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 collibra/chip --skill asset-editgit clone --depth 1 https://github.com/collibra/chipWrote 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/collibra/chip/asset-edit)<a href="https://agentmods.dev/skills/collibra/chip/asset-edit"><img src="https://agentmods.dev/badge/skills/collibra/chip/asset-edit/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/collibra/chip/asset-edit"><img src="https://agentmods.dev/badge/skills/collibra/chip/asset-edit.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 | $0.00020 | $0.01079 |
| Opus 5.5 | $0.00008 | $0.00432 |
| Sonnet 5.5 | $0.00004 | $0.00216 |
| Haiku 4.5 | $0.00002 | $0.00108 |
Grade A, and why
asset-edit 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 28d 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Editing assets
edit_asset applies a list of typed operations to a single asset, identified by UUID.
Each operation has its own required fields; mixing operation types in one call is fine and
runs them in order.
Operation types
| Operation | Use for | Key fields |
|---|---|---|
set_attribute |
Set an attribute's value (e.g. Definition, Note) — creates it if empty, updates it if already set |
attributeName, value |
add_attribute |
Append an additional value to a multi-valued attribute | attributeName, value |
remove_attribute |
Clear an attribute value | attributeName (optionally a specific value) |
update_property |
Change asset-level properties: name, displayName, statusId |
field, value |
add_relation |
Link this asset to another by relation role (e.g. is synonym of) |
relationType, target asset identifier |
remove_relation |
Unlink a relation | relationType, target asset identifier |
add_tag |
Append a free-text tag (does not replace existing tags) | tag |
set_responsibility |
Assign a user or group to a resource role (e.g. Steward, Owner) |
role, userId (UUID, username, email, or full name) |
remove_responsibility |
Unassign a user or group from a resource role | role, userId (UUID, username, email, or full name) |
Hard rules
set_attributevsadd_attribute. Useset_attributefor normal single-valued attributes (likeDefinition) — it creates the value if absent and updates it if present, so you never need to know the current state first.add_attributeonly appends an extra value to a multi-valued attribute. To see which attributes an asset can hold — including ones that are valid but currently empty — callget_asset_detailsand readassignableAttributes. An attribute missing from the asset's values but present there is settable, not invalid.update_propertyis restricted. Only three fields are allowed:name,displayName,statusId. Other fields return an error listing the allowed set.statusIdaccepts names. Pass a human-readable status name (e.g."Candidate","Accepted") or the UUID — chip resolves either.- Responsibility ops accept user identifiers in four forms. For
set_responsibilityandremove_responsibility,userIdmay be a UUID, a username, an email, or a person's full name ("Jane Smith"). Chip resolves the form server-side; a full name shared by several users comes back as an error listing the candidates — ask which person is meant rather than picking one, or resolve it up front withget_user_id_by_name. The same applies torelationTypetargets inadd_relation/remove_relation. remove_responsibilityonly removes direct responsibilities. It deletes a responsibility assigned directly on the asset; one inherited from a parent domain or community can't be removed here and returns an error pointing to where it's defined.- RICH_TEXT attribute values are Markdown. Same rule as
create_asset— write Markdown, chip converts to HTML. Seeshared/rich-text-markdown.mdfor the full rules. - Read-only attributes can't be edited.
set_attribute,add_attributeandremove_attributereturn an error for an attribute the assignment marks read-only, because Collibra calculates its value (e.g. a trust score). Tell the user the value is calculated; don't retry or report it as changed.
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.
- 28d ago Changed · +6 lines a80647d93223
- 2mo ago First seen · 66 lines · 20 tokens per session scan A 2fe7ae5ce85f
asset-edit is a skill published in the GitHub repository collibra/chip (37 stars, last pushed yesterday), licensed Apache-2.0. It adds 20 tokens to every session and 1,079 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.
asset-edit compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| asset-editcollibra/chip | Skill | 37 | yesterday | Apache-2.0 | A | 20 | Claude Code, Codex |
| create-prprisma/orm | Skill | 48k | yesterday | Apache-2.0 | A | 48 | Claude Code, Codex |
| schema-explorationlangchain-ai/deepagents | Skill | 31k | yesterday | MIT | A | 57 | Claude Code, Codex |
| atlas-mssqlariga/atlas | Skill | 8.8k | yesterday | Apache-2.0 | A | 163 | Claude Code |
| ha-data-storesshiwenwen/hope-agent | Skill | 1.9k | yesterday | MIT | A | 115 | Claude Code, Codex |
| nornicdb-cypher-queriesorneryd/NornicDB | Skill | 923 | yesterday | MIT | A | 79 | Claude Code, Codex |
| volcengine-rds-postgresqlbytedance/agentkit-samples | Skill | 484 | today | Apache-2.0 | A | 63 | Claude Code, Codex |