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 agentmods add skills/collibra/chip/contextnpx skills add collibra/chip --skill contextgit clone --depth 1 https://github.com/collibra/chipWhat 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 | $0.00053 | $0.02786 |
| Opus 5 | $0.00026 | $0.01393 |
| Sonnet 5 | $0.00011 | $0.00557 |
| Haiku 4.5 | $0.00005 | $0.00279 |
Grade A, and why
context 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 2d 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 — 253 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context generation: extract shaped metadata for any target system
A Context Specification is a blueprint that defines a governed subset of Collibra's Knowledge Graph. Starting from an asset (e.g., a Table), it specifies which relations to traverse, what fields to pull, and what shape to return for any target system: Snowflake, Databricks, a data product UI, or an AI agent's reasoning process.
In other words: Context Specifications define which slice of the Knowledge Graph matters for a specific use case, and what shape that slice should take when delivered to downstream consumers.
This skill explains the three-tool workflow: discover which specs are available, inspect a spec if needed, and execute it to get the shaped output.
The three tools
| Tool | Purpose | Returns | When required |
|---|---|---|---|
list_context_specifications |
Discover which Context Specifications (Knowledge Graph blueprints) are available for an asset or asset type | List of spec names, descriptions, and IDs | Always, entry point |
get_context_specification |
Inspect a spec's blueprint: which relations it defines, what fields it extracts from the Knowledge Graph, what transforms it applies | Complete YAML mapping and spec metadata | Optional, only when user asks what a spec covers |
get_asset_details (with contextSpecificationId) |
Execute a spec's blueprint against an asset to extract and shape its governed metadata subset; returns full asset details alongside the generated context | Asset details + structured YAML context shaped for the target system | Always, output step |
Decision rule: which tool to call first
Always start with list_context_specifications. It takes one of two parameters:
Option A: You have an asset UUID
Call list_context_specifications(assetId=<UUID>) to find specs whose source asset type matches that asset's type.
Use when: You've already resolved a user's request to a specific Collibra asset (e.g., "the Orders table" → resolved to UUID abc-123).
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.
- 2d ago First seen · 253 lines · 53 tokens per session scan A 22f2f9a91832
context is a skill published in the GitHub repository collibra/chip (36 stars, last pushed 4d ago), licensed Apache-2.0. It adds 53 tokens to every session and 2,786 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…