spec-kickoff

spec-kickoff is a skill for Claude Code, Codex from inkatze/planwright. It costs 108 tokens per session (7,033 once invoked), scanned A, original, MIT.

A guided walkthrough that takes a software specification section by section and records a shared understanding in a kickoff brief. It is part of a workflow where plans are reviewed before implementation begins.

In plain words
What is it for?
Use it to review a specification, produce its signed-off kickoff brief, move the specification from Draft to Ready, and prepare its pull request for review.
Why use it?
It gives the developer and agent a chance to find misunderstandings before execution, when mistakes are cheaper to correct.

Skill for Claude CodeCodex

Part of the planwright plugin — 11 skills, 9 hooks shipped together

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/inkatze/planwright/spec-kickoff
Any agent
npx skills add inkatze/planwright --skill spec-kickoff
Clone the repo
git clone --depth 1 https://github.com/inkatze/planwright

Made for: Claude Code, Codex.

Or install planwright, the plugin that ships this one along with the rest of its 11 skills, 9 hooks.

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-kickoff

README.md
[![agentmods](https://agentmods.dev/badge/skills/inkatze/planwright/spec-kickoff.svg)](https://agentmods.dev/skills/inkatze/planwright/spec-kickoff)
Your own site
<a href="https://agentmods.dev/skills/inkatze/planwright/spec-kickoff"><img src="https://agentmods.dev/badge/skills/inkatze/planwright/spec-kickoff.svg" alt="Measured on agentmods" height="20"></a>
Per session 108 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,033 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 $0.00108 $0.07033
Opus 5 $0.00054 $0.03517
Sonnet 5 $0.00022 $0.01407
Haiku 4.5 $0.00011 $0.00703

Measured today against content hash df30553e8bf7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

spec-kickoff 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 today.

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/spec-kickoff/SKILL.md · 446 lines

How it starts

The opening of the file, as written. The whole thing — 446 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/spec-kickoff

The comprehension layer of the planwright pipeline (REQ-B2.4, REQ-B2.2): a section-by-section walkthrough of a spec bundle until human and agent hold the same understanding, recorded as specs/<spec>/kickoff-brief.md — the durable contract (two-brief model, D-3). Downstream skills (/execute-task, /orchestrate) operate from the brief, not the spec; what this walkthrough gets wrong, execution gets wrong.

Sign-off is the first key of a two-key launch (D-44): it flips the spec Draft→Ready and, on a clean completion, marks the spec PR ready (D-6, D-7; the walkthrough is the bundle's review). The human's merge is the second key, making the Ready spec operational (the first dispatch derives Active, not this skill). This skill marks only the spec PR ready, never merges, never dispatches execution.

Doctrine

This skill is procedure, not doctrine. Resolve and read the run-start rule docs via the rule-doc resolution convention (scripts/resolve-rule-doc.sh <doc-name> under the resolved planwright root); their definitions govern wherever this skill names a concept:

  • security-posture — artifact data-hygiene: the brief and risk register are committed.

Invoking plugin scripts (REQ-D1.1, D-7). Call scripts/<name>.sh by the resolved literal absolute path, never $VAR/scripts/<name>.shdoctrine/plugin-script-invocation.md.

spec-format (pre-flight step 2) — the meta-spec: bundle format, status lifecycle, amendment ritual, sign-off records, content anchors, and sanctioned anchor command forms. This skill is the writer its sign-off rules name; it follows them exactly. Three more, at Sign-off step 1:

  • discovery-rigor — the lens checklist, coverage table, and fan-out behind the lens review.
  • autopilot-reflex — the altitude gate (D-11) behind the altitude check.
  • validation-rigor — validation of lens findings before disposition.

If any of those five does not resolve — at run start or point of use — halt naming the missing doc and the chain consulted (REQ-K1.7). The rest degrade gracefully instead:

Read the full file on GitHub · 446 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. today Changed · +2 lines df30553e8bf7
  2. 4d ago First seen · 444 lines · 108 tokens per session scan A 205d6a9570ea

Subscribe to this mod's changes

spec-kickoff is a skill published in the GitHub repository inkatze/planwright (3 stars, last pushed today), licensed MIT. It adds 108 tokens to every session and 7,033 once invoked, about $0.0005 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

accessibility-gate

Use as a pass/fail gate on any diff with a user-facing surface — by code-reviewer during review, by qa-engineer during the test pass, and by any IC before claiming a UI ticket done. This is the gate the plan called for instead of an accessibility specialist role. Triggers whenever a screen, component or state changes.

vmobifystudio/app-dev-team · 74 tokens

agent-isolation

Use before spawning any agent that writes files, and by every developer/fixer agent as its first and last action. Gives each agent its own git worktree, forbids blanket staging, and requires confirming a mutation actually landed. Triggers from /app-build, /app-audit, parallel-orchestrator, and any parallel agent…

vmobifystudio/app-dev-team · 82 tokens

architecture-builder

Use to produce the technical architecture doc and engineering principles for a mobile app. Used primarily by the CTO agent. Triggers on "design the architecture", "pick the stack", or as part of /app-plan.

vmobifystudio/app-dev-team · 46 tokens

board-doctor

Use to validate docs/31-board.md before spawning any agent, and to verify a developer's "DONE" claim before moving a row to review. Triggers as step 0 of /app-build and /app-run, from /app-status, and any time the board looks inconsistent. Catches tickets the sprint loop cannot see.

vmobifystudio/app-dev-team · 71 tokens

brownfield-onboarding

Use when pointing the team at an EXISTING, already-built app instead of a blank project — detects the stack, reverse-engineers the as-built architecture, and classifies remediation work as safe-to-auto-fix vs risky-needs-approval. Triggered by /app-onboard, /app-audit, and by /app-run when it detects a non-empty app…

vmobifystudio/app-dev-team · 81 tokens

business-model

Use when deciding or revisiting how the product makes money — pricing, tiers, trial shape, ad load, unit economics — by ceo when setting the model, by cpo when a scope decision turns on revenue, and by product-researcher when investigating willingness to pay. A pricing analysis is a document, not a standing role.

vmobifystudio/app-dev-team · 71 tokens