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 agentmods add skills/cboone/agent-harness-plugins/refresh-project-scaffoldingnpx skills add cboone/agent-harness-plugins --skill refresh-project-scaffoldinggit clone --depth 1 https://github.com/cboone/agent-harness-pluginsWrote 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/cboone/agent-harness-plugins/refresh-project-scaffolding)<a href="https://agentmods.dev/skills/cboone/agent-harness-plugins/refresh-project-scaffolding"><img src="https://agentmods.dev/badge/skills/cboone/agent-harness-plugins/refresh-project-scaffolding.svg" alt="Measured on agentmods" 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 | $0.00119 | $0.05455 |
| Opus 5 | $0.00060 | $0.02728 |
| Sonnet 5 | $0.00024 | $0.01091 |
| Haiku 4.5 | $0.00012 | $0.00545 |
Grade A, and why
refresh-project-scaffolding 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.
How it starts
The opening of the file, as written. The whole thing — 510 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Refresh Project Scaffolding
Refresh the current repository's existing scaffolding against the latest templates and best practices from the agent-harness-plugins ecosystem. Detect which tools have been used, compare existing files against current standards, present a plan of what's out of date, confirm with the user, and apply targeted updates.
This is the maintenance companion to bootstrap-project: bootstrap sets things up, this keeps them current.
Scope: This skill audits tools already in use and updates their files to match current templates. For tools that are partially configured, it can restore missing expected files. It does not set up tools that were never used; for initial setup, use the bootstrap-project skill or the individual tool.
Workflow
1. Detect Project Type
Scan for language and framework markers using Glob. Exclude node_modules/, .yarn/, vendor/, and other dependency directories from all searches.
| Marker(s) | Project type |
|---|---|
go.mod + (main.go or cmd/) |
Go CLI |
go.mod without main.go or cmd/ |
Go library |
package.json + JS/TS source files |
JavaScript/TypeScript |
pyproject.toml, setup.py, requirements.txt |
Python |
Cargo.toml |
Rust |
Gemfile, *.gemspec |
Ruby |
Package.swift |
Swift |
*.sh, bin/*, scripts/* |
Shell |
If multiple types are detected (monorepo), note all of them.
2. Detect Which Tools Have Been Used
For each tool in the ecosystem, check for its signature artifacts. Only tools whose artifacts are found will be audited.
| Tool | Signature artifacts |
|---|---|
scaffold-new-repo |
LICENSE + README.md + .gitignore |
scaffold-go-cli |
go.mod + cmd/ + .goreleaser.yml + .github/workflows/release.yml |
scaffold-go-library |
go.mod (no cmd/) + .golangci.yml + .github/workflows/ci.yml |
set-up-ci |
.github/workflows/ci.yml |
set-up-linters |
.editorconfig or .prettierrc.json or .golangci.yml |
set-up-secret-scanning |
.github/workflows/gitleaks.yml or .github/workflows/trufflehog.yml |
add-goreleaser-homebrew |
.goreleaser.yml with brews: section + .github/workflows/release.yml |
add-community-files |
CONTRIBUTING.md + CODE_OF_CONDUCT.md |
add-scrut-cli-tests |
tests/scrut/ directory |
set-up-installers |
Formula/ |
optimize-runner-usage |
concurrency: key in any .github/workflows/*.yml |
clean-up-agent-config |
AGENTS.md or (CLAUDE.md + .claude/settings.json) |
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.
- 5d ago First seen · 510 lines · 119 tokens per session scan A a561b42df62b
refresh-project-scaffolding is a skill published in the GitHub repository cboone/agent-harness-plugins (2 stars, last pushed 1mo ago), licensed MIT. It adds 119 tokens to every session and 5,455 once invoked, about $0.0006 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.
Other skills, from other repositories
uctm-init
Initialize uc-taskmanager for the current project. Creates works/ directory and configures Bash permissions in .claude/settings.local.json. Use when the user says "uctm init", "initialize uctm", "uctm 초기화", or "초기화".
work-pipeline
Triggers the WORK-PIPELINE when a user request starts with a [] tag (e.g., [new-feature], [bugfix], [WORK start]). Use this skill whenever you detect a [] tag at the beginning of a user message.
feature-spec
Creates a complete product feature specification with acceptance criteria, scope, dependencies, and risks. Delegates to the Prometeo (PM) agent.
implement-feature
Implements a feature from its specification. Reads the spec, designs architecture, writes code and tests. Delegates to the Forja (Dev) agent.
sdd-pipeline
파이프라인 에이전트(specifier, planner, scheduler, builder, verifier, committer)가 참조하는 규칙/스키마 문서 모음.
best-practices
Searchable knowledge base of 152+ programming best practices across 30+ languages and frameworks. BM25-powered search over curated resources from industry leaders (Google, Airbnb, Uber, Mozilla, Shopify, OWASP).