agentmods.dev

add-component

A command for adding selected CI/CD components to an existing repository. CI/CD means automated checks, security tasks and maintenance that run around code changes.

In plain words
What is it for?
Use it to plan or apply CI, security, Dependabot or maintenance files, review differences, and add the chosen starter configuration after approval.
Why use it?
It fills identified gaps without creating a new repository structure, while showing a dry-run plan before changing files.

Command for Claude Code

1 14d ago A scan 35 tokens original MIT
View the source file starter-series/create-starter
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 commands/starter-series/create-starter/add-component
Clone the repo
git clone --depth 1 https://github.com/starter-series/create-starter

Made for: Claude Code.

Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 472 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00035 $0.00472
Opus 5 $0.00017 $0.00236
Sonnet 5 $0.00007 $0.00094
Haiku 4.5 $0.00003 $0.00047

Measured yesterday against content hash 85792aac4ae5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

add-component 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 yesterday.

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.

.claude-plugin/commands/add-component.md · 41 lines

What it actually says

You are helping the user add Starter Series CI/CD components to an existing repo — the remediation step after an audit found gaps.

Steps

  1. Plan (dry-run) — call the add_component MCP tool with:

    • path: the absolute path of the user's repo
    • component: ci, security, dependabot, maintenance, or all (default all; if the user came from an audit_security finding, pick the group that covers it)
    • starter: omit to auto-detect; pass an explicit template id if detection warns about low confidence or the user disagrees
    • leave dry_run unset (defaults to true — nothing is written)

  2. Review the plan with the user — per file: create (new), identical (already matches), skip-exists (exists but differs — show the diff with git diff --no-index if the user wants to see it before overwriting).

  3. Apply — once the user approves, call add_component again with dry_run: false. If files were reported skip-exists and the user wants the starter's version, re-run with force: true — only after they've seen what they'd lose. The tool refuses a dirty git tree unless forced, so have them commit/stash first.

  4. Wire what needs hands — CD workflows are deliberately NOT lifted (they need per-repo secrets). If the user wants deploys, hand off to the deploy-setup skill next.

Do NOT

  • Force-overwrite without showing the user what differs first.
  • Lift onto a dirty tree by default — a clean tree keeps the change reviewable and revertable with one git checkout.
  • Touch application code; this command is for the .github/ pipeline layer plus SECURITY.md only.
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. yesterday First seen · 41 lines · 0 tokens per session scan A 85792aac4ae5

Subscribe to this mod's changes

add-component is a command published in the GitHub repository starter-series/create-starter (1 stars, last pushed 14d ago), licensed MIT. It adds 35 tokens to every session and 472 once invoked, about $0.0002 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.

Code reviewFrontendSecurityclaudeclaude-codeclaude-code-pluginclidevtools
Related

Other commands, from other repositories

test-e2e

Write end-to-end tests for critical user journeys.

mrwogu/promptscript · 9 tokens

test-integration

Write integration tests for component boundaries.

mrwogu/promptscript · 6 tokens

export

Design public API exports.

mrwogu/promptscript · 4 tokens

newpkg

Generate new package with Nx.

mrwogu/promptscript · 5 tokens

init

Initialize goal-flight state for a project.

simonrowland/goal-flight · 8 tokens

index

Command "index" from cesarandreslopez/tauri-agent-tools, covering command reference, command summary, categories, visual capture and dom inspection.

cesarandreslopez/tauri-agent-tools · 0 tokens