bouncer AGENTS.md

bouncer AGENTS.md is an instructions file for Codex, OpenCode from karanb192/bouncer. It costs 461 tokens per session, scanned F, original, MIT.

AGENTS.md instructions for a shell safety guard called Bouncer. A shell safety guard checks terminal commands before they run and blocks dangerous ones.

In plain words
What is it for?
Keeping terminal work within safer boundaries while allowing read-only inspection, scoped edits, and common version-control checks.
Why use it?
It prevents agents from running listed destructive commands, such as wiping disks, deleting databases, exposing secrets, or force-pushing protected branches.

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/karanb192/bouncer/agents-md
Clone the repo
git clone --depth 1 https://github.com/karanb192/bouncer

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 bouncer AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/karanb192/bouncer/agents-md.svg)](https://agentmods.dev/instructions/karanb192/bouncer/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/karanb192/bouncer/agents-md"><img src="https://agentmods.dev/badge/instructions/karanb192/bouncer/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 461 This file is loaded in full into every session.
When invoked 461 The same file — it is already loaded in full.
Security scan F 5 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 $0.00461 $0.00461
Opus 5 $0.00230 $0.00230
Sonnet 5 $0.00092 $0.00092
Haiku 4.5 $0.00046 $0.00046

Measured 3d ago against content hash 146eb0f7ef83, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade F, and why

bouncer AGENTS.md scanned grade F with 5 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 3d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

- `chmod 777`, `chown /`, `kill -9 1`, fork bombs, `npm publish`, `crontab -r`

Reaches for credential fileshighPrivilege escalation

SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.

- overwriting `/etc/passwd`, `/etc/shadow`, `/etc/sudoers`, `/etc/hosts`

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.

- `curl … | sh` (piping a URL straight to the shell); `curl`/`wget` to paste / exfil hosts

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

- `rm -rf ~`, `rm -rf /`, `rm` on system dirs or with parent-traversal / glob targets

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- `curl … | sh` (piping a URL straight to the shell); `curl`/`wget` to paste / exfil hosts
AGENTS.md · 28 lines

What it actually says

Bouncer is active

A door-guard sits in front of your shell. Every run_shell_command call passes the door before it runs; destructive commands are blocked by an enforced BeforeTool hook, not by you, and not negotiable.

Don't try to run the footguns below. They will be bounced with the exact rule that fired, and the turn is wasted. Reach for the safe alternative instead.

Bounced at the door (non-exhaustive):

  • rm -rf ~, rm -rf /, rm on system dirs or with parent-traversal / glob targets
  • dd/mkfs/wipefs to a disk device; writing to /dev/sd*, /dev/nvme*
  • overwriting /etc/passwd, /etc/shadow, /etc/sudoers, /etc/hosts
  • DROP TABLE/DROP DATABASE/TRUNCATE; DELETE/UPDATE with no WHERE
  • redis-cli flushall/flushdb, dropdb
  • curl … | sh (piping a URL straight to the shell); curl/wget to paste / exfil hosts
  • uploading or cat-ing secrets: .env, id_rsa, *.pem, *.key, credentials
  • git push --force to main/master, git reset --hard, git clean -f, git checkout .
  • chmod 777, chown /, kill -9 1, fork bombs, npm publish, crontab -r

Walk right in: read-only inspection, scoped edits, git status/diff/add/commit, tests, builds, a WHERE'd UPDATE, normal npm/docker/psql work.

This advisory is belt-and-suspenders. The real enforcement is the hook, but not provoking it keeps your turns productive. Tune with BOUNCER_LEVEL=critical|high|strict; disable with BOUNCER_OFF=1.

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. 3d ago First seen · 28 lines · 461 tokens per session scan F 146eb0f7ef83

Subscribe to this mod's changes

bouncer AGENTS.md is an instructions file published in the GitHub repository karanb192/bouncer (5 stars, last pushed 16d ago), licensed MIT. It adds 461 tokens to every session, about $0.0023 per session on Opus 5. A static security scan graded it F with 5 findings (asks for root, reaches for credential files, downloads and executes remote code). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.