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 skills add djscheuf/agentic-dev-ecosystem-template --skill nix-shellgit clone --depth 1 https://github.com/djscheuf/agentic-dev-ecosystem-templateWrote 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/skills/djscheuf/agentic-dev-ecosystem-template/nix-shell)<a href="https://agentmods.dev/skills/djscheuf/agentic-dev-ecosystem-template/nix-shell"><img src="https://agentmods.dev/badge/skills/djscheuf/agentic-dev-ecosystem-template/nix-shell/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/skills/djscheuf/agentic-dev-ecosystem-template/nix-shell"><img src="https://agentmods.dev/badge/skills/djscheuf/agentic-dev-ecosystem-template/nix-shell.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 | $0.00105 | $0.01175 |
| Opus 5.5 | $0.00042 | $0.00470 |
| Sonnet 5.5 | $0.00021 | $0.00235 |
| Haiku 4.5 | $0.00011 | $0.00118 |
Grade A, and why
nix-shell 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 22d 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.
How it starts
The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
nix-shell Skill
Overview
nix-shell builds a temporary environment containing the packages and dependencies you specify, then drops you into a shell (or runs a command). It is the standard way to access tools on NixOS without permanently installing them, and the standard way to set up reproducible project environments on any Nix system.
Use this skill when you are:
- Running a command and getting
command not foundon NixOS. - Creating a reproducible development environment for a project.
- Writing a
shell.nixorflake.nixdevShell. - Writing a script with a
nix-shellshebang. - Deciding whether to use
nix-shell,nix shell, ornix develop.
nix-shell vs nix shell vs nix develop
| Command | When to use it |
|---|---|
nix-shell -p <pkg> |
Quick, temporary access to one or more packages (legacy CLI) |
nix-shell |
Use shell.nix / default.nix in the current directory (legacy CLI) |
nix shell <flake> |
Modern replacement for nix-shell -p, uses flakes |
nix develop <flake> |
Enter a flake devShell (modern, project-oriented) |
On NixOS, nix-shell -p is universally available and the fastest way to get a tool for a single command. nix develop is preferred inside flake-based projects.
Decision tree: when to use nix-shell
Command fails with "command not found"
↓
Is it a core utility (ls, cat, grep, sed, awk, sh)?
YES → Something is wrong with the system or PATH
NO → Use nix-shell
↓
Do you know the package name?
YES → nix-shell -p <package> --run "<command>"
NO → Search with nix search nixpkgs <term> or https://search.nixos.org
Then try nix-shell -p <package> --run "<command>"
Quick reference
| Task | Command |
|---|---|
| Run one command with a package | nix-shell -p <pkg> --run "<cmd>" |
| Run with multiple packages | nix-shell -p <pkg1> <pkg2> --run "<cmd>" |
| Interactive shell with packages | nix-shell -p <pkg1> <pkg2> |
| Use a project shell.nix | nix-shell |
| Enter a flake devShell | nix develop |
| Run a command in a flake devShell | nix develop .#default --command <cmd> |
| Clean environment (close to build) | nix-shell -p <pkg> --pure --keep HOME |
| Self-contained script | #!/usr/bin/env nix-shell (see shebangs guide) |
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 22d ago First seen · 85 lines · 105 tokens per session scan A 1e4f4d1ca334
nix-shell is a skill published in the GitHub repository djscheuf/agentic-dev-ecosystem-template (12 stars, last pushed 20d ago), licensed MIT. It adds 105 tokens to every session and 1,175 once invoked, about $0.0004 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 2026-10-01.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…