agentmods.dev

AgentPort: Instructions file for Codex

AGENTS.md

AgentPort AGENTS.md is an instructions file for Codex, OpenCode from knownothing20/AgentPort. It costs 391 tokens per session, scanned A, original, MIT.

A set of repository instructions for AgentPort covering privacy checks, safe handling of credentials, and bounded remote searches. A bounded search limits searching to the requested project instead of the whole machine.

In plain words
What is it for?
Checking privacy before commits, keeping connection details out of source code, and searching remote project files safely.
Why use it?
It reduces the risk of committing secrets or searching unrelated files, while defining how remote content should be found.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is knownothing20/AgentPort's own configuration. It tells Codex and OpenCode how to work on AgentPort itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything AgentPort configures →

not rated 1repo changed 26d ago A scan 391 tokens original MIT
View source ↗ knownothing20/AgentPort
Reuse

Borrowing it

Nothing to install: this file belongs to knownothing20/AgentPort. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/knownothing20/AgentPort/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/knownothing20/AgentPort

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 AgentPort AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/knownothing20/agentport/agents-md/github.svg)](https://agentmods.dev/instructions/knownothing20/agentport/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/knownothing20/agentport/agents-md"><img src="https://agentmods.dev/badge/instructions/knownothing20/agentport/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for AgentPort AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/knownothing20/agentport/agents-md"><img src="https://agentmods.dev/badge/instructions/knownothing20/agentport/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 391 This file is loaded in full into every session.
When invoked 391 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00391 $0.00391
Opus 5.5 $0.00156 $0.00156
Sonnet 5.5 $0.00078 $0.00078
Haiku 4.5 $0.00039 $0.00039

Measured 26d ago against content hash 175b44cebb64, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

AgentPort 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 26d 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 · 31 lines

What it actually says

AgentPort Repository Rules

Before committing or pushing, run npm run privacy:check. Before a release, run npm run privacy:release. It checks working files, the staged snapshot, the complete HEAD history, and all local release tags.

  • Keep credentials, machine-specific connection data, and runtime configuration in ignored local/ files or environment files only.
  • Use documentation placeholders for hosts, users, paths, and tokens. Do not copy values from a live machine into source, tests, or examples.
  • Do not bypass the repository hook with --no-verify.
  • If the privacy check fails, remove or replace the value before committing.
  • Use the owner's verified GitHub noreply identity, never a personal machine account name or personal email. Keep this setting repository-local.
  • Enable the lightweight hooks with git config core.hooksPath .githooks. Pre-commit checks staged bytes and identity; pre-push checks outgoing history, including intermediate commits whose sensitive content was later removed. Annotated tags and Co-authored-by identities are also checked. Only remote commit IDs advertised for this push are treated as already published.
  • Skill sync copies only Git-tracked source files. Review and stage intended new source files first; never force-add private configs, logs, or scratch scripts.
  • Prefer AgentPort remote_grep for remote content search. It uses bounded Node search through the daemon and bounded grep through SSH fallback.
  • Before directly using rg on a remote host, run command -v rg >/dev/null 2>&1. If it is unavailable, silently use bounded grep or find instead.
  • Scope any recursive search to the requested project or workspace. Exclude .git, dependency directories, and build output; never search the whole disk.
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. 26d ago Changed · +11 lines · +171 tokens per session 175b44cebb64
  2. 2mo ago First seen · 20 lines · 220 tokens per session scan A 142f6963a570

Subscribe to this mod's changes

AgentPort AGENTS.md is an instructions file published in the GitHub repository knownothing20/AgentPort (1 stars, last pushed 15d ago), licensed MIT. It adds 391 tokens to every session, about $0.0016 per session on Opus 5.5. 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 2026-08-31.

Related

AgentPort AGENTS.md compared with instructions from other repositories

AgentPort AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
AgentPort AGENTS.mdknownothing20/AgentPortInstructions file115d agoMITA391Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file275k2d agoMITA4,313Codex, OpenCode