strata:decide

strata:decide is a skill for Claude Code, Codex from gideondk/strata. It costs 92 tokens per session (1,494 once invoked), scanned A, original, MPL-2.0.

A workflow for recording important technical choices as Markdown architectural decision records (ADRs). An ADR explains the context, decision, consequences, and alternatives behind a choice.

In plain words
What is it for?
Use it when choosing between reasonable options, accepting a lasting trade-off, or discovering a constraint worth remembering. It can create records with statuses such as proposed, accepted, rejected, or superseded.
Why use it?
It preserves the reasons for decisions after the original discussion is forgotten. A duplicate check helps prevent multiple records from documenting the same choice.

Skill for Claude CodeCodex

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the strata plugin — 24 skills, 2 agents, 5 hooks, 1 MCP server 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/gideondk/strata/decide
Any agent
npx skills add gideondk/strata --skill decide
Clone the repo
git clone --depth 1 https://github.com/gideondk/strata

Made for: Claude Code, Codex.

Or install strata, the plugin that ships this one along with the rest of its 24 skills, 2 agents, 5 hooks, 1 MCP server.

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 strata:decide

README.md
[![agentmods](https://agentmods.dev/badge/skills/gideondk/strata/decide.svg)](https://agentmods.dev/skills/gideondk/strata/decide)
Your own site
<a href="https://agentmods.dev/skills/gideondk/strata/decide"><img src="https://agentmods.dev/badge/skills/gideondk/strata/decide.svg" alt="Measured on agentmods" height="20"></a>
Per session 92 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,494 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 $0.00092 $0.01494
Opus 5 $0.00046 $0.00747
Sonnet 5 $0.00018 $0.00299
Haiku 4.5 $0.00009 $0.00149

Measured 3d ago against content hash 1e484b7d5049, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

strata:decide 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 3d 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.

skills/decide/SKILL.md · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

strata:decide

ADRs (Architectural Decision Records) capture why something is the way it is. They're durable team memory, code rots, ADRs explain it.

When to use

  • A choice between two reasonable options where future readers will wonder why.
  • A constraint discovered the hard way that should be remembered.
  • A trade-off that locks something in.

Not for: routine implementation choices, style preferences, or anything fully Explained by the code itself.

How

User runs /strata:decide <title>. You:

  1. Draft the body using the MADR sections: Context, Decision, Consequences, Alternatives considered. Be concrete. No fluff.
  2. Pick the status: proposed (default, opens a discussion), accepted (the team has agreed), or superseded/rejected/deprecated.
  3. Recall before you write — check for an existing decision first. Run the dedup precheck so you don't fork a parallel ADR for a choice that's already recorded (the "agents battling on ADRs" failure):
"${CLAUDE_PLUGIN_ROOT}/bin/strata" decide \
  --title "<title>" --check-only <<'STRATA_ADR'
<the body you drafted>
STRATA_ADR

It prints JSON {recommendation, candidates} and writes nothing to the vault (it may refresh the disposable index cache). Run it on its own — --check-only is a no-op alongside --supersedes/--no-dedup. Adjudicate:

  • clear → no overlap; proceed to step 4 (ADD).
  • warn / block → read the candidate(s) and decide, surfacing it to the user:
    • UPDATE — same decision, just refined → edit that note, don't create a new one.
    • SUPERSEDE — this replaces an earlier decision → write with --supersedes <slug> (see below).
    • NO-OP — already captured → write nothing; tell the user.
    • ADD — genuinely distinct despite the overlap → write with --ack-new (a block refuses to write without it).

Use the candidates to ground the draft. Even on clear, the precheck returns the nearest existing notes. Before writing, skim the top 2-3: match their section structure, reuse house terminology, and [[wikilink]] the genuinely related ones in your body. A well-linked draft beats an orphan.

Read the full file on GitHub · 128 lines

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. 3d ago First seen · 128 lines · 92 tokens per session scan A 1e484b7d5049

Subscribe to this mod's changes

strata:decide is a skill published in the GitHub repository gideondk/strata (5 stars, last pushed 1mo ago), licensed MPL-2.0. It adds 92 tokens to every session and 1,494 once invoked, about $0.0005 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

my-wiki

Manage local OKF-compatible Markdown My Wiki vaults with an AI agent. Use for capturing webpages, PDFs, Office documents, notes, images, folders, and ZIP bundles as References; maintaining Reference-to-Concept evidence links; searching or answering from a vault; checking or repairing vault health; switching among…

NimaChu/my-wiki · 78 tokens

save-to-favorites

The single complete Pickoo workflow for new Xiaohongshu, WeChat, Douyin, Bilibili, Xiaoyuzhou, podcast, music, article/blog, or general web links. Use for 收藏、保存、收录、抓取、归档、拆解、分析、OCR、ASR or 完整处理 from Codex, WorkBuddy, Hermes, Claude, or Claudian. It owns intake and the complete downstream workflow; obsolete standalone…

KristenPan/pickoo-your-favorites · 110 tokens

asset-review-agent

Independently review source-extracted quote, viewpoint, hook, and structure candidates. Image and shot assets are outside automatic review and enter only after explicit user interaction.

KristenPan/pickoo-your-favorites · 37 tokens

phase-orchestrator

Orchestrates phase-based implementation plans using the host's todo tracker and subagents for implementation, review, validation, default phase commits, plan finalization, and a final end-to-end review. Delegates work through the companion phase-implementer, phase-reviewer, and phase-final-reviewer skills and consumes…

hraness/kb · 101 tokens

answer-processing

Use whenever the user uploads a hand-written or scanned answer PDF to be graded against a reference solution. Converts answer PDFs in answers/.pdf to markdown in answers/converted/.md using the pdf skill (OCR as needed), then performs strategy-based grading against converted/solutions/.md or quizzes/answers.md.…

OPTIMETA/PAIDEIA · 79 tokens

course-builder

Use whenever the user wants to ingest a new course's materials (lecture notes, textbook chapters, HW problems, HW solutions) and build the course-specific knowledge base — patterns.md (recurring solution techniques), coverage.md (HW-to-section map with 🔥 exam tiers + ⚠weak flags), and summary.md (topic tree). Invoked…

OPTIMETA/PAIDEIA · 119 tokens