spec-plan

A planning method that compares a feature specification—the written description of desired behavior—with the current codebase.

In plain words
What is it for?
It reads the feature documents and relevant source files, checks existing work items, and creates tasks for closing the implementation gap.
Why use it?
It shows what is missing or different and avoids planning work that has already been completed or assigned.

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/schmidthole/serf/spec-plan
Any agent
npx skills add schmidthole/serf --skill spec-plan
Clone the repo
git clone --depth 1 https://github.com/schmidthole/serf

Made for: Claude Code, Codex.

Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 996 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 $0.00033 $0.00996
Opus 5 $0.00016 $0.00498
Sonnet 5 $0.00007 $0.00199
Haiku 4.5 $0.00003 $0.00100

Measured yesterday against content hash 74f616c67ea4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

spec-plan 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.

skills/spec-plan/SKILL.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

reference

read development-workflow.md for the full conventions governing the specs directory structure, features, work items, and their formats.

instructions

analyze the delta between a feature's desired state (its spec) and the current state of the codebase, then generate work items that describe how to close the gap. expects $ARGUMENTS as a feature name:

/spec-plan <feature-name>

follow these steps:

  1. read the feature spec. load specs/features/<feature-name>/proposal.md and specs/features/<feature-name>/spec.md. if either does not exist, inform the user. both files are needed to understand the desired state.

  2. read the current code. extract the ## Source Paths section from spec.md. for each source path, read the relevant files. if no source paths exist yet, note that all implementation is net-new and use the spec's described structure to determine where code should live.

  3. read existing active work items. glob for files in specs/work/active/ with frontmatter referencing this feature. understand what is already planned or in progress to avoid duplicating work.

  4. identify the delta. compare the spec's desired state against the current code and any existing work items. categorize the gaps:

    • net-new: functionality described in the spec with no corresponding code
    • modification: existing code that needs to change to match the spec
    • removal: existing code that the spec no longer describes or explicitly excludes
  5. present the plan. before creating any files, output a summary of the identified gaps and the work items you propose to create. each proposed work item should include:

    • a concise title (which becomes part of the filename)
    • which gap(s) it addresses
    • a brief description of the implementation approach
    • proposed acceptance criteria (concrete, verifiable conditions)

    ask the user for approval or adjustments before proceeding.

  6. create work items. after approval, for each work item:

    • ensure specs/work/active/ and specs/work/archive/ exist
    • create the file at specs/work/active/YYYY-MM-DD-title.md using today's date
    • populate frontmatter with feature, status: ready, start_date, empty archive_date, and relevant keywords
    • write a summary section that describes the gap, references the relevant parts of the spec, and explains why the change is needed
    • write an acceptance criteria section with concrete, testable conditions that define "done." each criterion should be independently verifiable by running a test, command, or observable check, not by reading code. good criteria take the form: "when X happens, Y is the result." avoid subjective criteria like "code is clean" or "handles errors properly."
    • write a tasks section with a numbered checklist breaking the work into concrete steps. include verification tasks (e.g., "write tests for X", "verify Y produces expected output") alongside implementation tasks, not just at the end
    • include an empty log section

Read the full file on GitHub · 69 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 · 69 lines · 33 tokens per session scan A 74f616c67ea4

Subscribe to this mod's changes

spec-plan is a skill published in the GitHub repository schmidthole/serf (2 stars, last pushed 5mo ago), licensed BSD-3-Clause. It adds 33 tokens to every session and 996 once invoked, about $0.0002 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

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

agent-host-chat-contributions

Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.

microsoft/vscode · 56 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