swarm-pi-scaffold

swarm-pi-scaffold is a skill for Claude Code, Codex from JiaWeiXie/swarm-pi-code-plugin. It costs 52 tokens per session (442 once invoked), scanned A, original, MIT.

A supervised way to start a new software project from an approved written specification. It works in an isolated staging area before changes are added to the target.

In plain words
What is it for?
Use it to plan and create an empty project, or to explicitly adopt an existing non-Git folder after reviewing its contents. It defines the runtime, package manager, structure, dependencies, scripts, and completion checks.
Why use it?
It reduces the risk of creating the wrong files or changing an existing project accidentally. The required review, rollback, and verification steps make the result easier to check.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present.

Part of the swarm-pi-code-plugin plugin — 10 skills, 2 agents, 1 hook shipped together

Good fit Use it to plan and create an empty project, or to explicitly adopt an existing non-Git folder after reviewing its contents. It defines the runtime, package manager, structure, dependencies, scripts, and completion checks.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jiaweixie/swarm-pi-code-plugin/swarm-pi-scaffold
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 JiaWeiXie/swarm-pi-code-plugin --skill swarm-pi-scaffold
Clone the repo
git clone --depth 1 https://github.com/JiaWeiXie/swarm-pi-code-plugin

Made for: Claude Code, Codex.

Or install swarm-pi-code-plugin, the plugin that ships this one along with the rest of its 10 skills, 2 agents, 1 hook.

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 swarm-pi-scaffold

README.md
[![agentmods](https://agentmods.dev/badge/skills/jiaweixie/swarm-pi-code-plugin/swarm-pi-scaffold.svg)](https://agentmods.dev/skills/jiaweixie/swarm-pi-code-plugin/swarm-pi-scaffold)
Your own site
<a href="https://agentmods.dev/skills/jiaweixie/swarm-pi-code-plugin/swarm-pi-scaffold"><img src="https://agentmods.dev/badge/skills/jiaweixie/swarm-pi-code-plugin/swarm-pi-scaffold.svg" alt="Measured on agentmods" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 442 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.
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 $0.00052 $0.00442
Opus 5 $0.00026 $0.00221
Sonnet 5 $0.00010 $0.00088
Haiku 4.5 $0.00005 $0.00044

Measured 8d ago against content hash e6555997de4a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

swarm-pi-scaffold 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 8d 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.

plugins/swarm-pi-code-plugin/skills/swarm-pi-scaffold/SKILL.md · 30 lines

What it actually says

Scaffold A Project With Pi

Follow the Skill Control Loop. Load Resource-Aware Execution before expensive or recursive scaffold commands.

  1. Run $RUNNER plan --host "$HOST" --role project-architect --prompt-file "$PROMPT_FILE" --execution-mode "$EXECUTION_MODE" --approval-mode "$APPROVAL_MODE" --json to draft a version 1 ScaffoldSpec. Use the control loop for every non-terminal result.
  2. Require request, project name, target mode, runtime, package manager, structure, dependencies, lifecycle-script policy, observable completion criteria, and sequential verification. Present the complete spec before mutation.
  3. After explicit approval, run $RUNNER scaffold --host "$HOST" --role scaffolder --spec-file "$SPEC_FILE" --target "$TARGET" --execution-mode "$EXECUTION_MODE" --approval-mode "$APPROVAL_MODE" --json.
  4. Eligible staging is exact, in-scope, fully reversible, and paired with rollback and verification. Adoption and materialization remain user decisions.
  5. Add --adopt-existing only after the user approves the target inventory and targetMode: adopt.
  6. Complete only when provenance, changed files, and fresh verification satisfy the approved spec. After explicit approval, materialize only a deliverable: true artifact through $RUNNER jobs materialize --job <id> --target "$TARGET" --json.

The trusted control plane owns target fencing, staging metadata, the initial artifact commit, and materialization; Pi produces the staged artifact.

Files

What ships with it

1 file 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.

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. 8d ago First seen · 30 lines · 52 tokens per session scan A e6555997de4a

Subscribe to this mod's changes

swarm-pi-scaffold is a skill published in the GitHub repository JiaWeiXie/swarm-pi-code-plugin (2 stars, last pushed 4d ago), licensed MIT. It adds 52 tokens to every session and 442 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 2026-08-31.