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 instructions/zksecurity/zkbugs/agents-mdgit clone --depth 1 https://github.com/zksecurity/zkbugsWrote 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/instructions/zksecurity/zkbugs/agents-md)<a href="https://agentmods.dev/instructions/zksecurity/zkbugs/agents-md"><img src="https://agentmods.dev/badge/instructions/zksecurity/zkbugs/agents-md.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 | $0.00997 | $0.00997 |
| Opus 5 | $0.00498 | $0.00498 |
| Sonnet 5 | $0.00199 | $0.00199 |
| Haiku 4.5 | $0.00100 | $0.00100 |
Grade A, and why
zkbugs AGENTS.md 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 4d 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
dataset/<dsl>/<org>/<repo>/<bug>/— Each vulnerability entry with reproduction scripts andzkbugs_config.json.dataset/codebases/— Full project codebases (gitignored, downloaded viascripts/download_sources.sh).scripts/— Infra and helpers (e.g.,download_sources.sh,test_all_circom.sh,install_circom.sh).scripts/patches/— Patch files applied to codebases for circom 2.x compatibility.prompts/— Detailed prompts for automated bug ingestion (process_audit_report.md,process_github_issue.md)..claude/skills/— Claude Code skills wrapping the prompts (process-audit-report,process-github-issue).reports/,misc/— Reference materials and analysis outputs.
Build, Test, and Development Commands
- Download codebases:
./scripts/download_sources.sh - Download ptau files:
./scripts/download_ptau.sh - Compile all circom bugs:
./scripts/test_all_circom.sh --compile-only --mode both - Full test (direct mode):
./scripts/test_all_circom.sh --skip-large - Print status table:
python3 scripts/print_bug_status.py Circom - Per-bug workflow (run inside the bug folder): edit
zkbugs_vars.sh(paths, entrypoints,PTAU_TARGET) →./zkbugs_setup.sh→./zkbugs_compile.shor./zkbugs_compile_setup.sh→./zkbugs_positive_test.sh→./zkbugs_clean.sh. - Two modes via
ZKBUGS_MODEenv var:direct(isolated wrapper) ororiginal(full project entrypoint). - Circom tooling:
scripts/install_circom.shinstallscircom,snarkjs, andffjavascriptwhen needed.
Coding Style & Naming Conventions
- Python: PEP 8, 4-space indent; keep scripts in
scripts/with descriptive names. - Shell: portable Bash; prefer
set -euo pipefailwhere safe; name per-bug scriptszkbugs_*.sh; mark executable. - JSON: four-space indent, stable key order; required file name:
zkbugs_config.json. - Bug paths: snake_case, descriptive (e.g.,
.../zksecurity_unsound_left_rotation).
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.
- 4d ago First seen · 53 lines · 997 tokens per session scan A 3596c9f777a6
zkbugs AGENTS.md is an instructions file published in the GitHub repository zksecurity/zkbugs (345 stars, last pushed 15d ago), licensed MIT. It adds 997 tokens to every session, about $0.0050 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 instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.