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.
curl -O https://raw.githubusercontent.com/humblebanana/dsh-record-replay/main/AGENTS.mdgit clone --depth 1 https://github.com/humblebanana/dsh-record-replayWrote 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/humblebanana/dsh-record-replay/agents-md)<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.
<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>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 5.1 | $0.00273 | $0.00273 |
| Opus 5 | $0.00137 | $0.00137 |
| Sonnet 5 | $0.00055 | $0.00055 |
| Haiku 4.5 | $0.00027 | $0.00027 |
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 10d 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 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 addexport default. ctx.tools.register(...)andctx.skills.register(...)return disposers that are fiber-attached; do not leak them.- The CLI is invoked only through
ctx.subprocess.spawnwith bounded collected output and an abort signal. Never use raw shell string interpolation. - Recording artifacts (
runsOut,skillInputsOut) must be workspace-relative and are validated insrc/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— theopen-record-replayskill body.tests/— registration-contract and runner unit tests.
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.
- 10d ago First seen · 32 lines · 273 tokens per session scan A 6edb6c8e9f98
dsh-record-replay AGENTS.md is an instructions file published in the GitHub repository humblebanana/dsh-record-replay (13 stars, last pushed 27d ago), licensed MIT. It adds 273 tokens to every session, about $0.0014 per session on Opus 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.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.