design

A design workflow for turning complex or high-risk Devora changes into a checked project plan. It uses project status, governance, quality information, source material, and an active Change record.

In plain words
What is it for?
Use it to clarify requirements, inspect a repository and related files or links, set up a Devora Change, record its sources, and prepare the design work.
Why use it?
It reduces the risk of implementing an unclear requirement or overlooking project rules, existing work, or important evidence.

Command

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 commands/cheney369/devora/design
Clone the repo
git clone --depth 1 https://github.com/cheney369/Devora
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 685 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 $0.00021 $0.00685
Opus 5 $0.00010 $0.00342
Sonnet 5 $0.00004 $0.00137
Haiku 4.5 $0.00002 $0.00068

Measured 2d ago against content hash aced1e86cc2c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

design 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.

templates/commands/design.md · 21 lines

How it starts

The opening of the file, as written. The whole thing — 21 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Devora Design

User input

$ARGUMENTS
  1. Run devora status --json, devora govern status --json, devora govern drift --json, and devora quality status --json. Read the relevant project context, repository evidence, active Change, project Skills, company policies, and detected quality baseline. Confirm that each materially relevant Governance scope is current and complete as ready or limited; re-govern drifted or blocked scopes first. If no Change is active, derive a lowercase kebab-case name and its quality types; for a complex project also derive the owning module and run devora change start <name> --module <module> --scope <governance-scope> --type <type> --json, repeating options when needed. Omit the module only for a flat project.
  2. Run devora change setup design --json. Treat the input as free-form: it may include text, files, directories, images, tickets, designs, or links. When a source materially contributes to the requirement, register it with devora change source record; use a project-relative path for local material and a version/digest when the Agent can observe one for a remote source. Record what was actually read, and mark inaccessible material unavailable instead of inventing its contents. Trivial prompt-only work does not need source registration.
  3. Separate confirmed evidence, inference, and unresolved decisions. For Change-specific conflicts, gaps, or ambiguity, use devora change requirement clarify with the related source IDs; resolve only from an explicit answer or evidence with requirement resolve. Use a bounded Governance scope instead when the conclusion is durable project knowledge. Clarify only choices that materially alter product behavior, business controls, safety, or architecture and cannot be inferred safely.
  4. Assess technical and business risks, confirm L1-L4, and ensure every L3/L4 risk has preventive, detective, approval, or recovery controls. Inspect the generated minimum matrix for the selected frontend, browser, accessibility, API, database, permission, dependency, SAST/DAST, recovery, organization-policy, and cross-repository dimensions. Include every validation ID inherited from Governance and company policy; apply only approved exceptions whose scope and expiry match the Change. Add further material checks when needed and do not weaken required policy checks.
  5. Update change.md with the sources actually read, unified behavior, acceptance criteria, resolved limitations, allowed and protected paths, risks and controls, approach, validation plan, and approval conditions. For registered sources, run devora change requirement confirm --summary <baseline> --acceptance <criterion> --actor <authority> --json, repeating acceptance criteria. This freezes the current source signatures; pending, drifted, or materially unresolved inputs block confirmation. Run devora change ensure --tasks --json only when the work benefits from an explicit checklist.
  6. When the design is implementable, run devora change complete design --json. Requirement blockers prevent completion and Build entry. Do not create business code during Design.

Read the full file on GitHub · 21 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 · 21 lines · 21 tokens per session scan A aced1e86cc2c

Subscribe to this mod's changes

design is a command published in the GitHub repository cheney369/Devora (255 stars, last pushed 4d ago), licensed Apache-2.0. It adds 21 tokens to every session and 685 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 2026-08-30.