agentmods.dev

c2pa-knowledge-graph: Skill for Claude Code

.claude/skills/c2pa-kg/SKILL.md

c2pa-kg is a skill for Claude Code from encypherai/c2pa-knowledge-graph. It costs 81 tokens per session (1,183 once invoked), scanned A, original, Apache-2.0.

A query tool for the C2PA standard, which defines how digital media can carry information about its origin and changes.

In plain words
What is it for?
Use it to look up C2PA entities, manifests, validation requirements, and differences between specification versions.
Why use it?
It provides specification-based answers about C2PA data structures and rules instead of requiring you to search large technical documents.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

This is encypherai/c2pa-knowledge-graph's own configuration. It tells Claude Code how to work on c2pa-knowledge-graph itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything c2pa-knowledge-graph configures →

not rated 3repo 5mo ago A scan 81 tokens original Apache-2.0
View source ↗ encypherai/c2pa-knowledge-graph
Reuse

Borrowing it

Nothing to install: this file belongs to encypherai/c2pa-knowledge-graph. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/encypherai/c2pa-knowledge-graph/main/.claude/skills/c2pa-kg/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/encypherai/c2pa-knowledge-graph

Made for: Claude Code.

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 c2pa-kg

README.md
[![agentmods](https://agentmods.dev/badge/skills/encypherai/c2pa-knowledge-graph/c2pa-kg/github.svg)](https://agentmods.dev/skills/encypherai/c2pa-knowledge-graph/c2pa-kg)
Your own site
<a href="https://agentmods.dev/skills/encypherai/c2pa-knowledge-graph/c2pa-kg"><img src="https://agentmods.dev/badge/skills/encypherai/c2pa-knowledge-graph/c2pa-kg/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.

agentmods 80×15 button for c2pa-kg

Your own site · 80×15
<a href="https://agentmods.dev/skills/encypherai/c2pa-knowledge-graph/c2pa-kg"><img src="https://agentmods.dev/badge/skills/encypherai/c2pa-knowledge-graph/c2pa-kg.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 81 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,183 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00081 $0.01183
Opus 5.5 $0.00032 $0.00473
Sonnet 5.5 $0.00016 $0.00237
Haiku 4.5 $0.00008 $0.00118

Measured 2mo ago against content hash 0d35d4972db1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

c2pa-kg 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 2mo 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/c2pa-kg/SKILL.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

C2PA Knowledge Graph Query

You have access to a machine-readable knowledge graph derived from the C2PA specification. Use it to answer questions about C2PA data structures, validation rules, and version changes with precision rather than relying on training data.

Data sources

The knowledge graph is generated from the C2PA specs-core repository and stored as JSON artifacts. Check for pre-generated artifacts in this order:

  1. MCP tools (if c2pa-knowledge-graph MCP server is running): use query_entity, query_validation_rules, diff_versions, or search_entities tools directly.
  2. Local artifacts: look for output/<version>/metadata.json in the c2pa-knowledge-graph repo directory. If found, read and parse the JSON.
  3. Generate on demand: if no artifacts exist and the user has specs-core cloned locally, run uv run c2pa-kg generate --spec-source <path> --version <version> --output-dir ./output.

How to answer queries

Entity lookup

When asked about a C2PA entity (e.g., "what properties does a Claim have?"):

  1. Load metadata.json for the requested version (default: latest, currently 2.4).
  2. Look up the entity in the entities dict. Entity names are CamelCase (e.g., ClaimMap, ClaimMapV2, ActionItemsMap, IngredientMapV3).
  3. Report the entity's properties (name, type, required, cardinality, description), relationships (target entity, relationship type), and whether it is deprecated.
  4. If the entity name is ambiguous, search across all entity names and suggest matches.

Validation rules

When asked about validation requirements:

  1. Load validation rules from metadata.json -> validation_rules.
  2. Filter by phase if specified: structural, cryptographic, trust, semantic, assertion, ingredient, timestamp, signature, content.
  3. Report rules with their severity (must/shall/should/may), description, and referenced entities.
  4. Cross-reference with status codes from status_codes when relevant.

Read the full file on GitHub · 103 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. 2mo ago First seen · 103 lines · 81 tokens per session scan A 0d35d4972db1

Subscribe to this mod's changes

c2pa-kg is a skill published in the GitHub repository encypherai/c2pa-knowledge-graph (3 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 81 tokens to every session and 1,183 once invoked, about $0.0003 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.

Legal and compliance
Related

c2pa-kg compared with skills from other repositories

c2pa-kg next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
c2pa-kgencypherai/c2pa-knowledge-graphSkill35mo agoApache-2.0A81Claude Code
fto-triageanthropics/claude-for-legalSkill10.0k5d agoApache-2.0A81Claude Code
legal-holdanthropics/claude-for-legalSkill10.0k5d agoApache-2.0A68Claude Code
specification-writingwanshuiyin/Auto-claude-code-research-in-sleepSkill19k2d agoMITA49Claude Code
regulatory-research-fallbackHKUDS/OpenSpaceSkill7.9k7d agoMITA20Claude Code, Codex
terms-of-servicegenspark-ai/genofficeSkill12ktodayApache-2.0A32Claude Code, Codex
x-scorecardx-cmd/x-cmdSkill4.8k14d agoApache-2.0A57Claude Code, Codex