Agent skill

SPEC.md Mutator

by JuliusBrussee in JuliusBrussee/cavekit

Creates, distills, amends and updates the project's SPEC.md from ideas, existing code or bug reports, as the only skill allowed to write that file.

MITAuto-check passedDevelopment

Install SPEC.md Mutator

skills CLI
$ npx skills add JuliusBrussee/cavekit --skill spec -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install JuliusBrussee/cavekit spec --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/JuliusBrussee/cavekit.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/spec .claude/skills/spec && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
spec
GitHub stars
1.1k
Token cost
~849 tokens
SKILL.md length
424 words
Files
1
Skills in repo
8
Repo updated
First seen
Licence
MIT

At a glance

Creates, distills, amends and updates the project's SPEC.md from ideas, existing code or bug reports, as the only skill allowed to write that file.

  • Works in 5 steps: No SPEC.md at repo root AND args… → No SPEC.md AND from-code in args → DISTILL → SPEC.md exists AND args start bug: →… → …
  • Starting a SPEC.md from a rough product idea
  • SKILL.md covers DISPATCH, INPUTS — spec is the sole…, NEW — idea → spec and DISTILL — code → spec, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

The agent inspects the request and the repo and picks a mode: a new spec from an idea when no SPEC.md exists, a spec distilled from code, a bug recorded through backprop when the argument starts with bug, an amendment of a named section, or a question about which mode when no argument is given. The spec file has sections for goal, constraints, interfaces, invariants, tasks as a pipe table, bugs and optional research, written in a compressed caveman style described in FORMAT.md.

As sole writer, it ingests handoff blocks from the grill, research, review and deepen verbs into the right sections, shows a diff and writes only when you say OK, and never rewrites a section the handoff did not name. For a bug it finds the root cause, drafts a new invariant if that would catch a recurrence, and adds a bug row plus any task changes. The source repository describes itself as frozen, with active work moved elsewhere.

When your agent uses it

  • Starting a SPEC.md from a rough product idea
  • Distilling a spec from an existing codebase
  • Recording a bug so it produces an invariant and a task
  • Amending one section of an existing spec

Example prompts

  • “Write the spec for a rate-limited webhook sender.”
  • “bug: retries fire twice after a timeout; record it in the spec.”
  • “Distill a spec from this repo's code and mark anything you are unsure about.”

Requirements

  • FORMAT.md at the repository root

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. No SPEC.md at repo root AND args describe idea → NEW
  2. No SPEC.md AND from-code in args → DISTILL
  3. SPEC.md exists AND args start bug: → BACKPROP
  4. SPEC.md exists AND args start amend → AMEND
  5. SPEC.md exists, no args → ask user which mode

What it can do on your machine

Read from SKILL.md and the folder at commit 7421e87. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

SPEC.md Mutator loads about 849 tokens when it runs. Until then it costs about 125 tokens; SKILL.md has 424 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~125
When it runs · the whole SKILL.md, loaded when a task matches
~849

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from JuliusBrussee/cavekit at commit 7421e87, republished under its MIT licence (© JuliusBrussee). 424 words, ~849 tokens.

Download SKILL.mdSave it as .claude/skills/spec/SKILL.md (or your agent's skills folder).
name
spec
description
Create, amend, or backprop bugs into SPEC.md at repo root. Sole mutator of the project spec. Triggers when the user asks to write a spec, start a new spec, distill a spec from existing code, add invariants, amend sections (§G, §C, §I, §V, §T, §B), or record a bug via backprop. Common phrasings: "write the spec for...", "new spec", "bug: ...", "amend §V.3", "distill spec from code", "spec this idea". Reads and follows FORMAT.md for the caveman encoding rules and pipe-table shape of §T and §B.

spec — spec mutator

Read FORMAT.md at repo root if not already loaded. Caveman skill applies to all writes here.

DISPATCH

Inspect user request and project state:

  1. No SPEC.md at repo root AND args describe idea → NEW
  2. No SPEC.md AND from-code in args → DISTILL
  3. SPEC.md exists AND args start bug: → BACKPROP
  4. SPEC.md exists AND args start amend → AMEND
  5. SPEC.md exists, no args → ask user which mode

INPUTS — spec is the sole mutator

The other verbs produce material; spec writes it. Ingest their handoff blocks into the right section, show a diff, write on OK:

  • grill → sharpened §G + §C
  • research → §R rows (add the §R section if absent)
  • review → drafted §V lines + the risk verdict
  • deepen → §I/§V/§T amendments

⊥ rewrite a section the handoff did not name. Sectioned ownership (see FORMAT.md).

