technical-decisions

technical-decisions is a skill for Claude Code from juanmhidalgo/claude-plugins. It costs 33 tokens per session (1,127 once invoked), scanned A, original, MIT.

A decision guide for choosing between multiple valid ways to implement a code-review fix.

In plain words
What is it for?
Use it during code-review fixes when the change could affect architecture, public APIs, data models, dependencies, performance, or security.
Why use it?
It prevents an agent from silently making architectural, dependency, performance, security, or breaking-change decisions that belong to the developer.

Skill for Claude Code

Written for Claude Code: disallowed-tools in frontmatter. Also seen: names the NotebookEdit tool.

Part of the code-review plugin — 5 skills, 14 commands, 13 agents shipped together

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 skills/juanmhidalgo/claude-plugins/technical-decisions
Any agent
npx skills add juanmhidalgo/claude-plugins --skill technical-decisions
Clone the repo
git clone --depth 1 https://github.com/juanmhidalgo/claude-plugins

Made for: Claude Code.

Or install code-review, the plugin that ships this one along with the rest of its 5 skills, 14 commands, 13 agents.

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 technical-decisions

README.md
[![agentmods](https://agentmods.dev/badge/skills/juanmhidalgo/claude-plugins/technical-decisions.svg)](https://agentmods.dev/skills/juanmhidalgo/claude-plugins/technical-decisions)
Your own site
<a href="https://agentmods.dev/skills/juanmhidalgo/claude-plugins/technical-decisions"><img src="https://agentmods.dev/badge/skills/juanmhidalgo/claude-plugins/technical-decisions.svg" alt="Measured on agentmods" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,127 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 5.1 $0.00033 $0.01127
Opus 5 $0.00016 $0.00563
Sonnet 5 $0.00007 $0.00225
Haiku 4.5 $0.00003 $0.00113

Measured 6d ago against content hash 94646e7f21b9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

technical-decisions 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 6d 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.

code-review/skills/technical-decisions/SKILL.md · 152 lines

How it starts

The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Technical Decisions

Overview

When implementing fixes from code review, some require technical decisions that should be made by your human partner, not assumed.

Core principle: Ask before implementing when there are multiple valid approaches or the change has architectural implications.

When to Ask

BEFORE implementing a fix, check if it involves:

1. ARCHITECTURE: Changes to patterns, structure, or dependencies
2. TRADE-OFFS: Performance vs readability, DRY vs simplicity
3. SCOPE: Fix could be minimal or comprehensive
4. ALTERNATIVES: Multiple valid solutions exist
5. RISK: Change could affect other parts of the codebase
6. NEW DEPENDENCIES: Adding libraries or packages
7. BREAKING CHANGES: API changes, data migrations

Decision Categories

Always Ask

Situation Why
Adding new dependency Cost, maintenance, security implications
Changing public API Breaking changes affect consumers
Data model changes Migration complexity, data integrity
Architectural patterns Consistency across codebase
Performance optimizations Trade-offs with readability/complexity
Security-related fixes Risk of incomplete fix or new vulnerabilities

Implement Directly

Situation Why
Typos and formatting No decision needed
Missing imports Single correct answer
Obvious bug fixes Clear problem, clear solution
Adding tests for existing code Coverage, not architecture
Documentation updates Clarification, not design

The Ask Pattern

WHEN decision required:

1. IDENTIFY: What needs deciding
2. OPTIONS: List 2-3 valid approaches
3. TRADE-OFFS: Pros/cons of each
4. RECOMMENDATION: Your suggestion with reasoning
5. ASK: Let human partner decide

FORMAT:
"This fix requires a decision:

**Issue:** [What the review feedback asks for]

**Options:**
1. [Approach A] - [brief description]
   - Pros: [benefits]
   - Cons: [drawbacks]

2. [Approach B] - [brief description]
   - Pros: [benefits]
   - Cons: [drawbacks]

**Recommendation:** [Your suggestion] because [reasoning]

Which approach do you prefer?"

Read the full file on GitHub · 152 lines

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. 6d ago First seen · 152 lines · 33 tokens per session scan A 94646e7f21b9

Subscribe to this mod's changes

technical-decisions is a skill published in the GitHub repository juanmhidalgo/claude-plugins (8 stars, last pushed 11d ago), licensed MIT. It adds 33 tokens to every session and 1,127 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.

Related

Other skills, from other repositories

decision-records

Use when a hard-to-reverse choice (database, framework, vendor, auth model) must be frozen as an immutable numbered ADR — the context that forced it, the options weighed, the decision, consequences both ways — or superseded without erasing history. NOT a meeting recap (that is meeting-notes), NOT standing project…

ericrisco/rsc-harness · 76 tokens

system-design-patterns

Architecture patterns (monolith, microservices, CQRS, event-driven, api-gateway, scalability), ADR methodology, trade-off analysis, fitness functions, and deterministic ADR completeness scoring via executable script. Use proactively when making or reviewing significant architectural decisions, writing or auditing…

Everyone-Needs-A-Copilot/claude-copilot · 94 tokens

mk:advise

Turn a raw idea into ONE honest recommendation: interview one question at a time until the problem, requirements, goals, non-goals, and constraints are CONFIRMED, then deliver a single verdict — do, don't, cheaper alternatives, trade-offs, ordered checklist, success metrics. Required: the user wants exactly ONE…

ngocsangyem/MeowKit · 228 tokens

mk:memory

JSON-canonical session memory. Use when capturing session learnings, extracting patterns, or tracking costs — persists to .meowkit/memory JSON stores; matching Markdown files are generated views. Activates during Phase 0 (Orient) to load context and Phase 6 (Reflect) to persist it. NOT for weekly-cadence engineering…

ngocsangyem/MeowKit · 86 tokens

adr-documentation

Architecture Decision Records (ADR) documentation practice. Use when documenting architectural decisions, recording technical trade-offs, creating decision logs, or establishing architectural patterns. Trigger keywords - "ADR", "architecture decision", "decision record", "trade-offs", "architectural decision"…

MadAppGang/claude-code · 60 tokens

ask-ai-to-show-its-reasoning

Prompt patterns to extract transparent, first-principles logic, trade-off comparisons, and elimination criteria behind any AI recommendation.

alivirgo/Major-AI-Skills · 34 tokens