shellguard AGENTS.md

Repository instructions for Shellguard, a Go service that parses shell commands, checks them against allowed commands, and can manage remote shell access.

In plain words
What is it for?
Use them when building Shellguard, running its tests or fuzz tests, changing the parser and validator, or updating command manifests.
Why use it?
They provide the build, test, lint, and project-structure details needed to change command validation safely.

Instructions file for CodexOpenCode

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/fawdyinc/shellguard/agents-md
Clone the repo
git clone --depth 1 https://github.com/fawdyinc/shellguard

Made for: Codex, OpenCode.

Per session 1,616 This file is loaded in full into every session.
When invoked 1,616 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 $0.01616 $0.01616
Opus 5 $0.00808 $0.00808
Sonnet 5 $0.00323 $0.00323
Haiku 4.5 $0.00162 $0.00162

Measured 2d ago against content hash baf23ca8b255, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

shellguard 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 2d 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 · 182 lines

How it starts

The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Instructions for AI coding agents working in this repository.

Build & Test Commands

make build          # Static binary to ./bin/shellguard (CGO_ENABLED=0)
make test           # go test ./... -count=1
make test-race      # go test ./... -race -count=1
make lint           # golangci-lint run ./...

Run a single test:

go test ./parser -run TestParseSimpleCommand -count=1

Run a single fuzz test:

go test ./parser -fuzz FuzzParse -fuzztime=30s

Project Structure

shellguard.go                    # Root package: Config, New(), RunStdio()
cmd/shellguard/                  # CLI entry point
server/                          # MCP server core, tool registration, Executor interface
parser/                          # Shell AST parser (mvdan.cc/sh/v3)
validator/                       # Command/flag allowlist validation
ssh/                             # SSH manager, ShellQuote, ReconstructCommand
manifest/                        # YAML command registry (embed.FS)
  manifests/                     # Allowed command manifests
  manifests/denied/              # Denied command manifests
output/                          # Output truncation (64KB cap)
toolkit/                         # Diagnostic tool provisioning (rg, jq, yq)

Dependency flow: server depends on all other packages. validator depends on parser and manifest. ssh (reconstruct) depends on parser. manifest, parser, and output are standalone with zero internal dependencies.

Code Style

Imports

Two groups separated by a blank line: stdlib first, then everything else (third-party and internal mixed together, alphabetically sorted).

import (
    "context"
    "fmt"

    "github.com/fawdyinc/shellguard/manifest"
    "github.com/fawdyinc/shellguard/parser"
    "github.com/modelcontextprotocol/go-sdk/mcp"
)

When a third-party package name conflicts with a local package, alias the third-party one (e.g., gossh "golang.org/x/crypto/ssh" in ssh/ssh.go).

Read the full file on GitHub · 182 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. 2d ago First seen · 182 lines · 1,616 tokens per session scan A baf23ca8b255

Subscribe to this mod's changes

shellguard AGENTS.md is an instructions file published in the GitHub repository fawdyinc/shellguard (20 stars, last pushed 11d ago), licensed Apache-2.0. It adds 1,616 tokens to every session, about $0.0081 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.