NEW — idea → spec

Input: user idea. If it arrived fuzzy, prefer running grill first.

Steps:

  1. Extract goal (1 line, caveman). → §G.
  2. List constraints user stated or implied. → §C.
  3. List external surfaces user named. → §I.
  4. §R only if research ran — else omit the section (right-size).
  5. Propose initial invariants. → §V (numbered V1…).
  6. Break goal into ordered tasks. → §T pipe table, all status ., ids T1…
  7. §B section with header row only (id|date|cause|fix).

Write to SPEC.md. Show user full file. Ask: "spec OK? /review if high-blast-radius, else /build."

DISTILL — code → spec

Walk repo. Produce §G (infer from README/package.json/main entry), §C (infer from stack), §I (enumerate public APIs/CLIs/configs), §V (derive from tests and assertions), §T (one task per known TODO or missing test), §B (empty).

Caveman everywhere. Flag uncertain items with ? in text so user can confirm.

Show full SKILL.md (152 more words)Show less

BACKPROP — bug → §B + §V

Input: bug: <description>.

Steps:

  1. Parse bug description.
  2. Find root cause (read relevant code).
  3. Decide: would a new invariant catch recurrence? If yes → draft V<next>.
  4. Append §B row: B<next>|<date>|<cause>|V<N>.
  5. Append new invariant to §V.
  6. If fix also changes behavior → add/update §T rows.
  7. Show diff. Apply only on user OK.

Rule: every bug gets a §B entry. Invariant optional but preferred.

AMEND — targeted edit

Input: amend §V.3 or amend §T etc.

Read that section. Show current. Ask user what changes. Write. Show diff.

Never silently rewrite sections user did not name.

OUTPUT RULES

  • Caveman format per FORMAT.md.
  • Preserve identifiers, paths, code verbatim.
  • Numbering monotonic — never reuse §V.N or §B.N.
  • §T row cites column ! list §V/§I deps: T5|.|impl auth mw|V2,I.api.

NON-GOALS

  • No sub-agents. Main thread writes.
  • No dashboards, no logs, no state files beyond SPEC.md itself.
  • No auto-build after spec. User invokes build explicitly.

© JuliusBrussee, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/spec of JuliusBrussee/cavekit.

Open the folder on GitHubat commit 7421e87

Compare with similar skills

SPEC.md Mutator next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

SPEC.md Mutator compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
SPEC.md Mutator this skillJuliusBrussee/cavekit1.1k—~849Automated safety check: PassMIT
SPARC Development Methodologyruvnet/ruflo74k2 repos~829Automated safety check: PassMIT
Ss SpecSerial-Studio/Serial-Studio7.2k—~766Automated safety check: PassCustom licence
Spec Driven Developzhu1090093659/spec_driven_develop984—~5.1kAutomated safety check: PassMIT
Bulletproof Workflowartemiimillier/bulletproof153—~3.5kAutomated safety check: PassMIT
Develop Feature Builderjsmastery-pro/skills1.4k—~3.8kAutomated safety check: NotesMIT

Similar skills

  • Applies the SPARC method (specification, pseudocode, architecture, refinement, completion) with 17 specialized modes and multi-agent orchestration, from research to deployment.

    74k GitHub starsUsed in 2 repos~829 tokens
    DevelopmentAuto-check passed
  • Ss Spec

    Serial-Studio/Serial-Studio

    Phase 1 of Serial Studio's spec-driven workflow: capture WHAT a feature must do and WHY, with no implementation detail.

    7.2k GitHub stars~766 tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Spec Driven Develop

    zhu1090093659/spec_driven_develop

    Automates pre-development workflow for large-scale complex tasks.

    984 GitHub stars~5.1k tokensUpdated 2 mo ago
    DevelopmentAuto-check passed
  • Bulletproof Workflow

    artemiimillier/bulletproof

    Applies a 12-stage verified workflow, from research to deploy, to non-trivial coding tasks, scaled to lightweight, standard or full mode by task size.

    153 GitHub stars~3.5k tokensUpdated 6 mo ago
    DevelopmentAuto-check passed
  • Develop Feature Builder

    jsmastery-pro/skills

    Builds a feature, page, component, API or data layer from an approved spec and AGENTS.md, and sends you back to /architect when a key decision is missing.

    1.4k GitHub stars~3.8k tokensUpdated 2 mo ago
    DevelopmentAuto-check: notes
  • PRP Plan

    Wirasm/prp

    Writes an implementation-ready plan for a feature, bug fix, refactor or chore from a PRD, issue or description, grounded in codebase evidence, and can post it back to the source issue.

