agentmods.dev

dsh-record-replay: Instructions file for Codex

AGENTS.md

dsh-record-replay AGENTS.md is an instructions file for Codex, OpenCode from humblebanana/dsh-record-replay. It costs 273 tokens per session, scanned A, original, MIT.

Repository-specific instructions for dsh-record-replay, a plugin that records and replays command-line runs for testing. They cover its layout, validation command, subprocess rules, registration contract, and where recording files may be stored.

In plain words
What is it for?
Use them when developing, testing, validating, or reviewing the dsh-record-replay plugin and its command runner.
Why use it?
They prevent unsafe command execution, leaked registrations, invalid artifact paths, and incorrect plugin exports.

Instructions file for CodexOpenCode

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

This is humblebanana/dsh-record-replay's own configuration. It tells Codex and OpenCode how to work on dsh-record-replay 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 dsh-record-replay configures →

not rated 13repo 2mo ago A scan 273 tokens original MIT
View source ↗ humblebanana/dsh-record-replay
Reuse

Borrowing it

Nothing to install: this file belongs to humblebanana/dsh-record-replay. 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/humblebanana/dsh-record-replay/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/humblebanana/dsh-record-replay

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 dsh-record-replay AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/humblebanana/dsh-record-replay/agents-md/github.svg)](https://agentmods.dev/instructions/humblebanana/dsh-record-replay/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/humblebanana/dsh-record-replay/agents-md"><img src="https://agentmods.dev/badge/instructions/humblebanana/dsh-record-replay/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 dsh-record-replay AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/humblebanana/dsh-record-replay/agents-md"><img src="https://agentmods.dev/badge/instructions/humblebanana/dsh-record-replay/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 273 This file is loaded in full into every session.
When invoked 273 The same file — it is already loaded in full.
Security scan A 1 finding. 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 $0.00273 $0.00273
Opus 5.5 $0.00109 $0.00109
Sonnet 5.5 $0.00055 $0.00055
Haiku 4.5 $0.00027 $0.00027

Measured 2mo ago against content hash 6edb6c8e9f98, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

dsh-record-replay AGENTS.md scanned grade A with 1 finding 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 2mo 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

- The CLI is invoked only through `ctx.subprocess.spawn` with bounded collected
AGENTS.md · 32 lines

What it actually says

AGENTS

Guidance for coding agents working in this repository.

Build and test

pnpm install
node scripts/link-dsh.mjs   # link @deepseek-ai/* from a DSH harness/checkout
pnpm validate               # build + test

Hard rules

  • The plugin module (src/index.ts) must export a Cordis namespace plugin (name, inject, Config, apply) and must NOT add export default.
  • ctx.tools.register(...) and ctx.skills.register(...) return disposers that are fiber-attached; do not leak them.
  • The CLI is invoked only through ctx.subprocess.spawn with bounded collected output and an abort signal. Never use raw shell string interpolation.
  • Recording artifacts (runsOut, skillInputsOut) must be workspace-relative and are validated in src/config.ts.

Layout

  • src/index.ts — plugin entry (registration).
  • src/config.ts — schema and validation.
  • src/tools.ts — model-facing tool definitions.
  • src/runner.ts — CLI resolution and subprocess invocation.
  • src/skill.ts — the open-record-replay skill body.
  • tests/ — registration-contract and runner unit tests.
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. 2mo ago First seen · 32 lines · 273 tokens per session scan A 6edb6c8e9f98

Subscribe to this mod's changes

dsh-record-replay AGENTS.md is an instructions file published in the GitHub repository humblebanana/dsh-record-replay (13 stars, last pushed 2mo ago), licensed MIT. It adds 273 tokens to every session, about $0.0011 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

computer-usedeepseek-harnessdsh-pluginmacosrecord-replay
Related

dsh-record-replay AGENTS.md compared with instructions from other repositories

dsh-record-replay AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
dsh-record-replay AGENTS.mdhumblebanana/dsh-record-replayInstructions file132mo agoMITA273Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
vscode ai-customization.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA1,907GitHub Copilot