pdca

A continuous-improvement method that repeats four steps: plan a measurable change, try it, check the result, and keep or revise it.

In plain words
What is it for?
Use it to reduce defects, shorten processing time, lower error counts, or improve other repeatable processes.
Why use it?
It replaces guesswork with small, measured experiments and repeated learning.

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/tupe12334/instinct/pdca
Any agent
npx skills add tupe12334/instinct --skill pdca
Clone the repo
git clone --depth 1 https://github.com/tupe12334/instinct

Made for: Claude Code, Codex.

Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,862 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 $0.00017 $0.01862
Opus 5 $0.00009 $0.00931
Sonnet 5 $0.00003 $0.00372
Haiku 4.5 $0.00002 $0.00186

Measured 2d ago against content hash ab145340ff3e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pdca 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 2d 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/pdca/SKILL.md · 131 lines

How it starts

The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PDCA Cycle (Plan–Do–Check–Act)

Overview

PDCA is a four-phase iterative loop for solving problems and improving processes. Each cycle produces a tested change; repeat until the target condition is reached. Also called the Deming Wheel or Shewhart Cycle.

          ┌─────────────────────────────┐
          │                             │
     ┌────▼────┐               ┌────────┴────┐
     │  PLAN   │               │     ACT     │
     │ Define  │               │ Standardize │
     │ target  │               │  or re-plan │
     └────┬────┘               └────────▲────┘
          │                             │
     ┌────▼────┐               ┌────────┴────┐
     │   DO    │──────────────►│    CHECK    │
     │ Execute │               │  Measure &  │
     │ on small│               │   compare   │
     │  scale  │               └─────────────┘
     └─────────┘

PDCA is most effective on measurable, repeatable processes — defect rates, cycle times, conversion rates, error counts.

Phase Definitions

Plan — Identify the gap and design a countermeasure

  • State the problem in measurable terms: current value vs. target value.
  • Root-cause analysis before jumping to solutions (use Five Whys or fishbone if needed).
  • Define one hypothesis: "If we change X, we expect Y to improve by Z."
  • Specify success criteria, measurement method, and timeline up front.

Do — Execute the change at small scale

  • Run a controlled pilot or time-boxed experiment — not a full rollout.
  • Keep scope small enough to be reversible in hours or days.
  • Document what was done, who did it, and any deviations from the plan.
  • Collect raw data during execution — do not rely on memory after the fact.

Check — Compare results to the prediction

  • Measure the same metric(s) defined in Plan.
  • Did results match the hypothesis? If not, why?
  • Separate signal from noise: was the sample size or duration enough to draw a conclusion?
  • List side effects — unintended changes to adjacent metrics.

Read the full file on GitHub · 131 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. 2d ago First seen · 131 lines · 17 tokens per session scan A ab145340ff3e

Subscribe to this mod's changes

pdca is a skill published in the GitHub repository tupe12334/instinct (1 stars, last pushed 16d ago), licensed MIT. It adds 17 tokens to every session and 1,862 once invoked, about $0.0001 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.