PR To Spec

What it does

When your agent uses it

• Declaring intent before a change
• Checking a finished change for drift against that intent
• Generating a spec for agent review
• With /pr-to-spec

Example prompts

• “/pr-to-spec”
• “pr-to-spec scan”
• “pr-to-spec check”
• “/pr-to-spec”

Requirements

• Node.js
• Compatibility (from SKILL.md): Requires the pr-to-spec CLI on PATH (Node.js 18+; ships with this plugin) and a git repository to analyze. Runs in Claude Code or any agent runtime with shell access.
• Pre-approved tools (allowed-tools): Bash(pr-to-spec:*)

What it can do on your machine

Read from SKILL.md and the folder at commit cfae287. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • Bash(pr-to-spec:*)

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md (its code samples are bash, json and markdown).

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

• Network

  Links to these hosts (documentation or services it may open):

  • github.com
  • jeremylongshore.github.io

  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.

• Compatibility

  Requires the pr-to-spec CLI on PATH (Node.js 18+; ships with this plugin) and a git repository to analyze. Runs in Claude Code or any agent runtime with shell access.

  From compatibility in the SKILL.md frontmatter.

Context cost

PR To Spec loads about 1.1k tokens when it runs. Until then it costs about 102 tokens; SKILL.md has 366 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~102

When it runs · the whole SKILL.md, loaded when a task matches

~1.1k

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

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 jeremylongshore/tons-of-skills-marketplace at commit cfae287, republished under its MIT licence (© jeremylongshore). 366 words, ~1,125 tokens.

name

pr-to-spec

description

Analyze code changes and detect intent drift using the pr-to-spec CLI — converts a branch, staged edits, or recent commits into a structured, agent-consumable spec. Use when declaring intent before a change, checking a finished change for drift against that intent, or generating a spec for agent review. Trigger with "/pr-to-spec", "pr-to-spec scan", "pr-to-spec check", or "pr-to-spec intent".

allowed-tools

Bash(pr-to-spec:*)

compatibility

Requires the pr-to-spec CLI on PATH (Node.js 18+; ships with this plugin) and a git repository to analyze. Runs in Claude Code or any agent runtime with shell access.

version

0.8.0

author

Jeremy Longshore <jeremy@intentsolutions.io>

license

MIT

tags

git, pr, spec, intent-drift, code-review, agent-protocol

argument-hint

[scan | check | intent set | intent show]

pr-to-spec scan --branch main --json

pr-to-spec check --json

pr-to-spec intent set --goal "Add rate limiting to API" --scope "src/middleware/**" --forbid "src/db/**" --max-risk medium

pr-to-spec intent show --json

{
  "version": 1,
  "command": "check",
  "status": "drift_detected",
  "exit_code": 3,
  "signals": [...],
  "spec": {...},
  "intent": {...}
}

pr-to-spec intent set --goal "Add rate limiting to API" --scope "src/middleware/**" --forbid "src/db/**" --max-risk medium
# ...make the changes...
pr-to-spec check --json    # exit 0 = clean, 2 = high-risk, 3 = drift

## Change Validation

Before any significant code change:
1. Set intent: `pr-to-spec intent set --goal "..." --scope "..." --max-risk medium`
2. After changes: `pr-to-spec check --json` — exit 3 means drift, investigate before continuing

© jeremylongshore, 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 plugins/mcp/pr-to-spec/.claude/skills/pr-to-spec of jeremylongshore/tons-of-skills-marketplace.

Open the folder on GitHubat commit cfae287