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/discoverynpx skills add collibra/chip --skill discoverygit 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 | $0.00019 | $0.00763 |
| Opus 5 | $0.00010 | $0.00381 |
| Sonnet 5 | $0.00004 | $0.00153 |
| Haiku 4.5 | $0.00002 | $0.00076 |
Grade A, and why
discovery 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Discovery — finding assets and business terms
Chip has three discovery entry points. They serve different shapes of question; picking the wrong one is the most common cause of empty results.
Decision rule
- Open-ended, conceptual, or paraphrased question ("what customer data do we have?",
"find tables with revenue figures") →
discover_data_assets(semantic search over data assets) ordiscover_business_glossary(semantic search over the business glossary). - Exact name known, or filtering by type/community/domain/status →
search_asset_keyword. Its filters accept a name or a UUID — passassetType: "Table"orstatus: "Obsolete"directly; no separate UUID lookup is needed. - Browsing or disambiguating asset type names →
list_asset_types(not required just to filter — theassetTypefilter already resolves names).
Do not start with search_asset_keyword for paraphrased questions. The keyword search will
miss synonyms, plurals, and definitional matches that semantic search returns.
Permission gates
discover_data_assetsanddiscover_business_glossaryrequire thedgc.ai-copilotscope. If a call returns a permission error, surface the scope name to the user — do not silently fall back to keyword search, because the result set will be qualitatively different.search_asset_keywordandlist_asset_typeswork with default catalog read scopes.
Workflow: from name to UUID
Most chip tools require a UUID. The pattern:
- Call
discover_data_assets(ordiscover_business_glossary, orsearch_asset_keyword) with the user's phrasing. - From the response, pick the UUID of the asset whose name and type match the user's intent. If multiple plausible matches exist, present them to the user and ask which they meant — do not guess.
- Pass that UUID to the next tool (
get_asset_details,get_table_semantics,get_column_semantics,get_measure_data,get_business_term_data, etc.).
Hard rules
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 · 62 lines · 19 tokens per session scan A 03d0368df0f7
discovery is a skill published in the GitHub repository collibra/chip (36 stars, last pushed 4d ago), licensed Apache-2.0. It adds 19 tokens to every session and 763 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…