demo-5-sandbox-feature-pr

demo-5-sandbox-feature-pr is a skill for Claude Code, Codex from decodingai-magazine/building-a-coding-agent-from-scratch-course. It costs 60 tokens per session (1,247 once invoked), scanned A, original, Apache-2.0.

A demonstration workflow that runs a coding agent inside an isolated copy of a course repository and turns one small feature into a draft pull request.

In plain words
What is it for?
Use it with Docker or Modal sandboxing to clone the repository, plan and build a small feature, hand the branch back, and open a draft pull request.
Why use it?
It lets the demonstration change a separate workspace, reducing the risk of touching the original checkout while showing the full build-and-handoff process.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it with Docker or Modal sandboxing to clone the repository, plan and build a small feature, hand the branch back, and open a draft pull request.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/decodingai-magazine/building-a-coding-agent-from-scratch-course/demo-5-sandbox-feature-pr
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.

Any agent
npx skills add decodingai-magazine/building-a-coding-agent-from-scratch-course --skill demo-5-sandbox-feature-pr
Clone the repo
git clone --depth 1 https://github.com/decodingai-magazine/building-a-coding-agent-from-scratch-course

Made for: Claude Code, Codex.

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 demo-5-sandbox-feature-pr

README.md
[![agentmods](https://agentmods.dev/badge/skills/decodingai-magazine/building-a-coding-agent-from-scratch-course/demo-5-sandbox-feature-pr/github.svg)](https://agentmods.dev/skills/decodingai-magazine/building-a-coding-agent-from-scratch-course/demo-5-sandbox-feature-pr)
Your own site
<a href="https://agentmods.dev/skills/decodingai-magazine/building-a-coding-agent-from-scratch-course/demo-5-sandbox-feature-pr"><img src="https://agentmods.dev/badge/skills/decodingai-magazine/building-a-coding-agent-from-scratch-course/demo-5-sandbox-feature-pr/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 demo-5-sandbox-feature-pr

Your own site · 80×15
<a href="https://agentmods.dev/skills/decodingai-magazine/building-a-coding-agent-from-scratch-course/demo-5-sandbox-feature-pr"><img src="https://agentmods.dev/badge/skills/decodingai-magazine/building-a-coding-agent-from-scratch-course/demo-5-sandbox-feature-pr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,247 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Tool Misuse · line 74
    Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
    Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
How audits are shown
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 $0.00060 $0.01247
Opus 5 $0.00030 $0.00624
Sonnet 5 $0.00012 $0.00249
Haiku 4.5 $0.00006 $0.00125

Measured 12d ago against content hash b163c95c8688, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

demo-5-sandbox-feature-pr 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 12d 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.

.decode/skills/demo-5-sandbox-feature-pr/SKILL.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

The meta demo: decode improves decode. Run decode inside an isolated sandbox Workspace that is a clone of this very course repo, plan and implement one small self-contained feature there, and let the harness ship the work back as a branch you turn into a draft PR.

Nothing the model does touches your host checkout — the Workspace is an isolated clone, and the branch only lands on your host through Hand-back (ADR-0012 §8).

1. Launch decode against a sandboxed clone of the course repo (human step)

Sandbox mode is selected by the SANDBOX_MODE environment variable — it is an env var, not a command-line flag; the repo to clone into the Workspace is the --repo flag. Launch the local docker rung (Docker must be running):

SANDBOX_MODE=docker decode --repo [email protected]:decodingai-magazine/building-a-coding-agent-from-scratch-course.git

This clones the course repo into the isolated Workspace (/workspace ≡ host .decode/sandbox) and drops you into the REPL, with bash and the file tools scoped to that clone.

To run the same demo on the remote rung instead, swap SANDBOX_MODE=docker for SANDBOX_MODE=modal — everything else is identical (Modal credentials must be configured).

2. Plan the feature — in plan mode

If you are decode reading this inside the Workspace, start here — step 1 is the human's launch command, already done; do NOT try to run decode yourself. Enter plan mode by calling enter_plan_mode with no arguments (it takes none — you present the plan later, to exit_plan_mode), explore the code read-only, then present a short plan before touching anything. Pick ONE feature — small, self-contained, provable in a single session:

  • A decode --version flag that prints the installed package version, plus its unit test.
  • One small pure helper (e.g. in tools/ or entities/) with a focused unit test.
  • A scoped docstring/README fix that resolves a real inaccuracy you found while exploring.

The plan should name the files to touch, the test that proves the feature, and nothing else. Exit plan mode (exit_plan_mode) once the human approves it.

Read the full file on GitHub · 102 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. 12d ago First seen · 102 lines · 60 tokens per session scan A b163c95c8688

Subscribe to this mod's changes

demo-5-sandbox-feature-pr is a skill published in the GitHub repository decodingai-magazine/building-a-coding-agent-from-scratch-course (387 stars, last pushed today), licensed Apache-2.0. It adds 60 tokens to every session and 1,247 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

aidlc-portfolio

Coordinate multiple AI-DLC workflows across repositories and Git worktrees using an evidence-backed portfolio catalog and deterministic workspace tooling. Use when initializing an AI-DLC portfolio workspace, discovering organization or business context, registering projects and dependencies, creating child intents and…

awslabs/cli-agent-orchestrator · 74 tokens

gentle-ai-work-unit-commits

Plan commits as reviewable work units. Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code.

Gentleman-Programming/gentle-pi · 36 tokens

michel-cli-demo-recorder

Produce proof-of-execution demos of the Packmind CLI (packmind-cli) as terminal-styled images (colors and formatting preserved exactly), for embedding in a GitHub PR. Renders a crisp master SVG and rasterizes it to a PNG — the PNG is what you embed, because GitHub does not render SVG in PR/issue bodies. Use this…

PackmindHub/packmind · 212 tokens

michel-monitor-pull-request-github-actions

Diagnose a failed, stuck, or never-triggered CI run on a GitHub PR, apply a local fix if possible, push it, and document the result in a single running PR comment. Invoke whenever Michel's CI monitor loop triggers with anyfailure, stuck, or nottriggered — the bash loop already handles pending and allgreen silently, so…

PackmindHub/packmind · 97 tokens

git-commit-smart

Generates meaningful, conventional commit messages automatically. Use when committing code changes. Analyzes diff to create descriptive commits following best practices.

majiayu000/spellbook · 32 tokens

review-gate

Use before an agent-produced diff is committed, pushed, opened as a PR, merged, landed, or applied to user files when explicit implementation approval is missing. Trigger for review gate, review pack, approve before landing, diff first then land, human approval, merge gate, commit gate, push gate, or PR readiness.…

majiayu000/spellbook · 95 tokens