spec

A requirements-writing workflow that chooses how much planning a change needs before coding starts. Small changes may need only a test and commit message, while larger or riskier work gets a written specification and plan.

In plain words
What is it for?
Use it before non-trivial features or changes to choose a planning level, interview the owner, write requirements, define interfaces and rollback steps, and describe how the result will be checked.
Why use it?
It prevents developers from building unspecified behavior while avoiding unnecessary paperwork for simple fixes. It also records decisions that may matter later.

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/tradebaas/groundwork/spec
Any agent
npx skills add Tradebaas/Groundwork --skill spec
Clone the repo
git clone --depth 1 https://github.com/Tradebaas/Groundwork

Made for: Claude Code, Codex.

Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,270 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 $0.00058 $0.01270
Opus 5 $0.00029 $0.00635
Sonnet 5 $0.00012 $0.00254
Haiku 4.5 $0.00006 $0.00127

Measured yesterday against content hash b1dfe9bf7cb3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 yesterday.

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/spec/SKILL.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

spec: as much process as the change deserves, and no more

1. Pick the tier: argue it, don't default upward

  • S: no spec. Small, clear, reversible: bugfix, copy change, config tweak, single-file change with obvious behavior. The commit message and a test are the record. If you're explaining the tier choice in more than a sentence, it isn't S.
  • M: spec.md only. A feature or change in one area, buildable in a session or two.
  • L: spec.md + plan.md. Multi-session, multi-area, risky, or contested. Copy docs/specs/TEMPLATE-PLAN.md to plan.md: build order (owned by the ticket graph), seams/interfaces touched, migration/rollback, verification approach.

Two honest tests: Would a senior write this down first? and Will anyone need to know why in three months? Yes to either → at least M.

2. Tier M and L: interview before writing

Build shared understanding first; a finished draft the owner can only react to is not that. Tier S is exempt: a bugfix gets no interview. The rules:

  • One question at a time. Each question comes with your recommended answer and a one-line reason, so the owner can accept the default or push back cheaply.
  • Recommendations are argued, not agreeable. A question with a real design choice behind it gets the critical-thinking moves first: the recommendation names the alternative it beat.
  • Facts are looked up, never asked. Whatever the repo, the docs, or the code can answer, you answer yourself before asking anything.
  • Decisions are put to the owner, never assumed. Scope, trade-offs, and preferences are the owner's; surface each one as a question, however obvious the answer seems.
  • Pin fuzzy terms as they surface. A word with two possible meanings goes into the glossary docs/product/CONTEXT.md right then, so the spec uses one word for one thing.
  • Write only after confirmation. Close the interview by playing back your understanding in a few lines and asking the owner to confirm it. Only then start writing. Record the confirmation (date plus the owner's words) in the spec's sign-off line; it replaces a bare "approved".

Read the full file on GitHub · 88 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. yesterday First seen · 88 lines · 58 tokens per session scan A b1dfe9bf7cb3

Subscribe to this mod's changes

spec is a skill published in the GitHub repository Tradebaas/Groundwork (2 stars, last pushed 6d ago), licensed MIT. It adds 58 tokens to every session and 1,270 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

mission-driver

Create roadmaps and mission configs, then drive the mission-driver AI dev-loop engine. mission-driver lives at tools/mission-driver/ — it reads missions/ .json and loops CHECK → REVIEWPLANS → EXECPLANS → DRAFTPLANS → DEEPAUDIT until the roadmap is done or the audit budget is exhausted. Use this skill when the user…

entropy-cloud/attractor-guided-engineering-template · 199 tokens

keel-plan

Create or revise PLAN.md — propose the phase DAG (phases · gates · dependencies) from the user's goal, get approval, write the table and regenerate the colored Mermaid diagram from it. Statuses flip at rituals (/keel-handover, /keel-phase-review); post-completion fixes land in the Fix log.

muratsilahtaroglu/claude-code-starter-kit · 70 tokens

keel-stats

Render the ritual telemetry visually — turns .claude/ritual-log into reports/ritual-stats.md with PLAN.md-style colored Mermaid interval boxes (session/compact boundaries) + a counts table. Answers "which skills/commands/hooks ran, how often, in which interval".

muratsilahtaroglu/claude-code-starter-kit · 62 tokens

init

Configure an uninitialized project from an approved charter: stack, scripts, identity, optional Git, and verification.

bnet47/codexicon · 24 tokens

sdd-serve

Serve the SDD Builder's AI request queue: claim requests with sddnextrequest, draft the proposal, answer with sddrespondrequest. Never writes spec files — the user accepts each proposal in the builder. Use when the user asks to attend, serve or listen to the SDD board queue. / Atiende la cola de peticiones del SDD…

juanklagos/spec-driven-development-template · 80 tokens

review-creative

Audit customer-facing work for UX, accessibility, brand fit, credibility, and generic AI output. Use for design, marketing, document, presentation, or visual review.

bnet47/codexicon · 37 tokens