documentation-criteria

A guide for deciding which technical documents a code change needs, including a PRD, design document, work plan, or ADR. An ADR is a short record of an important architecture decision.

In plain words
What is it for?
Classifying changes, deciding documentation scope, and determining the order for creating requirements, design, planning, and architecture-decision documents.
Why use it?
It prevents both unnecessary paperwork for small changes and missing design records for work that crosses boundaries or creates lasting decisions. The choice is based on the change's decision burden, not just its file count.

Skill for Claude CodeCodex

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/shinpr/agentic-code/documentation-criteria
Any agent
npx skills add shinpr/agentic-code --skill documentation-criteria
Clone the repo
git clone --depth 1 https://github.com/shinpr/agentic-code

Made for: Claude Code, Codex.

Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,141 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 $0.00032 $0.01141
Opus 5 $0.00016 $0.00571
Sonnet 5 $0.00006 $0.00228
Haiku 4.5 $0.00003 $0.00114

Measured 3d ago against content hash 6892a38afeb2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

documentation-criteria 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.

.agents/skills/documentation-criteria/SKILL.md · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Documentation Creation Criteria

Creation Decision Matrix

Structural Scale Required Documents Creation Order
Small None Direct task execution
Medium Design Doc → Work Plan Start with Design Doc
Large PRD → Design Doc → Work Plan Continue after PRD approval

Insert an ADR immediately before the Design Doc only when a current-scope decision passes both ADR filters below. A qualifying ADR decision sets the scale floor to Medium.

Structural Scale

Classify the decision burden, not repository layout. File count is supporting evidence only.

Scale Structural condition
Small One coherent outcome follows existing patterns within one responsibility boundary
Medium One coherent outcome coordinates across a boundary or requires a durable design decision
Large Multiple independently valuable outcomes require separate design decisions

Multiple files or layers that serve one coherent outcome remain Medium. Large applies only when separate outcomes require separate design decisions.

ADR Creation Conditions

Check accepted ADRs that govern the changed responsibility, then apply both filters to each technical topic in the confirmed scope:

  1. Choice requires judgment: Current requirements, accepted decisions, and representative repository patterns support at least two credible, materially distinct options.
  2. Decision is durable: The choice materially changes a responsibility, dependency direction, shared contract, persistence model, technology dependency, reversibility, or lifecycle cost that future work must preserve.

Create one ADR for each topic that passes both filters. Keep a topic in the Design Doc when one repository-supported implementation is evident or the choice remains cheaply reversible.

Qualifying durable choices can include:

  • introducing or replacing a technology, platform, storage model, or external dependency;
  • changing ownership, dependency direction, a trust boundary, or a shared public contract when credible alternatives exist;
  • reversing or superseding an accepted architecture decision;
  • selecting an irreversible or high-cost compatibility or data migration strategy.

Read the full file on GitHub · 117 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 · 117 lines · 32 tokens per session scan A 6892a38afeb2

Subscribe to this mod's changes

documentation-criteria is a skill published in the GitHub repository shinpr/agentic-code (49 stars, last pushed 4d ago), licensed MIT. It adds 32 tokens to every session and 1,141 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 2026-08-30.