lens needs its source read in full. A path that starts with ../ is
read from this skill's folder as realpath resolves it. If either file
is missing, stop and say the installation is incomplete.
This pass covers {covers}.
Input
The arguments name what to review. Read them as the first of these that matches:
- Empty: the current branch's change. The default branch is
origin/HEADwhen set, elsemain, elsemaster. The scope is every file changed since the merge base ofHEADand the default branch (git diff --name-only <base>, committed and uncommitted alike), plus every untracked file git does not ignore (git status --porcelain --untracked-files=all). When there is no merge base (no default branch, a shallow clone, or unrelated histories), the scope is the uncommitted change againstHEADplus the untracked files, and the Scope line says the merge base was not found. In a repository with no commit, it is every file not ignored, listed asalllists them. - The word
all: every file in the repository that git does not ignore, tracked or untracked (git ls-files --cached --others --exclude-standard). Expect this to take a while. - A range (
main..HEAD,main...HEAD): the files that range changes, read as they are at its end. - A commit that
git rev-parse --verify --quiet "<arg>^{commit}"resolves (a SHA, a tag, a branch): the change that commit made, against its first parent. - A path or a glob: every file under it as it is now, untracked files
included
(
git ls-files --cached --others --exclude-standard -- <path>). A path that does not exist is an error; say so and stop. A name that is both a commit and a path reads as the commit; write./<name>for the path.
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 Changed · +9 lines 7ff80f9df79c
- 16d ago Changed · +28 lines 615f085bef77
- 24d ago Changed · +39 lines · -13 tokens per session 147b9337a1d8
- 25d ago Changed · +37 lines 08d11cd0a3ab
- 26d ago First seen · 92 lines · 46 tokens per session scan A 8616bb48e81e
arch-review-{group} is a skill published in the GitHub repository baristaze/swe_guidelines (94 stars, last pushed today), licensed MIT. It adds 33 tokens to every session and 2,654 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 2026-09-20.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…