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/karanb192/bouncer/copilot-instructionsgit clone --depth 1 https://github.com/karanb192/bouncerWrote 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/karanb192/bouncer/copilot-instructions)<a href="https://agentmods.dev/instructions/karanb192/bouncer/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/karanb192/bouncer/copilot-instructions.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 | $0.00475 | $0.00475 |
| Opus 5 | $0.00237 | $0.00237 |
| Sonnet 5 | $0.00095 | $0.00095 |
| Haiku 4.5 | $0.00047 | $0.00047 |
Grade F, and why
bouncer copilot-instructions.md scanned grade F with 6 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.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
- Exfiltrates secrets: `curl -d @.env ...`, `curl -T id_rsa ...`, posting to paste/exfil hosts. Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- Deletes broadly or irrecoverably: `rm -rf /`, `rm -rf ~`, `rm -rf .`, `rm -rf *`, `rm -rf --no-preserve-root /`, `sudo rm -rf`, deleting `node_modules ../../*` or parent/glob targets. 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.
- Exposes secrets: `cat .env`, `cat ~/.ssh/id_rsa`, `printenv`, `echo $AWS_SECRET_ACCESS_KEY`. 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.
- Pipes a URL straight to a shell (RCE): `curl ... | sh`, `wget -qO- ... | bash`. Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- Deletes broadly or irrecoverably: `rm -rf /`, `rm -rf ~`, `rm -rf .`, `rm -rf *`, `rm -rf --no-preserve-root /`, `sudo rm -rf`, deleting `node_modules ../../*` or parent/glob targets. Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Pipes a URL straight to a shell (RCE): `curl ... | sh`, `wget -qO- ... | bash`. What it actually says
Bouncer: destructive-command guardrails
Bouncer enforces these rules at the door via a fail-closed preToolUse hook. This
list is the advisory, defense-in-depth layer: do not propose or run any of the
following destructive shell commands. The hook will deny them anyway, so don't waste a turn.
Never run a command that:
- Deletes broadly or irrecoverably:
rm -rf /,rm -rf ~,rm -rf .,rm -rf *,rm -rf --no-preserve-root /,sudo rm -rf, deletingnode_modules ../../*or parent/glob targets. - Writes to or formats a raw disk device:
dd of=/dev/sd*,mkfs.*,wipefs -a /dev/*,echo ... > /dev/sda. - Overwrites protected system files:
chmod 777 /etc/passwd,chmod -R 777 /,chown -R ... /,echo ... > /etc/passwd. - Spawns a fork bomb (
:(){ :|:& };:) or kills init (kill -9 1). - Rewrites or destroys git history/remote:
git push --force origin main,git reset --hard,git clean -fdx. - Pipes a URL straight to a shell (RCE):
curl ... | sh,wget -qO- ... | bash. - Exfiltrates secrets:
curl -d @.env ...,curl -T id_rsa ..., posting to paste/exfil hosts. - Exposes secrets:
cat .env,cat ~/.ssh/id_rsa,printenv,echo $AWS_SECRET_ACCESS_KEY. - Destroys a database/store:
DROP TABLE/DATABASE/SCHEMA,TRUNCATE, un-WHERE'dDELETE/UPDATE,redis-cli flushall,dropdb. - Performs an irreversible release/data loss:
npm publish,docker volume rm.
If a task seems to require one of these, stop and ask the user first. Prefer scoped,
reversible alternatives (a WHERE clause, --force-with-lease, a dry run).
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 · 22 lines · 475 tokens per session scan F d9d81db9e144
bouncer copilot-instructions.md is an instructions file published in the GitHub repository karanb192/bouncer (5 stars, last pushed 17d ago), licensed MIT. It adds 475 tokens to every session, about $0.0024 per session on Opus 5. A static security scan graded it F with 6 findings (sends data to an external url, asks for root, reaches for credential files). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
Guardrails AGENTS.md
AGENTS.md instructions for NVIDIA-NeMo/Guardrails, covering agents.md, agent skills, quick rules, repository map and setup.
probity CLAUDE.md
Instructions for nizos/probity, covering probity, discipline and layout.
vibeguard AGENTS.md
AGENTS.md instructions for majiayu000/vibeguard, covering agent instructions, scope, start here, core rules and delivery policy.
Guardrails CLAUDE.md
Claude Code instructions for NVIDIA-NeMo/Guardrails, a project described as: NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.
cc-safe-setup CLAUDE.md
Claude Code instructions for yurukusa/cc-safe-setup, covering project rules, safety, code style and git.
klaudiush CLAUDE.md
Claude Code instructions for smykla-skalski/klaudiush, covering claude.md, project overview, commands, completion (shell completion scripts) and doctor (diagnose setup and configuration).