Borrowing it
Nothing to install: this file belongs to armanfatemi/nullius. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/armanfatemi/nullius/main/.claude/skills/proposal-to-pr/SKILL.mdgit clone --depth 1 https://github.com/armanfatemi/nulliusWrote 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.
[](https://agentmods.dev/skills/armanfatemi/nullius/proposal-to-pr)<a href="https://agentmods.dev/skills/armanfatemi/nullius/proposal-to-pr"><img src="https://agentmods.dev/badge/skills/armanfatemi/nullius/proposal-to-pr/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<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="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Memory Poisoning · line 98 Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.Fix: Protect agent memory and state from modification by untrusted content. Use read-only memory for critical instructions and validate all state changes.
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 5.1 | $0.00126 | $0.18610 |
| Opus 5.5 | $0.00050 | $0.07444 |
| Sonnet 5.5 | $0.00025 | $0.03722 |
| Haiku 4.5 | $0.00013 | $0.01861 |
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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 1,561 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-run— terminal 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 editproposal.md,design.mdortasks.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 mandatorycanary clear, so the run still ends with every artefact as it found it.review-evidence.mdis the record of the review that did happen, and is written either way.) Savepaused=true,pause_reason=dry_run, and leavestageat 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.
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.
- 1mo ago Changed · +1 lines ff114dc8f55a
- 1mo ago Changed · +276 lines aa2d78a179ee
- 2mo ago First seen · 1,284 lines · 126 tokens per session scan A f2cd1b4964b7
proposal-to-pr is a skill published in the GitHub repository armanfatemi/nullius (5 stars, last pushed 13d ago), licensed MIT. It adds 126 tokens to every session and 18,610 once invoked, about $0.0005 per session on Opus 5.5. 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.
Other skills, from other repositories
argot-setup
Set argot up for a repository end to end — audit its history, decide what should shape its voice, fit, verify the fit actually catches things, tune the rules its own history says are noisy, and wire the places it runs (pre-write hook, pre-commit, MCP, CI). One sitting, one decision at a time, each proposed with the…
watch-pr
Watch a GitHub pull request for CI status, reviews, comments, merge conflicts, and terminal states using the gh-watch extension. Use when the user wants to monitor a PR, wait for CI, or track PR progress.
bellwether
Bring the current PR to a mergeable state: CI green, all review comments resolved, no merge conflicts. Self-contained — watches CI, fixes issues, watches again until merge-ready. Use when the user wants to keep a PR green, auto-fix CI, resolve review comments, or says "get this merged".
autofix-pr
Watch a pull request and fix it from a worktree of its own - CI failures, review feedback from trusted authors and merge conflicts are fixed, pushed to the PR branch and answered on the PR under the user's git and gh identity. Usage - /autofix-pr [ | ] [--once] [--every ] [--no-reply] [--yes] [instructions]…
gh-find-prs
Survey open Codewhale PRs and triage each for mergeability and disposition against the real landing branch.
hunk-release
Prepares, publishes, verifies, and curates Hunk releases. Use for release metadata, benchmarks, tags, publishing, release videos, backports, or recovery.