agentmods.dev

shipproof AGENTS.md

shipproof AGENTS.md is an instructions file for Codex, OpenCode from kingggg5/shipproof. It costs 1,028 tokens per session, scanned A, original, MIT.

Repository instructions for ShipProof, a dependency-free checker that scans AI-written code for production risks and can enforce resource and capacity limits.

In plain words
What is it for?
Use them when adding or changing scanner rules, tests, capacity checks, distribution adapters, or verification steps for the command-line tool, GitHub Action, pre-commit hook, or MCP server.
Why use it?
They define the project's safety boundaries and the evidence required before a scanner rule or other change is considered complete.

Instructions file for CodexOpenCode

not rated 18 yesterday A scan 1,028 tokens original MIT
View the source file kingggg5/shipproof
Install

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.

agentmods
npx agentmods add instructions/kingggg5/shipproof/agents-md
Clone the repo
git clone --depth 1 https://github.com/kingggg5/shipproof

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for shipproof AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/kingggg5/shipproof/agents-md.svg)](https://agentmods.dev/instructions/kingggg5/shipproof/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/kingggg5/shipproof/agents-md"><img src="https://agentmods.dev/badge/instructions/kingggg5/shipproof/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,028 This file is loaded in full into every session.
When invoked 1,028 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.01028 $0.01028
Opus 5 $0.00514 $0.00514
Sonnet 5 $0.00206 $0.00206
Haiku 4.5 $0.00103 $0.00103

Measured 5d ago against content hash b7b0e987e9b9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

shipproof 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 5d 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.

AGENTS.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Guidance for AI coding agents (Codex, Claude Code, Cursor, and others) working in this repository.

What this repository is

ShipProof is a zero-dependency production gate for AI-written code: a static scanner (skills/audit-production-readiness/scripts/scan_repo.py), a resource-budget gate, a capacity model with k6 generation, and thin distribution adapters (npm CLI in lib/, GitHub Action, pre-commit hook, MCP server). Read README.md for the product contract and CONTRIBUTING.md before changing anything.

Non-negotiable rules

  • The default workflow stays read-only, offline, and dependency-free. Never add telemetry, network calls, install scripts, or dependency downloads to the default path.
  • Never copy rules or guidance from Semgrep or any license-restricted source. Build detectors from primary sources (CWE, OWASP, framework docs, real CVEs) with your own implementation and fixtures.
  • Every scanner rule needs a stable SPxxx ID, positive and negative tests, a CWE/control mapping, remediation text, and a false-positive analysis. Update both README rule tables when rules change — a structure test enforces this.
  • Exit codes are a contract: 0 pass, 1 gate failure, 2 invalid or unavailable evidence. Do not change them casually.

Verify before declaring done

npm run check        # lint + full test suite + pack check + packed-artifact smoke test
python skills/audit-production-readiness/scripts/scan_repo.py . --fail-on high

Both must pass with zero findings at the high gate. If your change adds findings in test fixtures, obfuscate the vulnerable literal (string concatenation) instead of weakening the gate.

Where things live

  • Scanner rules and engines: skills/audit-production-readiness/scripts/scan_repo.py (RULES tuple, RULE_EXPLANATIONS, regex + Python AST engines).
  • Node CLI, policy parser, evidence adapters, MCP server: lib/*.mjs.
  • Compatibility contract: fixtures/golden-contract/ + fixtures/expected-golden-scan.json — identical findings and fingerprints through direct Python, the Node CLI, and SARIF. Update the expectation deliberately when a detection change is intended.
  • Tests: tests/ (Python) and tests/node/ (Node). Both run in CI across Python 3.10/3.11/3.12/3.13/3.14 and Node 20/22/24.

Read the full file on GitHub · 56 lines

Changes

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.

  1. 5d ago First seen · 56 lines · 1,028 tokens per session scan A b7b0e987e9b9

Subscribe to this mod's changes

shipproof AGENTS.md is an instructions file published in the GitHub repository kingggg5/shipproof (18 stars, last pushed yesterday), licensed MIT. It adds 1,028 tokens to every session, about $0.0051 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.

ai-codeapplication-securitydevsecopsgithub-actionsmcpproduction-readiness
Related

Other instructions, from other repositories

ai-appsec AGENTS.md

Instructions for subodhkc/ai-appsec, covering agents.md — haiec agent security mcp (phase -1 → phase 18), 1. workspace layout, 2. architectural principles (apply to every phase), 3. hard constraints (never violate) and 4. phase discipline.

subodhkc/ai-appsec · 2,730 tokens

MCP-Sentinel AGENTS.md

Instructions for BashaarJavaid/MCP-Sentinel, covering agents.md, project, where things live, conventions and commands.

BashaarJavaid/MCP-Sentinel · 2,226 tokens

kc-secure-repo-template AGENTS.md

AGENTS.md instructions for CaseyLabs/kc-secure-repo-template, covering agents.md, project overview, project defaults, public interface and skill routing.

CaseyLabs/kc-secure-repo-template · 1,559 tokens

kc-secure-repo-template CLAUDE.md

Claude Code instructions for CaseyLabs/kc-secure-repo-template, a project described as: Security-hardened GitHub repository template, designed to prevent supply-chain attacks. Includes vulnerability scanning and AI agent skills.

CaseyLabs/kc-secure-repo-template · 5 tokens

stride-gpt AGENTS.md

AGENTS.md instructions for mrwadams/stride-gpt, covering agents.md, what this project is, repository layout, how the agentic analysis works and progressive disclosure pattern.

mrwadams/stride-gpt · 4,122 tokens

skylos CLAUDE.md

Claude Code instructions for duriantaco/skylos, covering claude.md, what this repo is, install, use and skill for using skylos.

duriantaco/skylos · 652 tokens