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/vincentkoc/tokenjuice/autoreviewnpx skills add vincentkoc/tokenjuice --skill autoreviewgit clone --depth 1 https://github.com/vincentkoc/tokenjuiceWrote 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/vincentkoc/tokenjuice/autoreview)<a href="https://agentmods.dev/skills/vincentkoc/tokenjuice/autoreview"><img src="https://agentmods.dev/badge/skills/vincentkoc/tokenjuice/autoreview.svg" alt="Measured on agentmods" 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 | $0.00025 | $0.01665 |
| Opus 5 | $0.00013 | $0.00833 |
| Sonnet 5 | $0.00005 | $0.00333 |
| Haiku 4.5 | $0.00003 | $0.00167 |
Grade A, and why
autoreview 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 6d 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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auto Review
Run the bundled structured review helper as a closeout check. This is code review, not Guardian auto_review approval routing.
Codex review is the default when no engine is set. It usually delivers the best review results and should remain the normal final closeout engine.
Use when:
- user asks for Codex review / Claude review / autoreview / second-model review
- after non-trivial code edits, before final/commit/ship
- reviewing a local branch or PR branch after fixes
Contract
- Treat review output as advisory. Never blindly apply it.
- Verify every finding by reading the real code path and adjacent files.
- Read dependency docs/source/types when the finding depends on external behavior.
- Reject unrealistic edge cases, speculative risks, broad rewrites, and fixes that over-complicate the codebase.
- Prefer small fixes at the right ownership boundary; no refactor unless it clearly improves the bug class.
- Keep going until structured review returns no accepted/actionable findings.
- If a review-triggered fix changes code, rerun focused tests and rerun the structured review helper.
- For security-audit suppression changes, verify accepted findings remain auditable: suppressed findings stay in structured output, active output keeps an unsuppressible suppression notice, and aggregate findings cannot hide unrelated active risk.
- Never switch or override the requested review engine/model. If the review hits model capacity, retry the same command a few times with the same engine/model.
- Tools are useful in review mode. The helper allows read-only inspection tools and web search by default so reviewers can check dependency contracts, upstream docs, and current behavior.
- Security perspective is always included, but it should not cripple legitimate functionality. Report security findings only when the change creates a concrete, actionable risk or removes an important safety check.
- Do not invoke built-in
codex review, nested reviewers, or reviewer panels from inside the review. The helper builds one bundle, calls one selected engine, validates one structured result, and stops. - Stop as soon as the helper exits 0 with no accepted/actionable findings. Do not run an extra review just to get a nicer "clean" line, a second opinion, or clearer closeout wording.
- Treat the helper's successful exit plus absence of actionable findings as the clean review result, even if the underlying Codex CLI output is terse.
- If rejecting a finding as intentional/not worth fixing, add a brief inline code comment only when it explains a real invariant or ownership decision that future reviewers should know.
- If
gh/Gitcrawl reportsdatabase disk image is malformed, rungitcrawl doctor --jsononce to let the portable cache repair before retrying review; do not bypass the shim unless repair fails and freshness requires live GitHub. - If Gitcrawl reports a portable manifest mismatch, source/runtime DB health error, or stale portable-store checkout, run
gitcrawl doctor --jsonand inspectsource_db_health,runtime_db_health, andportable_store_statusbefore falling back to live GitHub. - Do not push just to review. Push only when the user requested push/ship/PR update.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 6d ago First seen · 145 lines · 25 tokens per session scan A 5022ca875c7f
autoreview is a skill published in the GitHub repository vincentkoc/tokenjuice (517 stars, last pushed yesterday), licensed MIT. It adds 25 tokens to every session and 1,665 once invoked, about $0.0001 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
gguf-quantization
GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU requirements.
gptq
Post-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4× memory reduction with <2% perplexity degradation, or for faster inference (3-4× speedup) vs FP16. Integrates with transformers and PEFT for QLoRA fine-tuning.
deepspeed
Expert guidance for distributed training with DeepSpeed - ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8, 1-bit Adam, sparse attention.
github-secret-hunting
Find leaked API keys, tokens, and credentials in public GitHub repositories.
ml-training-recipes
Battle-tested PyTorch training recipes for all domains — LLMs, vision, diffusion, medical imaging, protein/drug discovery, spatial omics, genomics. Covers training loops, optimizer selection (AdamW, Muon), LR scheduling, mixed precision, debugging, and systematic experimentation. Use when training or fine-tuning…
prompt-optimization
Use this skill when the user wants to optimize, modify, or improve the system prompt of an AI agent. This includes requests like 'optimize the prompt', 'make the AI more focused on X', 'change the system prompt', 'improve the agent behavior', or 'modify how the AI responds'.