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 steph-dove/klaussy-agents --skill fastapi-address-reviewgit clone --depth 1 https://github.com/steph-dove/klaussy-agentsWrote 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/steph-dove/klaussy-agents/fastapi-address-review)<a href="https://agentmods.dev/skills/steph-dove/klaussy-agents/fastapi-address-review"><img src="https://agentmods.dev/badge/skills/steph-dove/klaussy-agents/fastapi-address-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/steph-dove/klaussy-agents/fastapi-address-review"><img src="https://agentmods.dev/badge/skills/steph-dove/klaussy-agents/fastapi-address-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 | $0.00062 | $0.02045 |
| Opus 5 | $0.00031 | $0.01022 |
| Sonnet 5 | $0.00012 | $0.00409 |
| Haiku 4.5 | $0.00006 | $0.00204 |
Grade A, and why
fastapi-address-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.
Copies of this mod
1 near-identical copy found in the catalogue:
- httpx-address-review — 97% identical, 2 lines differ
How it starts
The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Address the review feedback on the current PR. Every comment gets a response: a change, or a reasoned reply explaining why not. Don't silently skip any.
Phase 1: Gather the feedback
- Get the review comments. If
ghis available, pull them for the current branch's PR:gh pr view --json reviews,commentsandgh api repos/{owner}/{repo}/pulls/<n>/commentsfor inline (line-level) comments. Ifghisn't available or there's no PR, ask the user to paste the feedback. - Read CLAUDE.md and any
.claude/rules/*.mdcovering the touched files — a fix must still satisfy the repo's conventions. - Build the change list. For each comment, capture: the file/line, what's asked, and the reviewer's intent (not just the literal words). Group comments that touch the same code so you fix each spot once.
Phase 2: Triage each comment
Sort every comment into one of:
- Accept & fix — a real issue or a clear improvement. Most comments.
- Accept with a different fix — the concern is valid but the reviewer's suggested change isn't the best one; do the better fix and say why in the reply.
- Discuss / decline — you believe the current code is correct, or the change is out of scope. This is legitimate, but it requires a specific, respectful reason, not a dismissal. When unsure whether to decline, ask the user rather than deciding unilaterally.
State the triage before editing, so the user can redirect if they disagree.
Phase 3: Apply the changes
- Make each accepted change as a minimal, targeted edit — fix what the comment raised, don't refactor around it.
- Check for siblings. If a comment points at a pattern (not just one line), grep for the same pattern elsewhere in the diff and fix those too, unless the reviewer scoped it to the one spot.
- Re-verify after editing — run the tests/lint from CLAUDE.md. A fix that breaks the suite isn't done.
- Keep the changes reviewable. One logical follow-up; don't fold in unrelated work that a re-review would have to untangle.
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 · 78 lines · 62 tokens per session scan A fa09a826c129
fastapi-address-review is a skill published in the GitHub repository steph-dove/klaussy-agents (16 stars, last pushed 15d ago), licensed MIT. It adds 62 tokens to every session and 2,045 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
gh-find-prs
Survey open Codewhale PRs and triage each for mergeability and disposition against the real landing branch.
hunk-extensions
Maps the hunkdiff/extension authoring surface for Hunk, the terminal diff viewer — hiding or reordering reviewed files, docked panes, alternate file views, commands and key bindings, dialogs, workspace writes, themes, syntax languages, VCS backends, lifecycle events. Use when writing, debugging, or installing a Hunk…
hunk-launch-video
Produces Hunk videos by driving the real TUI headlessly in a PTY, compositing captioned 1080p frames in Chromium, and encoding with ffmpeg. Use for feature demos, workflow explainers, announcements, launch videos, and full-release roundups.
hunk-release
Prepares, publishes, verifies, and curates Hunk releases. Use for release metadata, benchmarks, tags, publishing, release videos, backports, or recovery.
git
Git and code hosting platform management — GitHub, GitLab, Codeberg, Forgejo. Zero barrier — install x-cmd and manage repos from the terminal. Use for "git", "github", "gitlab", "repo", "pull request", "code hosting".
vhs-e2e-gif
Record a test run, a TUI session, or any terminal command as a GIF with VHS and attach it to a GitHub PR as a release-hosted asset, never a repo commit. Use when asked to record an e2e run, demo a fix on a PR, attach a GIF or screen recording to a pull request, show a test passing visually, or produce a terminal…