agentmods.dev

tentaflake AGENTS.md

tentaflake AGENTS.md is an instructions file for Codex, OpenCode from timfewi/tentaflake. It costs 669 tokens per session, scanned A, original, MIT.

Repository instructions for bloomery, a generic NixOS template for running isolated AI agents in Docker containers on one machine.

In plain words
What is it for?
Use them when building or testing the template, changing its Nix or Rust code, preparing commits, or ensuring documentation matches behavior.
Why use it?
They collect the project’s build, test, formatting, commit, security, and documentation rules in one place.

Instructions file for CodexOpenCode

not rated 30 yesterday A scan 669 tokens original MIT
View the source file timfewi/tentaflake
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/timfewi/tentaflake/agents-md
Clone the repo
git clone --depth 1 https://github.com/timfewi/tentaflake

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 tentaflake AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/timfewi/tentaflake/agents-md.svg)](https://agentmods.dev/instructions/timfewi/tentaflake/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/timfewi/tentaflake/agents-md"><img src="https://agentmods.dev/badge/instructions/timfewi/tentaflake/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 669 This file is loaded in full into every session.
When invoked 669 The same file — it is already loaded in full.
Security scan A 0 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 $0.00669 $0.00669
Opus 5 $0.00334 $0.00334
Sonnet 5 $0.00134 $0.00134
Haiku 4.5 $0.00067 $0.00067

Measured 5d ago against content hash 04fb4beb09d5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tentaflake 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 5d 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 · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Instructions — tentaflake

NixOS flake template for running isolated AI agents (Hermes and ZeroClaw) in Docker containers on a single machine.

Build & Test

nix flake check
nix build .#installer-iso
nix build \
  .#checks.x86_64-linux.vm-integration \
  -L
cargo fmt --all -- --check
cargo clippy --workspace \
  --all-targets -- -D warnings
cargo test --workspace
just e2e
just e2e-devcontainer
just e2e-installer
just e2e-run-vm
just security

Conventions

  • Nix: nix fmt (nixfmt), 2-space indent
  • Rust: cargo fmt, cargo clippy --workspace --all-targets -- -D warnings, cargo test --workspace
  • Commits: Conventional Commits (feat:, fix:, docs:)
  • DCO: every non-merge PR commit needs Signed-off-by:; use git commit -s

Template Rule

This repo is a GENERIC template. NEVER commit domain-specific code (company config, real hostnames, hardware configs, API keys, secrets, agent SOUL.md/skills written for specific deployments). Domain-specific work belongs in FORKS, not here.

Keep Docs In Sync

After any change that alters behavior, options, or usage, verify the docs are still accurate before finishing — and update them in the same change:

  • README.md and docs/ — user-facing docs
  • this AGENTS.md / CLAUDE.md — agent instructions
  • relevant .agents/skills/ — bundled skill docs

Module Boundaries

  • modules/ — reusable NixOS modules, including security, brokered egress, image-provenance gates, disposable workers, workspace quotas, encrypted backup, and generic options
  • lib/ — helpers (mkHermesAgent, mkZeroClawAgent, agentsFromData, pinnedImage, constants, devshell)
  • crates/ and pkgs/ — Rust CLI/broker/worker workspace and Nix packages
  • A balanced agent with autoStart = true requires its exact broker, worker, and workspace-quota declarations; stopped scaffolds remain network=none.
  • tests/ — NixOS VM test backing checks.<system>.vm-integration
  • installer/ — installer ISO and disk-install scripts
  • examples/ — consumer-flake reference
  • docs/ — user-facing documentation
  • .agents/skills/ — bundled Hermes skills (also development agent instructions for this repo)

Read the full file on GitHub · 69 lines

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. 5d ago First seen · 69 lines · 669 tokens per session scan A 04fb4beb09d5

Subscribe to this mod's changes

tentaflake AGENTS.md is an instructions file published in the GitHub repository timfewi/tentaflake (30 stars, last pushed yesterday), licensed MIT. It adds 669 tokens to every session, about $0.0033 per session on Opus 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 2026-08-30.

DevOps and cloudTestingWriting and docsagentscybersecurityinfrastructure-as-codelinuxnix-flake
Related

Other instructions, from other repositories

microsandbox AGENTS.md

AGENTS.md instructions for superradcompany/microsandbox, covering agents.md, scope, project map, design principles and backward compatibility review.

superradcompany/microsandbox · 3,652 tokens

strix AGENTS.md

AGENTS.md instructions for usestrix/strix, covering strix — agent guide, using strix from an agent and contributing to this repo.

usestrix/strix · 1,847 tokens

prismor CLAUDE.md

Claude Code instructions for PrismorSec/prismor, covering prismor security — claude.md, prismor runtime protection, cloaking (secret prevention) and working in this repo.

PrismorSec/prismor · 359 tokens

OpenHack AGENTS.md

Instructions for openhackai/OpenHack, covering openhack scanner guidance, repository scope and cli contract.

openhackai/OpenHack · 218 tokens

aptl AGENTS.md

AGENTS.md instructions for Brad-Edwards/aptl, covering agent instructions, ground control context, skill installation, raes asset inventory capture skill and ground control overview.

Brad-Edwards/aptl · 1,317 tokens

codebay CLAUDE.md

Claude Code instructions for khromov/codebay, covering claude.md, what this is, runtime & commands, comments and architecture.

khromov/codebay · 6,586 tokens