spec-planning

spec-planning is a skill for Claude Code, Codex from capitalone/context-specs. It costs 125 tokens per session (3,694 once invoked), scanned A, original, Apache-2.0.

A planning tool that turns a product requirements document (PRD) and its executable test into an implementation specification. It researches the codebase and divides the work into dependency-ordered slices.

In plain words
What is it for?
Preparing implementation plans from files under a project’s PRD directory. It produces a main specification and smaller work slices whose success includes passing the PRD test.
Why use it?
It connects the requested behavior to the existing code and gives completion a testable definition. This reduces uncertainty about what to build first and how to verify it.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: names the AskUserQuestion tool.

Good fit Preparing implementation plans from files under a project’s PRD directory. It produces a main specification and smaller work slices whose success includes passing the PRD test.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/capitalone/context-specs/spec-planning
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.

Any agent
npx skills add capitalone/context-specs --skill spec-planning
Clone the repo
git clone --depth 1 https://github.com/capitalone/context-specs

Made for: Claude Code, Codex.

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-planning

README.md
[![agentmods](https://agentmods.dev/badge/skills/capitalone/context-specs/spec-planning/github.svg)](https://agentmods.dev/skills/capitalone/context-specs/spec-planning)
Your own site
<a href="https://agentmods.dev/skills/capitalone/context-specs/spec-planning"><img src="https://agentmods.dev/badge/skills/capitalone/context-specs/spec-planning/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for spec-planning

Your own site · 80×15
<a href="https://agentmods.dev/skills/capitalone/context-specs/spec-planning"><img src="https://agentmods.dev/badge/skills/capitalone/context-specs/spec-planning.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 125 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,694 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00125 $0.03694
Opus 5.5 $0.00050 $0.01478
Sonnet 5.5 $0.00025 $0.00739
Haiku 4.5 $0.00013 $0.00369

Measured 2mo ago against content hash 68ebbbd3d7ce, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

spec-planning 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 2mo 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/sdd/spec-planning/SKILL.md · 318 lines

How it starts

The opening of the file, as written. The whole thing — 318 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Spec Planning

Turn a PRD into a structured Spec Plan using Spec-Driven Development. Agent-first: this skill is invoked headless by the harness dispatcher, with the feature slug as its single argument. It reads disk, does the work, commits artifacts plus a sentinel, and exits.

Invocation Contract

Invoked by the dispatcher as: claude -p "/spec-planning <feature>", run from inside the feature worktree (the dispatcher cds into it — there is no print-mode --cwd flag).

Single argument: <feature> — kebab-case feature slug. All paths derive from this.

Inputs read from disk (paths relative to cwd):

  • prds/<feature>/prd.md — the why, user story, definition of done, constraints, out-of-scope.
  • prds/<feature>/run-prd-test.sh — executable test runner for this feature's PRD test. Exits 0 when the feature is done.
  • Any verification artifacts under prds/<feature>/ invoked by run-prd-test.sh — fixtures, LLM-judge prompts, helper test files, etc. The runner is the single contract; its internals are intentionally flexible (pure unit test, LLM-as-judge, deterministic shell checks, or any mix).
  • The current codebase.

Outputs to disk (paths relative to cwd):

  • specs/<feature>/mainspec.md
  • specs/<feature>/slices/*.md
  • specs/<feature>/.planning-done (empty sentinel)

Completion protocol (in order):

  1. Write all mainspec + slice files.
  2. git add those files, commit with a clear message, push.
  3. touch specs/<feature>/.planning-done.
  4. git add the sentinel, commit, push.

The sentinel is the final commit-and-push action, only after every other artifact is in place. The dispatcher uses only the sentinel to advance to spec-validate.

Idempotency:

  • If specs/<feature>/.planning-done already exists, exit immediately (the previous invocation completed; the dispatcher's worktree wipe will have discarded any uncommitted intermediate state).
  • If specs/<feature>/mainspec.md exists but the sentinel does not, treat as crash recovery: verify the existing artifacts are complete and self-consistent, fix any gaps, then write the sentinel.

Read the full file on GitHub · 318 lines

Files

What ships with it

1 file 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. 2mo ago First seen · 318 lines · 125 tokens per session scan A 68ebbbd3d7ce

Subscribe to this mod's changes

spec-planning is a skill published in the GitHub repository capitalone/context-specs (46 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 125 tokens to every session and 3,694 once invoked, about $0.0005 per session on Opus 5.5. 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.

Related

spec-planning compared with skills from other repositories

spec-planning next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
spec-planningcapitalone/context-specsSkill462mo agoApache-2.0A125Claude Code, Codex
imagegenopenai/codexSkill136ktodayApache-2.0A113Codex
playwright-climicrosoft/playwrightSkill101ktodayApache-2.0A19Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill81k3d agoMITA200Claude Code, Codex
browser-automationopenclaw/openclawSkill395ktodayMITA36Claude Code
free-llm-apismnfst/awesome-free-llm-apisSkill14ktodayCC0-1.0A113Claude Code, Codex
next-cache-components-adoptionvercel/next.jsSkill144ktodayMITA95Claude Code