Borrowing it
Nothing to install: this file belongs to future-architect/uzomuzo-oss. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/future-architect/uzomuzo-oss/main/.github/prompts/diet-fuzz.prompt.mdgit clone --depth 1 https://github.com/future-architect/uzomuzo-ossWrote 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/commands/future-architect/uzomuzo-oss/diet-fuzz)<a href="https://agentmods.dev/commands/future-architect/uzomuzo-oss/diet-fuzz"><img src="https://agentmods.dev/badge/commands/future-architect/uzomuzo-oss/diet-fuzz/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/commands/future-architect/uzomuzo-oss/diet-fuzz"><img src="https://agentmods.dev/badge/commands/future-architect/uzomuzo-oss/diet-fuzz.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 | $0.00019 | $0.05313 |
| Opus 5.5 | $0.00008 | $0.02125 |
| Sonnet 5.5 | $0.00004 | $0.01063 |
| Haiku 4.5 | $0.00002 | $0.00531 |
Grade C, and why
diet-fuzz scanned grade C with 2 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 1mo 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
- **trivy**: `curl -sfL https://raw.githubusercontent.com/aquasecurity/trivy/main/contrib/install.sh | sh -s -- -b ~/bin` Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **trivy**: `curl -sfL https://raw.githubusercontent.com/aquasecurity/trivy/main/contrib/install.sh | sh -s -- -b ~/bin` How it starts
The opening of the file, as written. The whole thing — 552 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/diet-fuzz — Batch Diet Fuzz Testing
Run uzomuzo diet-trial on many OSS projects across multiple languages to fuzz-test parser accuracy, find detection bugs, and accumulate evidence for known issues.
Arguments
Parse the user's arguments:
<languages|all>(required): Comma-separated language list (go,python,typescript,js) orall(=go,python,typescript,js)--count N(optional, default:5): Number of projects per language--tool <trivy,syft,cdxgen>(optional, default: all three): Comma-separated SBOM tools to use. Each project is analyzed with every specified tool.--max-parallel N(optional, default:4): Maximum concurrent agents--projects-file <path>(optional): Path to a file listingorg/repoentries (one per line, with optional# languagesuffix). When provided, skip auto-selection.
Examples
/diet-fuzz all # 5 projects × 4 languages × 3 tools
/diet-fuzz go,typescript --count 10 # 10 projects × 2 languages × 3 tools
/diet-fuzz python --tool syft --count 3 # 3 Python projects × syft only
/diet-fuzz all --projects-file projects.txt # Use curated list
Pipeline Overview
1. Pull & Build → git pull origin/main, rebuild uzomuzo-diet
2. Select Projects → stratified sampling or projects-file
3. Pre-filter → clone + SBOM, skip if dependency graph empty
4. Diet Analysis → run uzomuzo-diet per project × tool
5. Anomaly Detect → find IMPORTS-BUT-NO-CALLS, EOL-ZERO-SCORE, etc.
6. Compare Past → diff against previous run JSONs
7. File Issues → auto-create or comment on existing issues
8. Record Findings → append new insights to findings.md
9. Report → display cross-language summary table
Phase 1: Pull & Build
Always rebuild from latest origin/main to avoid stale binary issues.
cd <project-root>
git fetch origin main
git checkout main
git pull origin main
mkdir -p ~/bin
CGO_ENABLED=1 go build -o ~/bin/uzomuzo-diet ./cmd/uzomuzo-diet
export PATH="$HOME/bin:$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.
- 1mo ago First seen · 552 lines · 19 tokens per session scan C cb95cc09f939
diet-fuzz is a command published in the GitHub repository future-architect/uzomuzo-oss (42 stars, last pushed today), licensed Apache-2.0. It adds 19 tokens to every session and 5,313 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-07.
Other commands, from other repositories
security
Scan a SQL string, .sql file, or SQL-building source file for injection risks with GoSQLX.
modernize-transform
Transform one legacy module to the target stack — idiomatic rewrite with behavior-equivalence tests.
write-skill-test
RED-GREEN-REFACTOR implementation for writing-skills: Baseline testing, minimal skill writing, loophole closure, and full creation checklist.
verify
Run verification commands and confirm output before making success claims. Use before committing, creating PRs, or claiming work is complete. Evidence before assertions, ALWAYS.
auto-verify
A command for checking a website's front-end user experience with Playwright, a tool that automates web browsers.
test
Generate tests for the specified code or feature.