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/asset-editnpx skills add collibra/chip --skill asset-editgit 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 | $0.00020 | $0.00948 |
| Opus 5 | $0.00010 | $0.00474 |
| Sonnet 5 | $0.00004 | $0.00190 |
| Haiku 4.5 | $0.00002 | $0.00095 |
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 3d 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 — 66 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, or email) |
remove_responsibility |
Unassign a user or group from a resource role | role, userId (UUID, username, or email) |
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 three forms. For
set_responsibilityandremove_responsibility,userIdmay be a UUID, a username, or an email. Chip resolves the form server-side. 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.
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.
- 3d ago First seen · 66 lines · 20 tokens per session scan A 2fe7ae5ce85f
asset-edit is a skill published in the GitHub repository collibra/chip (36 stars, last pushed 5d ago), licensed Apache-2.0. It adds 20 tokens to every session and 948 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
prisma-upgrade-v7
Complete migration guide from Prisma ORM v6 to v7 covering all breaking changes. Use when upgrading Prisma versions, encountering v7 errors, or migrating existing projects. Triggers on "upgrade to prisma 7", "prisma 7 migration", "prisma-client generator", "driver adapter required".
ddia-systems
Design data systems by understanding storage engines, replication, partitioning, transactions, and consistency models. Use when the user mentions "database choice", "which database should I use", "SQL or NoSQL", "replication lag", "partitioning strategy", "consistency vs availability", "stream processing", "ACID…
sqlitecpp-update-sqlite
How to update the bundled SQLite3 amalgamation (sqlite3/sqlite3.c and sqlite3.h), the Meson wrap, README.md, and CHANGELOG.md. Use when upgrading SQLite, refreshing the vendored amalgamation, or bumping the sqlite3 wrap.
dsql
Build with Aurora DSQL — manage schemas, execute queries, handle migrations, diagnose query plans, diagnose cluster performance, load data, and develop applications with a serverless, distributed SQL database. Covers IAM auth, multi-tenant patterns, MySQL-to-DSQL and PostgreSQL-to-DSQL schema conversion, FK…
mongodb-natural-language-querying
Generate read-only MongoDB queries (find) or aggregation pipelines using natural language, with collection schema context and sample documents. Use this skill whenever the user asks to write, create, or generate MongoDB queries, wants to filter/query/aggregate data in MongoDB, asks "how do I query...", needs help with…
sql-translate
Translate SQL queries between database dialects (Snowflake, BigQuery, PostgreSQL, MySQL, etc.).