Run any Skill in Manus with one click

set-sources

Stars2

Forks1

UpdatedMay 27, 2026 at 05:49

Add or remove durable files in a ChatGPT project's Sources tab. Use after a verified result lands, after a route pivot, or when the durable proof-state file has been updated locally.

Installation

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

Run Skill in Manus

Source

p-aldighieri

p-aldighieri/MathPipeProver

View GitHub Repository View Creator Repositories

Download

Run Skill in Manus

Related occupationsSOC

Based on SOC occupation classification

Software DevelopersComputer and Mathematical Occupations·SOC 15-1252

SKILL.md

readonly

More from this repository

same repository

search-council

p-aldighieri/MathPipeProver

Fan out a 4-member council (1 Codex thinking-high + 1 Gemini Pro + 1 Claude Opus + 1 ChatGPT Extended Pro) on a stalled re-attack. Preserves all four independent memos; hands off to the regular Strategy Searcher for pure selection. Opt-in (attempt ≥2), ~3× the cost of a single search.

2026-06-012

recover-chat

p-aldighieri/MathPipeProver

Harvest a completed ChatGPT chat's last assistant message into a response file. Use when a role finished but the response file wasn't captured (e.g., orchestrator lost the chat URL, or the submit script died after the model responded).

2026-05-292

set-referee-targets

p-aldighieri/MathPipeProver

Create or update {PROOF_REPO}/referee_targets.yaml — the target-journal registry the paper_referee role consults to judge whether the result clears the bar at the journals you might submit to. Optional; without it the referee falls back to a generic publishability check.

2026-05-272

mathpipe-browser-proof-ops

p-aldighieri/MathPipeProver

Use when working in MathPipeProver on ChatGPT project preparation, durable source refresh, project-source inspection, or browser-backed external_agent submission. Prefer scripts/chatgpt_browser_agent.sh prepare/submit over ad hoc UI work, enforce the Extended Pro target, and keep durable sources separate from temporary attachments.

2026-05-272

inspect-chat

p-aldighieri/MathPipeProver

Read-only one-shot inspection of a live ChatGPT chat — returns generating flag, assistant turn count, last assistant message length and tail. Use during long-running roles to check whether the chat is still working or done.

2026-05-272

set-model-extended

p-aldighieri/MathPipeProver

Verify or set the ChatGPT composer to the Extended Pro target (reasoning Pro + model 5.5; pill reads "Extended Pro" or "Pro"). Required before any analytical submission.

2026-05-272

name	set-sources
description	Add or remove durable files in a ChatGPT project's Sources tab. Use after a verified result lands, after a route pivot, or when the durable proof-state file has been updated locally.

set-sources

Canonical content: .claude/commands/set-sources.md in this repo. Codex and Claude Code share the same procedure — edit the Claude command file, not this stub.

TL;DR for Codex sessions

Manage the ChatGPT project's Sources tab (the durable per-project context that every chat in that project sees). NOT the same as per-prompt composer attachments — see docs/browser_chatgpt.md for the durable-vs-temporary policy.

Typical use:

After a consolidator produces a new proof-state → refresh the durable proof-state source.
After a route pivot → remove the stale route memo, add the new one.
After scope changes → update the objective file.

Mechanics: shells out to scripts/chatgpt_browser_agent.sh prepare with --add-source PATH / --remove-source NAME flags. The browser refresh includes a cache-bust gap so new chats see the latest content.

Read .claude/commands/set-sources.md for full args + the durable-source housekeeping rules from CLAUDE.md.