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.
npx skills add cognitedata/builder-skills --skill dm-graph-traversalgit clone --depth 1 https://github.com/cognitedata/builder-skillsWrote 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/cognitedata/builder-skills/dm-graph-traversal)<a href="https://agentmods.dev/skills/cognitedata/builder-skills/dm-graph-traversal"><img src="https://agentmods.dev/badge/skills/cognitedata/builder-skills/dm-graph-traversal/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/cognitedata/builder-skills/dm-graph-traversal"><img src="https://agentmods.dev/badge/skills/cognitedata/builder-skills/dm-graph-traversal.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00053 | $0.02921 |
| Opus 5 | $0.00026 | $0.01460 |
| Sonnet 5 | $0.00011 | $0.00584 |
| Haiku 4.5 | $0.00005 | $0.00292 |
Grade A, and why
dm-graph-traversal 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 10d 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 — 360 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DM Graph Traversal
Outcome
Ship correct, maintainable, graph-native CDF Data Model reads.
This skill turns query/list ambiguity into a deterministic workflow:
- Decide whether the read is graph-native.
- Build safe
instances/querypayloads. - Validate traversal semantics and cursor behavior.
- Encode merge/dedupe policy explicitly.
- Lock behavior with payload-shape tests.
Decision Tree: instances/query vs instances/list
Use instances/query when any is true:
- You start from one node type and need related nodes/edges.
- You need reverse relation traversal (
direction,through,from). - You would otherwise do multiple list calls and stitch results client-side.
- You need step-specific pagination and relationship-aware filtering.
Use instances/list when all are true:
- Single node/edge type lookup.
- No traversal intent.
- Flat filtering is sufficient.
Heuristic:
- "If this read needs graph context, it is a query."
Search-First Entry Pattern
When user intent is discovery/ranking (for example free-text name matching), prefer:
instances.searchto find/rank candidate anchors.instances.queryto hydrate graph-related details for those anchors.
Why:
- Search APIs are better for ranking and fuzzy discovery.
- Query APIs are better for explicit graph traversal and constrained joins.
- This avoids broad traversal scans when the first step is actually discovery.
Operating Mode (Hard Rule)
- Default to Node.js/TypeScript workflows for parity checks, examples, and validator tooling.
- Use
code/validate-query-parity.cjsfor payload validation in all normal cases. - Do not introduce Python parity scripts by default in TypeScript repositories.
- Use Python-based validation only if the user explicitly requests Python or no viable Node.js path exists.
Related Skill Boundary
This skill is the source of truth for graph query correctness (traversal shape, refs, relation direction, and payload guardrails).
What ships with it
17 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- code/examples/cursor-shape-fail.json 1.0 KB
- code/examples/cursor-shape-pass.json 950 B
- code/examples/inwards-list-direct-relations-fail.json 1.6 KB
- code/examples/inwards-list-direct-relations-pass.json 1.4 KB
- code/examples/query1-fail.json 863 B
- code/examples/query1-pass.json 949 B
- code/examples/query2-fail.json 2.2 KB
- code/examples/query2-pass.json 2.3 KB
- code/examples/schema-hints.json 187 B
- code/examples/start-step-hasdata-fail.json 540 B
- code/examples/start-step-hasdata-pass.json 895 B
- code/examples/versioned-ref-fail.json 1.5 KB
- code/examples/versioned-ref-pass.json 1.5 KB
- code/validate-query-parity.cjs 13 KB runs code
- evals/evals.json 17 KB
- README.md 2.2 KB
- references/query-vs-list.md 1.6 KB
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.
- 10d ago First seen · 360 lines · 53 tokens per session scan A da70850da2db
dm-graph-traversal is a skill published in the GitHub repository cognitedata/builder-skills (6 stars, last pushed 3d ago), licensed Apache-2.0. It adds 53 tokens to every session and 2,921 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
event-store-design
Design and implement event stores for event-sourced systems. Use when building event sourcing infrastructure, choosing event store technologies, or implementing event persistence patterns.
convex-explain-app
Explain an existing Convex app — data model + relationships, public vs internal functions, auth/ownership model, components, a request→data flow — read from the schema and function surface. Read-only.
platform-custom-field-generate
Use this skill when users need to create, generate, or validate Salesforce Custom Field metadata. Trigger when users mention custom fields, field types, Roll-up Summary fields, Master-Detail relationships, Lookup relationships, formula fields, picklists, dependent (controlling) picklists, referencing a value set from…
field-service-sobject-create-configure
Headless 360 REST API deployment step for creating sObject records. Handles describe-based field discovery, required-field derivation, entity-relationship ordering, and composite graph transactions. Use this skill when a designer skill (or a user directly) needs to create sObject records after design confirmation…
durable-objects
Build, debug, or review Cloudflare Durable Objects code for persistent state and coordination.
nornicdb-grpc
Drive NornicDB over gRPC — the Qdrant-compatible surface (Collections, Points, Snapshots) plus the additive NornicSearch service. Use when ingesting via Qdrant SDKs, migrating from Qdrant, or running hybrid text+vector search from a non-Bolt client. Covers connection, RPC catalog, collection→database mapping…