proposal-to-pr

proposal-to-pr is a skill for Claude Code, Codex from armanfatemi/nullius. It costs 126 tokens per session (18,575 once invoked), scanned A, original, MIT.

A guided process for taking an OpenSpec change proposal through implementation and into a pull request (a request to merge code).

In plain words
What is it for?
Use it to coordinate a change from its written proposal through code work, testing, review, and a merge-ready pull request.
Why use it?
It keeps prerequisites, reviews, implementation tasks, and verification from being skipped or marked complete without evidence.

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/armanfatemi/nullius/proposal-to-pr
Any agent
npx skills add armanfatemi/nullius --skill proposal-to-pr
Clone the repo
git clone --depth 1 https://github.com/armanfatemi/nullius

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 proposal-to-pr

README.md
[![agentmods](https://agentmods.dev/badge/skills/armanfatemi/nullius/proposal-to-pr.svg)](https://agentmods.dev/skills/armanfatemi/nullius/proposal-to-pr)
Your own site
<a href="https://agentmods.dev/skills/armanfatemi/nullius/proposal-to-pr"><img src="https://agentmods.dev/badge/skills/armanfatemi/nullius/proposal-to-pr.svg" alt="Measured on agentmods" height="20"></a>
Per session 126 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 18,575 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 $0.00126 $0.18575
Opus 5 $0.00063 $0.09288
Sonnet 5 $0.00025 $0.03715
Haiku 4.5 $0.00013 $0.01858

Measured yesterday against content hash aa2d78a179ee, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

proposal-to-pr 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.

.claude/skills/proposal-to-pr/SKILL.md · 1,560 lines

How it starts

The opening of the file, as written. The whole thing — 1,560 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OpenSpec → PR pipeline

The umbrella orchestrator for taking an OpenSpec change from proposal to merge-ready PR. It is a skill rather than a shell script because a handful of its steps need judgement — which reviewers have something concrete to look at, whether a blocker has actually been addressed, whether a failing test is a wrong expectation or a real bug.

Everything else is not judgement, and does not live here. Every decision that can be settled by re-reading an artefact belongs to nullius-kit pipeline, which is TypeScript under pnpm test: what a change touches, which reviewers those paths earn, whether a pause box is unchecked, whether a command is human-only, what the resume state is. That split is the point. A routing row decided by a model is a review stage that dispatches nothing and reports success, which is the one failure this repository exists to make impossible.

First-run note — verify, do not assume

Older harnesses loaded the agent registry once at session start, so an agent file added mid-session was not dispatchable and the call failed with Agent type 'retro-writer' not found. Measured here, that is no longer true: retro-writer.md landed and was dispatchable in the same session.

Treat the restart advice as a claim about a harness version, not a law. The durable instruction is the check: ping the agent with a one-word dispatch before relying on it. If the ping returns, proceed; if it fails, start a fresh session.

Inputs

Required: a change name that resolves to openspec/changes/<name>/ containing at least proposal.md, design.md, and tasks.md.

Optional flags surfaced in the invocation:

  • --from-stage <stage> — resume from a specific stage (defaults to the stored stage, or 1)
  • --no-auto-fix — disable the Stage 5 auto-fix loop (single attempt only)
  • --dry-runterminal stage: the end of Stage 2. Run Stage 1 and Stage 2 in full — dependency gate, grounding gate, canary, parallel pre-review, synthesis, both evidence appends — then report the blockers and stop before entering Stage 3. Stage 3 is the first stage whose purpose is to edit proposal.md, design.md or tasks.md, and Stage 4 edits code; a dry run reaches neither. (Stage 2's canary is planted into the proposal and removed again by the mandatory canary clear, so the run still ends with every artefact as it found it. review-evidence.md is the record of the review that did happen, and is written either way.) Save paused=true, pause_reason=dry_run, and leave stage at whatever Stage 2's Decision selected, so a later invocation without the flag resumes there.
  • --max-refine <n> — cap Stage 3 refinement iterations. Default 3. Stage 3 reads this value; it is not a second hard-coded 3.

Read the full file on GitHub · 1,560 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 Changed · +276 lines aa2d78a179ee
  2. 5d ago First seen · 1,284 lines · 126 tokens per session scan A f2cd1b4964b7

Subscribe to this mod's changes

proposal-to-pr is a skill published in the GitHub repository armanfatemi/nullius (5 stars, last pushed today), licensed MIT. It adds 126 tokens to every session and 18,575 once invoked, about $0.0006 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.