    2.3k GitHub stars~4k tokensUpdated 6 days ago
    DevelopmentAuto-check passed

More from JuliusBrussee/cavekit

All 8 skills in this repo
  • Backprop: Bug-to-Spec Protocol

    JuliusBrussee/cavekit

    After a bug is found, traces its root cause and feeds a new testable invariant back into the project spec so the bug class can't recur.

    1.1k GitHub stars~653 tokensUpdated 1 mo ago
    Auto-check passed
  • Caveman Spec Compression

    JuliusBrussee/cavekit

    Compresses SPEC.md writes and spec-referencing prose into terse, symbol-heavy fragments that drop articles, filler and hedging while keeping facts intact.

    1.1k GitHub stars~721 tokensUpdated 1 mo ago
    Auto-check passed
  • Spec Drift Check

    JuliusBrussee/cavekit

    Read-only detector that compares SPEC.md with the code and reports invariant, interface and task drift grouped by severity, without changing anything.

    1.1k GitHub stars~666 tokensUpdated 1 mo ago
    Auto-check passed
  • Adversarial Spec Review

    JuliusBrussee/cavekit

    Builds a skeptical reviewer grounded in the codebase and research notes to try to refute a spec before any code is written, citing file:line evidence and ending in a go or no-go gate.

    1.1k GitHub stars~959 tokensUpdated 1 mo ago
    Auto-check passed
  • Deepen Module Design

    JuliusBrussee/cavekit

    Scans the code a spec touches for its shallowest module, then proposes a refactor that hides more behind a smaller interface without changing behavior.

    1.1k GitHub stars~1k tokensUpdated 1 mo ago
    Auto-check passed
  • Grill Before Spec

    JuliusBrussee/cavekit

    Interrogates a vague idea one question at a time, recommending an answer each round and recording results as goals and constraints before a spec is written.

    1.1k GitHub stars~812 tokensUpdated 1 mo ago
    Auto-check passed

Questions about SPEC.md Mutator

What does SPEC.md Mutator do?

Creates, distills, amends and updates the project's SPEC.md from ideas, existing code or bug reports, as the only skill allowed to write that file. md exists, a spec distilled from code, a bug recorded through backprop when the argument starts with bug, an amendment of a named section, or a question about which mode when no argument is given.md.

When should I use SPEC.md Mutator?

SPEC.md Mutator fits situations like: starting a SPEC.md from a rough product idea; distilling a spec from an existing codebase; recording a bug so it produces an invariant and a task; amending one section of an existing spec.

How do I install SPEC.md Mutator in Claude Code?

Run `npx skills add JuliusBrussee/cavekit --skill spec -a claude-code`. Or copy the skill folder (skills/spec in JuliusBrussee/cavekit) into .claude/skills/spec in your project. Claude Code loads it when a task matches its description.

How do I install SPEC.md Mutator in Codex?

Run `npx skills add JuliusBrussee/cavekit --skill spec -a codex`. Or copy the skill folder (skills/spec in JuliusBrussee/cavekit) into .agents/skills/spec in your project. Codex loads it when a task matches its description.

Can I use SPEC.md Mutator in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add JuliusBrussee/cavekit --skill spec -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/spec, .gemini/skills/spec, .github/skills/spec and .opencode/skills/spec in your project.

What does SPEC.md Mutator need to run?

SKILL.md names no scripts, command-line tools or credentials: SPEC.md Mutator is instructions for the agent only. Our summary lists: FORMAT.md at the repository root.

Does SPEC.md Mutator access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is SPEC.md Mutator safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does SPEC.md Mutator use?

SPEC.md Mutator is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does SPEC.md Mutator use?

About 849 tokens (SKILL.md is roughly 3.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to SPEC.md Mutator?

Skills that share tags, products or a category with SPEC.md Mutator: SPARC Development Methodology (ruvnet/ruflo, 74k stars), Ss Spec (Serial-Studio/Serial-Studio, 7.2k stars), Spec Driven Develop (zhu1090093659/spec_driven_develop, 984 stars) and Bulletproof Workflow (artemiimillier/bulletproof, 153 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains SPEC.md Mutator?

JuliusBrussee (a GitHub user) maintains it in JuliusBrussee/cavekit, which has 1,149 GitHub stars. The repository holds 8 skills in this directory. The repository was last updated on August 14, 2026.

Source: JuliusBrussee/cavekit on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.