spec-redesign

spec-redesign is a command for coding agents from nicelight/DevRails-26. It costs 15 tokens per session (841 once invoked), scanned A, original, MIT.

A controlled way to revise an already accepted software design or shared contract, meaning an agreement about how parts of the system work together.

In plain words
What is it for?
Use it when an accepted backbone, specification, architecture decision, or shared contract must change and its linked features, tasks, and review evidence need updating.
Why use it?
It limits design changes to an accepted decision and the canonical files affected by it, while preserving completed work and unrelated approvals.

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/nicelight/devrails-26/spec-redesign
Clone the repo
git clone --depth 1 https://github.com/nicelight/DevRails-26

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 spec-redesign

README.md
[![agentmods](https://agentmods.dev/badge/commands/nicelight/devrails-26/spec-redesign.svg)](https://agentmods.dev/commands/nicelight/devrails-26/spec-redesign)
Your own site
<a href="https://agentmods.dev/commands/nicelight/devrails-26/spec-redesign"><img src="https://agentmods.dev/badge/commands/nicelight/devrails-26/spec-redesign.svg" alt="Measured on agentmods" height="20"></a>
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 841 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 $0.00015 $0.00841
Opus 5 $0.00008 $0.00420
Sonnet 5 $0.00003 $0.00168
Haiku 4.5 $0.00002 $0.00084

Measured 4d ago against content hash d3a207d83ca7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

spec-redesign 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 4d 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/_shared/references/commands/spec-redesign.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/spec-redesign - Accepted design change gate

<input_contract> Require:

  • Global Backbone Status complete|minimal with positive Planning Revision;
  • the accepted change or exact unresolved operator decision;
  • current canonical specs, feature links, task plans/cards, and review evidence needed to trace consumers and planning impact;
  • .memory-bank/workflows/sdd-design-contract.md;
  • .memory-bank/workflows/execute-loop.md#planning-redesign-boundary and #fresh-feature-tasking-boundary.

If no successful positive-revision backbone exists, route to /spec-design. If the requested target change is not authoritative, obtain the operator-owned decision before changing canonical contracts. </input_contract>

<hard_invariants>

  • Change only the owning canonical backbone, spec, ADR, Foundation, feature, or registry links required by the accepted decision.
  • Do not create task records, plans, revision history, impact registries, lifecycle, schema, or a parallel review system. Bounded routing uses only the feature-body marker below.
  • Preserve task lifecycle, completed evidence, protocols, and unaffected approvals.
  • Do not use revision mismatch as impact proof. Establish semantic impact before deciding whether revision changes.
  • Do not revisit Foundation unless its decision or executable baseline contract is affected. </hard_invariants>

<operator_decisions> Apply the shared authority and operator-decision boundary. Unattended flow uses the existing blocking halt and names /spec-redesign as the resume route. </operator_decisions>

<required_outputs> Apply the SDD Design Contract to the accepted delta: update its canonical owner, every affected canonical consumer, registry links, and affected feature links. Update backbone status/matrix/mode or Foundation only when their owned semantics actually changed.

Classify impact under the loaded Planning Redesign Boundary. Report the none|bounded|global verdict, changed planning semantics or the evidence that they were preserved, exact affected features, Planning Revision before/after, and Foundation impact. If the impact boundary cannot be proved, return blocked without changing revision.

Reconcile bounded|global affected features one at a time through the Fresh Feature Tasking Boundary. For bounded, add PLANNING_RECONCILIATION_REQUIRED only to affected task-linked feature bodies whose planning needs repair; do not change feature frontmatter, Global Backbone Status, or Planning Revision. Unaffected features remain eligible. Rerun Foundation planning only when its decision or executable baseline changed. </required_outputs>

<agent_discretion> Choose the minimum reading, trace, artifact edits, and validation sufficient to prove the verdict. Reuse current accepted artifact shapes and canonical paths. </agent_discretion>

<handoff_contract> Report changed contracts, impact verdict and evidence, Planning Revision before/after, affected features, Foundation impact, blockers, and one next command:

  • none -> resume the prior owner;
  • bounded|global -> next affected /spec-auto FT-<NNN> when feature design needs reconciliation, otherwise fresh /feature-to-tasks FT-<NNN>;
  • blocked -> obtain the named decision/evidence and rerun /spec-redesign. </handoff_contract>

Read the full file on GitHub · 93 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. 4d ago First seen · 93 lines · 15 tokens per session scan A d3a207d83ca7

Subscribe to this mod's changes

spec-redesign is a command published in the GitHub repository nicelight/DevRails-26 (22 stars, last pushed 6d ago), licensed MIT. It adds 15 tokens to every session and 841 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.