write-spec

A command that turns requirements and planning material into a detailed specification for a new feature. The specification is saved as spec.md in the feature's spec folder.

In plain words
What is it for?
Use it after gathering requirements and any visual references to write a feature specification. A spec is a detailed description of what should be built and how it should behave.
Why use it?
It collects the intended behavior and constraints into one document before development tasks are created. This gives later planning work a clear source to follow.

Command for Claude Code

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/adawalli/nexus/write-spec
Clone the repo
git clone --depth 1 https://github.com/adawalli/nexus

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 158 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 $0.00000 $0.00158
Opus 5 $0.00000 $0.00079
Sonnet 5 $0.00000 $0.00032
Haiku 4.5 $0.00000 $0.00016

Measured 2d ago against content hash e86e495904a7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

write-spec 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.

.claude/commands/agent-os/write-spec.md · 24 lines

What it actually says

Spec Writing Process

You are creating a comprehensive specification for a new feature.

Use the spec-writer subagent to create the specification document for this spec:

Provide the spec-writer with:

  • The spec folder path (find the current one or the most recent in agent-os/specs/*/)
  • The requirements from planning/requirements.md
  • Any visual assets in planning/visuals/

The spec-writer will create spec.md inside the spec folder.

Once the spec-writer has created spec.md output the following to inform the user:

Your spec.md is ready!

✅ Spec document created: `[spec-path]`

NEXT STEP 👉 Run `/create-tasks` to generate your tasks list for this spec.
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 · 24 lines · 0 tokens per session scan A e86e495904a7

Subscribe to this mod's changes

write-spec is a command published in the GitHub repository adawalli/nexus (23 stars, last pushed 20d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 158 tokens. 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.