with one click
papyrus-link
Atomic — add one typed edge between two needs
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.
Menu
Atomic — add one typed edge between two needs
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.
Based on SOC occupation classification
| name | papyrus-link |
| description | Atomic — add one typed edge between two needs |
Create one typed directed edge from a source need to a target need. The target may live in the same Papyrus workspace or in a configured external pharaoh workspace.
papyrus get <mem_id> shows <link_type>: <target_id> in the rendered outputinput:
mem_id: existing need id in current workspace chain
target_id: existing id in the chain OR in a configured external pharaoh workspace
link_type: one of: relates, supports, depends, supersedes, contradicts, extends, derives, satisfies
output:
side effect: append edge to source need's RST directive (no-op if triple already present)
stdout: "Linked <mem_id> -<link_type>-> <target_id>"
exit: 0 on success; non-zero on unknown id or invalid link_type
After invocation:
papyrus get <mem_id> | grep ":<link_type>:" | grep "<target_id>"
Exits 0 = success.
CLI:
papyrus link <mem_id> <target_id> --as <link_type>
MCP tool memory_link:
{"mem_id": "DEC_foo", "target_id": "REQ_bar", "link_type": "satisfies"}
Capture-and-link (most common flow):
papyrus-write new DEC/RISKpapyrus-link to the requirement or parent decision it's aboutCross-scope link (after promote):
papyrus-promote --to program elevates the needpapyrus-link from the promoted need to a program-scope requirementRetrofit graph (hygiene flow):
papyrus-query to find orphan needs (no outgoing links)papyrus-link to appropriate targetshared/link-types.md — semantics of each link_typepapyrus-write — typical predecessorpapyrus-impact — consumer of the graph built by linkpapyrus-trace — consumer for supersession chainsAtomic — search memories by filter (lexical or semantic), return ranked list
Atomic — regenerate .papyrus/index.json and (optionally) semantic vectors for a workspace
Atomic — mark a memory deprecated, optionally with supersedes link
Atomic — list memories whose review_after has passed
Atomic — fetch a single memory in full by id
Atomic — bidirectional graph walk from a starting need