agentmods.dev

sii: Command for Claude Code

.claude/commands/new-decision.md

new-decision is a command for Claude Code from albertomarturelo/sii. It costs 0 tokens per session (361 once invoked), scanned A, original, MIT.

A guided workflow for recording an important software-architecture decision in an ADR, a short document explaining what was decided and why. It helps compare alternatives before creating the document.

In plain words
What is it for?
Writing a new decision document, comparing two or three approaches, and updating related project conventions when needed.
Why use it?
Important technical choices can otherwise remain undocumented or be debated repeatedly. This records the reasoning and keeps the project’s decision index up to date.

Command for Claude Code

Written for Claude Code: installed under .claude/.

This is albertomarturelo/sii's own configuration. It tells Claude Code how to work on sii itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything sii configures →

not rated 7repo 8d ago A scan 0 tokens original MIT
View source ↗ albertomarturelo/sii
Reuse

Borrowing it

Nothing to install: this file belongs to albertomarturelo/sii. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/albertomarturelo/sii/main/.claude/commands/new-decision.md
Clone the repo
git clone --depth 1 https://github.com/albertomarturelo/sii

Made for: Claude Code.

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 new-decision

README.md
[![agentmods](https://agentmods.dev/badge/commands/albertomarturelo/sii/new-decision/github.svg)](https://agentmods.dev/commands/albertomarturelo/sii/new-decision)
Your own site
<a href="https://agentmods.dev/commands/albertomarturelo/sii/new-decision"><img src="https://agentmods.dev/badge/commands/albertomarturelo/sii/new-decision/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 new-decision

Your own site · 80×15
<a href="https://agentmods.dev/commands/albertomarturelo/sii/new-decision"><img src="https://agentmods.dev/badge/commands/albertomarturelo/sii/new-decision.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 361 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 $0.00000 $0.00361
Opus 5 $0.00000 $0.00180
Sonnet 5 $0.00000 $0.00072
Haiku 4.5 $0.00000 $0.00036

Measured 9d ago against content hash 19b1803895a6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

new-decision 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 9d 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.

.claude/commands/new-decision.md · 37 lines

What it actually says

Guide the user through documenting a new architectural decision.

  1. Ask: "What decision needs to be made?"

  2. Help articulate the Context: what problem are we solving, what constraints apply, what is the trigger for deciding now.

  3. Propose 2–3 alternatives with explicit pros and cons. Do not short-circuit to your favorite — the user has to choose.

  4. Once chosen, generate a new ADR file at docs/decisions/<NNN>-<slug>.md following docs/decisions/TEMPLATE.md exactly. Increment <NNN> to one above the highest existing.

  5. Update docs/decisions/_index.md with the new entry (one row).

Constraints:

  • The ADR MUST be ≤100 lines.
  • If the decision affects a recurring convention, also update docs/CONVENTIONS.md and reference the new ADR there.
  • Do NOT skip "Alternatives Considered". Future sessions need to know why the rejected paths were rejected, or they'll re-litigate.
  • When a rule is ported from the Python sii-cli, cite the source ADR (e.g. "lineage: sii-py ADR-019") rather than re-deriving it.
  • Status starts as Accepted unless the user explicitly asks for Proposed.

When the ADR file is written, stop. The user reviews it before the implementation that depends on it begins.

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. 9d ago First seen · 37 lines · 0 tokens per session scan A 19b1803895a6

Subscribe to this mod's changes

new-decision is a command published in the GitHub repository albertomarturelo/sii (7 stars, last pushed 8d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 361 tokens. 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.

PlanningWriting and docsanthropicchileclaudeclimcpmodel-context-protocol
Related

Other commands, from other repositories

atomic-plan

Write a design doc (concepts, business rules, approaches) and a checkpoint-table spec (contract) for non-trivial work; inline spec only for trivial. Gauges triviality; loops spec authoring with subagents. Human-facing artifact, Mermaid diagrams allowed.

damusix/atomic-claude · 54 tokens

review-branch

Review the current branch's diff against base by dispatching atomic-reviewer. No orchestration loop, no spec required — pre-flight before /commit pr or /commit merge.

damusix/atomic-claude · 35 tokens

create-task-list.template

This prompt was authored for Claude-style slash workflows. In Codex runtime, adapt tool calls as follows.

evan043/claude-cli-advanced-starter-pack · 0 tokens

adopt-roadmap.template

This prompt was authored for Claude-style slash workflows. In Codex runtime, adapt tool calls as follows.

evan043/claude-cli-advanced-starter-pack · 0 tokens

update-check.template

This prompt was authored for Claude-style slash workflows. In Codex runtime, adapt tool calls as follows.

evan043/claude-cli-advanced-starter-pack · 0 tokens

perf-profile.template

This prompt was authored for Claude-style slash workflows. In Codex runtime, adapt tool calls as follows.

evan043/claude-cli-advanced-starter-pack · 0 tokens