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 skills/huggingface/diffusers/self-reviewnpx skills add huggingface/diffusers --skill self-reviewgit clone --depth 1 https://github.com/huggingface/diffusersWhat 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 | $0.00088 | $0.00701 |
| Opus 5 | $0.00044 | $0.00351 |
| Sonnet 5 | $0.00018 | $0.00140 |
| Haiku 4.5 | $0.00009 | $0.00070 |
Grade A, and why
self-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 yesterday.
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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Self-review
Runs the same rubric as the @claude CI reviewer, so you catch issues before a
maintainer does — but over your whole PR diff. (The CI scopes itself to
src/diffusers/, tests/, and .ai/; for your own PR, also review your docs
and scripts.) You're already on the branch with the conventions loaded, so: get
the
diff → review it against the rubric → report → iterate with the contributor
until it's ready, then remind them to share the final notes on the PR.
1. Get the diff
git diff main...HEAD # use your target branch if not main
If the branch trails main and the diff looks polluted with unrelated merged
files, scope to your own commits: git log main..HEAD --oneline, then
git show <commit>.
2. Read the rubric
references/review-rules.md is the canonical rubric (the CI pins it from main) — read
it and review against it; don't rely on a remembered copy. For the areas you
touched, also read references/code_style.md, references/models.md, references/pipelines.md,
references/modular.md, references/testing.md, or references/pitfalls.md.
3. Report
- Blocking issues — numbered. Each: title → explanation →
file.py:line→ impact. Cite the rule, e.g. Perreferences/models.md: "…only keep the inference path." - Non-blocking issues — same format, lower severity.
- Dead code (advisory) — a table:
path:line· Likely-dead / Used · reason. - Summary — short synthesis and a verdict (READY / NEEDS CHANGES),
spelling out:
- Fix before submitting — all blocking issues, and remove the flagged dead code.
- Leave for the actual review — non-blocking issues that aren't obviously correct; raise these with the reviewer rather than guessing at them now.
Report only — do not edit files. Be concrete, cite the rule, review the whole diff, and don't invent issues or flag pure style.
4. Iterate until ready, then share
Expect several rounds: the contributor addresses findings, you review again. Keep working with them to fix as much as possible until the verdict is READY — the Leave for the actual review items are the only ones that should reach the reviewer unresolved. End the final round's report by reminding the contributor to share it on the PR (description or a comment) — it saves the reviewer a few rounds of back-and-forth. Never commit the notes as part of the diff.
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.
- yesterday First seen · 62 lines · 88 tokens per session scan A 3b6e2670c3dd
self-review is a skill published in the GitHub repository huggingface/diffusers (34,407 stars, last pushed yesterday), licensed Apache-2.0. It adds 88 tokens to every session and 701 once invoked, about $0.0004 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
nano-banana-pro-openrouter
Deterministic OpenRouter image generation adapter for Nano Banana Pro / Gemini image models. Use as skillexec when a meta-skill needs local image files and structured IMAGEREADY records without spawning an LLM agent.
founder-meditation
When something goes wrong — build failures, crashes, errors, test failures, deployment issues — generate a short calming meditation with TTS audio to reassure the user that everything will be okay.
music-and-singing-studio
Generate instrumental music, background beds, jingles, or sung songs with lyrics through OpenSquilla audio tools. Use when the user asks for BGM, music generation, 唱歌, 生成歌曲, lyrics to song, or a playable music audio artifact.
api-contrib
Contributing to the Kokoro-FastAPI Python API: module layout, endpoint gating pattern, test expectations. Use when adding or changing endpoints, services, or inference code.
ima2
Use the ima2-gen CLI/server to generate, edit, inspect, and manage local AI image generation jobs.
videoagent-image-studio
Tired of juggling 8 API keys? This skill gives you one-command access to Midjourney, Flux, Ideogram, and more, with zero setup. Use when you want to generate any image without worrying about API keys.