Jidoka Instruction Architecture

Build quality into agent instructions

One instruction architecture for humans and agents. Eight layers, each with a single job — and checks that stop the line the moment a layer drifts.

Scroll

Instructions sprawl, and nothing stops the drift.

Prompts pile up. Layers restate each other, jobs go stale, and nobody notices until an agent misbehaves. Jidoka takes the Toyota path: build quality into the process itself. One layered architecture where every layer owns a single job and carries a machine-checkable budget — so a defect traces to exactly one layer, and the line stops before it ships.

8
Layers
Most general to most specific
1
Job per layer
No layer restates another
0
Guesswork
Every defect localizes to one layer

Eight layers. Most general to most specific.

Each layer loads at the right moment and owns one concern. Auto-loaded layers stay budgeted so context never bloats; on-demand layers disclose only when the work calls for them.

L0
System Prompt

Harness mechanics: turns, tool calls, the completion signal. Nothing about your project.

L1
CLAUDE.md

Project identity — what it is, who it serves, and where to find its jobs and checklists.

L2
CONTRIBUTING.md & JTBD.md

Contribution standards and the jobs each persona hires the work to do.

L3
Agent Profile

One persona — voice, skill routing, and scope constraints. Boundaries, not steps.

L4
Agent References

Cross-cutting protocols shared across agents: memory, coordination, approval.

L5
Skill Procedure

The complete, imperative steps for one domain of work — no tribal knowledge required.

L6
Skill References

The data a procedure consults: templates, worked examples, lookup tables.

L7
Checklists

Binary verification at a pause point. No explanation — just confirmation.

What agents align to, and how alignment holds.

Three well-publicized ideas answer the halves of the problem — and together they explain why the layers are shaped the way they are, and why the checks stop the line.

Toyota
Jidoka

How quality holds. It is built into the process, not inspected in afterward — the checks halt at the first defect and never pass one downstream.

Christensen & Moesta
Jobs To Be Done

What agents align to. Every layer traces to the progress a persona seeks in a specific circumstance — not to a feature list.

Atul Gawande
The Checklist Manifesto

How alignment holds under load. Structured instructions keep existing knowledge consistently applied — by humans and agents alike.

Two gates. One at entry, one at exit.

Checklists never teach — they confirm; if an item needs explaining, the procedure above it is incomplete. Each gate is wrapped in a semantic <read_do_checklist> or <do_confirm_checklist> tag, so every pause point in the repository is one rg search away — no map required.

Entry gate
READ-DO

Read each item, then do it. Loads constraints into memory before the first line of work, when missing one sends everything in the wrong direction.

rg '<read_do_checklist'
Exit gate
DO-CONFIRM

Do from memory, then pause and confirm. Verifies nothing was missed before a commit, merge, or release — independent checks, no interruption mid-flow.

rg '<do_confirm_checklist'

Adopt it in three lines.

Install the skill pack. Tell Claude to set it up.

Terminal
cd my-repo/
apm install forwardimpact/jidoka-skills
echo "Set up Jidoka" | claude

Then wire the jidoka binary (or npx @forwardimpact/jidoka) into your checks, so the line stops at the first drifted layer. Read the full standard in JIDOKA.md.