write-spec

A tool for writing an approved product specification: a durable description of what a software change must do and how it will be accepted.

In plain words
What is it for?
Use it to create, store, split, or update specifications for product capabilities that may be developed or released separately.
Why use it?
It turns a confirmed idea into a clear agreement before implementation begins, while avoiding decisions about the underlying technology.

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/rmjosea/agentic-sdlc-kit/write-spec
Any agent
npx skills add rmjosea/agentic-sdlc-kit --skill write-spec
Clone the repo
git clone --depth 1 https://github.com/rmjosea/agentic-sdlc-kit

Made for: Claude Code, Codex.

Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 810 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 $0.00062 $0.00810
Opus 5 $0.00031 $0.00405
Sonnet 5 $0.00012 $0.00162
Haiku 4.5 $0.00006 $0.00081

Measured 2d ago against content hash 70ea2e32219b, 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.

.agents/skills/write-spec/SKILL.md · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Write Product Specifications

Create the first stable artifact in the workflow. Define what must be true, not the implementation that will make it true.

Do not create a spec merely because code will change. Use one when product behavior needs a durable acceptance contract; use the direct or plan-only path from AGENTS.md when that contract would add no value.

Preconditions

Require an explicitly approved conversational understanding or equivalent authoritative input. If material product ambiguity remains, return to shape-idea.

Choose spec boundaries

Prefer one specification when the change has one cohesive outcome and shared rules. Split into multiple specifications when capabilities:

  • deliver independent user value;
  • can be accepted or released separately;
  • have distinct actors, rules, or lifecycles;
  • require independent planning;
  • would force multiple primary objectives into one document.

Split by capability, never by technical layer. Do not create separate frontend, backend, database, or API specs for one product capability.

Before writing multiple specs, show the proposed boundaries, dependencies, and rationale. Ask for confirmation when the decomposition materially affects scope or delivery.

Write

Use assets/spec.template.md. Remove sections that do not add information. Store:

specs/<NNN-capability>/spec.md

When more than one spec exists, maintain a concise specs/README.md containing only the capability list, state, and functional dependencies. Use assets/spec-index.template.md.

Assign each spec a stable ID and one lifecycle state:

draft -> approved -> [planned] -> implemented -> verified
  • draft: still being authored or awaiting product approval.
  • approved: product behavior and acceptance criteria are confirmed.
  • planned: an approved technical plan covers the spec.
  • implemented: the implementation is complete but not yet verified by review evidence.
  • verified: review evidence confirms the acceptance criteria.

Read the full file on GitHub · 111 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 111 lines · 62 tokens per session scan A 70ea2e32219b

Subscribe to this mod's changes

write-spec is a skill published in the GitHub repository rmjosea/agentic-sdlc-kit (2 stars, last pushed 1mo ago), licensed MIT. It adds 62 tokens to every session and 810 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens