graph-add

graph-add is a skill for Claude Code, Codex from xcota/pos. It costs 16 tokens per session (810 once invoked), scanned A, original, MIT.

A command for adding a person, project, concept, tool, decision, research item, business, or fact to a knowledge graph—a structured collection of connected notes.

In plain words
What is it for?
Creating knowledge notes, adding facts, finding related entities, and recording conflicts instead of overwriting disputed information.
Why use it?
It provides a consistent place and format for recording new knowledge, while checking for conflicting existing information.

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/xcota/pos/graph-add
Any agent
npx skills add xcota/pos --skill graph-add
Clone the repo
git clone --depth 1 https://github.com/xcota/pos

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 graph-add

README.md
[![agentmods](https://agentmods.dev/badge/skills/xcota/pos/graph-add.svg)](https://agentmods.dev/skills/xcota/pos/graph-add)
Your own site
<a href="https://agentmods.dev/skills/xcota/pos/graph-add"><img src="https://agentmods.dev/badge/skills/xcota/pos/graph-add.svg" alt="Measured on agentmods" height="20"></a>
Per session 16 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 810 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 $0.00016 $0.00810
Opus 5 $0.00008 $0.00405
Sonnet 5 $0.00003 $0.00162
Haiku 4.5 $0.00002 $0.00081

Measured 3d ago against content hash aaa1f9408467, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

graph-add 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 3d 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.

.claude/skills/graph-add/SKILL.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/graph-add — Add Knowledge to the Graph

Quickly add a new entity or fact to the knowledge graph.

Usage

/graph-add — interactive mode, asks questions /graph-add {type} {name} {facts} — direct mode

Entity Types

  • personknowledge/people/{name}.md
  • projectknowledge/projects/{name}.md
  • conceptknowledge/concepts/{name}.md
  • toolknowledge/tools/{name}.md
  • decisionknowledge/decisions/{date}-{name}.md
  • researchknowledge/research/{date}-{name}.md
  • businessknowledge/business/{name}.md

Steps

  1. Determine type (ask if not provided).
  2. Determine name (ask if not provided).
  3. Collect key facts (ask if not provided). 3b. Conflict checkgrep -rl "{normalized subject}" knowledge/. If an existing note asserts a DIFFERENT value for the same subject → do NOT overwrite: use conflict-as-record (see knowledge/conflicts/AGENTS.md) — create knowledge/conflicts/<slug>-conflict-{date}.md (both claims + provenance + promotion_blocked: true), downgrade the original to disputed, then stop and report to the user.
  4. Identify related entities — search existing files:
    grep -rl "{related term}" knowledge/
    
  5. Create the entity file:
    ---
    type: {type}
    tags: [{relevant tags}]
    updated: {today}
    # epistemic (optional, enums: knowledge/conflicts/AGENTS.md): modality · epistemic_status (fresh single-source → extracted_candidate) · confidence · last_verified · conflicts: []
    ---
    # {Name}
    
    {Key facts as prose or bullet points}
    
    ## Connections
    - Related to [[{entity-1}]] — {why}
    - Related to [[{entity-2}]] — {why}
    
  6. Update related entity files to add a backlink [[{new-entity}]].
  7. Report what was created and linked.

File Naming

  • Lowercase, hyphens for spaces: "Acme Corp" → acme-corp.md.
  • Decisions and research are date-prefixed: 2026-01-05-chose-obsidian.md.
  • Max 60 chars.

Rules

  • Always add [[wikilinks]] to related entities.
  • MANDATORY: update backlinks in ≥1 related file — a new entity MUST have ≥1 incoming link. If you create a file and no other file links to it, it's invisible in the graph. This is the #1 graph quality rule.
  • Don't create duplicates — search first: grep -rl "term" knowledge/.
  • Keep entity files focused: one entity = one file.
  • Minimum content: YAML frontmatter + 1 paragraph + ≥2 outgoing [[wikilinks]] + ≥1 incoming backlink added to another file.

Read the full file on GitHub · 75 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. 3d ago First seen · 75 lines · 16 tokens per session scan A aaa1f9408467

Subscribe to this mod's changes

graph-add is a skill published in the GitHub repository xcota/pos (43 stars, last pushed 1mo ago), licensed MIT. It adds 16 tokens to every session and 810 once invoked, about $0.0001 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 2026-08-30.

Related

Other skills, from other repositories

ori-memory

Persistent agent memory with learning retrieval. Knowledge graph on markdown files — capture insights, decisions, research, and learnings during work, then retrieve them weeks or months later. Use when knowledge is too valuable to lose but too much to inject into every prompt.

aayoawoyemi/Ori-Mnemos · 54 tokens

rtg-knowledge-graph-mcp

Operate the Vellis RTG Knowledge Graph MCP server for agent-driven graph work. Use when an agent has RTG MCP tools such as rtgvalidategraph, rtgapplylivegraphchanges, rtgstageknowledgechanges, rtgapplymigrationcutover, rtgexecutequery, snapshots, or ledger replay, especially for schema evolution, validation recovery…

volantlabs/vellis · 87 tokens

documentation-sync

Keep human documentation synchronized with canonical SysML v2 models, generated component and application views, implementation realizations, repository tooling, skills, and workflow rules. Use after model, code, generated-view, README, AGENTS, skill, command, or public behavior changes.

volantlabs/vellis · 57 tokens

python-component-implementation

Implement, review, or revise Python realizations of components from accepted textual SysML v2 contracts and generated views. Use when creating or aligning Python protocols, component classes, reference implementations, implementation bindings, or black-box contract tests.

volantlabs/vellis · 51 tokens

sysml-reference

Ground textual SysML v2 and KerML authoring, review, language-semantics decisions, construct selection, and official-validator diagnosis in the repository's checksum-pinned specification corpus. Use for questions or changes involving parts, references, features, actions, bindings, successions, flows, ports…

volantlabs/vellis · 92 tokens

model-hygiene-review

Audit accepted SysML v2 component or application models against implementations, protocols, consumers, tests, generated evidence, predecessor contracts, and git history before proposing remediation. Use for periodic model hygiene, suspected model/implementation drift, migration-loss reviews, verification-closure…

volantlabs/vellis · 72 tokens