discovery

discovery is a skill for Claude Code, Codex from collibra/chip. It costs 19 tokens per session (866 once invoked), scanned A, original, Apache-2.0.

A decision guide for finding Collibra data assets and business terms using either meaning-based search or exact-word filters. Collibra is a catalogue for organising and describing company data.

In plain words
What is it for?
It supports open-ended searches, exact-name or filtered searches, and checking available asset types.
Why use it?
It helps choose the right search method, reducing empty or incomplete results when a question is phrased differently from an asset's name.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It supports open-ended searches, exact-name or filtered searches, and checking available asset types.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/collibra/chip/discovery
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.

Any agent
npx skills add collibra/chip --skill discovery
Clone the repo
git clone --depth 1 https://github.com/collibra/chip

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 discovery

README.md
[![agentmods](https://agentmods.dev/badge/skills/collibra/chip/discovery/github.svg)](https://agentmods.dev/skills/collibra/chip/discovery)
Your own site
<a href="https://agentmods.dev/skills/collibra/chip/discovery"><img src="https://agentmods.dev/badge/skills/collibra/chip/discovery/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 discovery

Your own site · 80×15
<a href="https://agentmods.dev/skills/collibra/chip/discovery"><img src="https://agentmods.dev/badge/skills/collibra/chip/discovery.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 866 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00019 $0.00866
Opus 5.5 $0.00008 $0.00346
Sonnet 5.5 $0.00004 $0.00173
Haiku 4.5 $0.00002 $0.00087

Measured 2mo ago against content hash 9a37bd4bd1c6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 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.

pkg/skills/files/collibra/discovery/SKILL.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 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) or discover_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 — pass assetType: "Table" or status: "Obsolete" directly; no separate UUID lookup is needed.
  • Disambiguating an asset type name → list_asset_types (not required just to filter — the assetType filter 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_assets and discover_business_glossary require the dgc.ai-copilot scope. 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_keyword and list_asset_types work with default catalog read scopes.

Workflow: from name to UUID

Most chip tools require a UUID. The pattern:

  1. Call discover_data_assets (or discover_business_glossary, or search_asset_keyword) with the user's phrasing.
  2. 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.
  3. 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

  1. Do not paraphrase the user when searching. The semantic search ranks against the user's own wording — passing a rewritten query loses signal.
  2. Resolve ambiguity before drilling down. If two assets share a name across domains, ask the user which they want. Do not call detail tools on a guess.
  3. list_asset_types is for confirming or disambiguating a type, not for browsing. search_asset_keyword's assetType filter accepts a type name or UUID directly, so reach for list_asset_types only when a name is ambiguous — not as a first-step exploration tool. To disambiguate, pass name to narrow server-side, or product (e.g. HELPDESK, GLOSSARY) to separate a real product type from a test/decoy type of the same name. A publicId/product filter scans a bounded window of the catalog — check resultsTruncated before treating the result as complete; if it is true, narrow further with name rather than trusting the list.

Read the full file on GitHub · 66 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 Changed · +4 lines 9a37bd4bd1c6
  2. 2mo ago First seen · 62 lines · 19 tokens per session scan A 03d0368df0f7

Subscribe to this mod's changes

discovery is a skill published in the GitHub repository collibra/chip (37 stars, last pushed yesterday), licensed Apache-2.0. It adds 19 tokens to every session and 866 once invoked, about $0.0001 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 2026-08-30.

Related

discovery compared with skills from other repositories

discovery next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
discoverycollibra/chipSkill37yesterdayApache-2.0A19Claude Code, Codex
create-prprisma/ormSkill48kyesterdayApache-2.0A48Claude Code, Codex
schema-explorationlangchain-ai/deepagentsSkill31kyesterdayMITA57Claude Code, Codex
atlas-mssqlariga/atlasSkill8.8kyesterdayApache-2.0A163Claude Code
ha-data-storesshiwenwen/hope-agentSkill1.9kyesterdayMITA115Claude Code, Codex
nornicdb-cypher-queriesorneryd/NornicDBSkill923yesterdayMITA79Claude Code, Codex
volcengine-rds-postgresqlbytedance/agentkit-samplesSkill484todayApache-2.0A63Claude Code, Codex