A documentation tool for changing an existing feature specification by adding, removing, or revising functionality. It updates the proposal and detailed specification and records the change.

Use it to amend a named feature after reviewing its current proposal, specification, source code, and related project documentation.

It keeps an existing feature's documentation current as the product evolves. Recording the amendment preserves why the specification changed.

spec-amend — Skill for Claude Code and Codex by schmidthole: A documentation tool for changing an existing feature specification…

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-amend

Any agent

npx skills add schmidthole/serf --skill spec-amend

Clone the repo

git clone --depth 1 https://github.com/schmidthole/serf

Made for: Claude Code, Codex.

Or install serf, the plugin that ships this one along with the rest of its 7 skills.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/schmidthole/serf/spec-amend.svg)](https://agentmods.dev/skills/schmidthole/serf/spec-amend)

Your own site

<a href="https://agentmods.dev/skills/schmidthole/serf/spec-amend"><img src="https://agentmods.dev/badge/skills/schmidthole/serf/spec-amend.svg" alt="Measured on agentmods" height="20"></a>

Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,021 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.

Model	Per session	Once invoked
Fable 5	$0.00037	$0.01021
Opus 5	$0.00018	$0.00511
Sonnet 5	$0.00007	$0.00204
Haiku 4.5	$0.00004	$0.00102

Measured 3d ago against content hash 7a21c13ce383, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

spec-amend 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 3d 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/spec-amend/SKILL.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 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

amend an existing feature by updating its proposal and spec files and recording the amendment for historical context. expects $ARGUMENTS in the format:

/spec-amend <feature-name> <description of what to add, remove, or change>

the description can be as brief or detailed as the user wants. use whatever context is provided to determine the scope of the amendment.

follow these steps:

locate the feature. glob for specs/features/<feature-name>/. if the feature does not exist, inform the user and suggest /spec-new instead.
read the current state. read the feature's proposal.md and spec.md in full. understand the existing purpose, use cases, failure states, and technical details before making any changes.
read the codebase context. if spec.md has a ## Source Paths section, read the code at those paths to understand the current implementation. also read specs/features/features.md and the project's README.md for broader context.
classify the amendment. based on the description, determine what type of change this is:
- addition: new functionality, use cases, or technical components being added to the feature
- modification: existing functionality being changed in behavior, interface, or implementation
- removal: functionality being dropped from the feature
present a summary. before making any changes, output:
- the amendment type (addition, modification, removal)
- what will change in proposal.md (new/updated use cases, failure states, purpose changes)
- what will change in spec.md (new/updated source paths, data structures, logic)
- any sections that will be removed or replaced
ask the user for approval or adjustments before proceeding.
update proposal.md. apply the amendment to the proposal:
- for additions: add new use cases and failure states. expand the purpose section if the feature's scope is growing. do not remove existing content that is still valid.
- for modifications: update the affected use cases, failure states, or purpose description in place. preserve content that is unchanged.
- for removals: remove the relevant use cases and failure states. update the purpose section if the feature's scope is shrinking. if a removed item had associated failure states, remove those too.
- do not change the status frontmatter unless the user explicitly requests it.

Read the full file on GitHub · 89 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.

3d ago First seen · 89 lines · 37 tokens per session scan A 7a21c13ce383

Subscribe to this mod's changes

spec-amend is a skill published in the GitHub repository schmidthole/serf (2 stars, last pushed 5mo ago), licensed BSD-3-Clause. It adds 37 tokens to every session and 1,021 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.

Planning Writing and docs

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