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/datachain-ai/datachain/knowledgenpx skills add datachain-ai/datachain --skill knowledgegit clone --depth 1 https://github.com/datachain-ai/datachainWhat 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 | $0.00104 | $0.02455 |
| Opus 5 | $0.00052 | $0.01228 |
| Sonnet 5 | $0.00021 | $0.00491 |
| Haiku 4.5 | $0.00010 | $0.00246 |
Grade A, and why
datachain-knowledge 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 yesterday.
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 — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Maintain a knowledge base at dc-knowledge/. .md files are the persistent
output. .json files are intermediate (generated in Step 3, consumed in
Step 4, then deleted).
CAST.md (sibling to this file) is the canonical methodology — the four
layers, naming + tagging, layer-ladder planning, calibration, dialogue
template, reuse rules, methodology transmission. Mode B reads it in full
as a precondition. When something methodology-related needs to change,
change CAST.md, not this file.
Critical Rules
CAST.md §6 owns the CAST-doctrine rules (follow CAST, never bypass
DataChain, C/A/S substrate mandatory, one script per stage, one
.save() per script). The rules below are operational additions unique
to this skill.
- Path is
dc-knowledge/— NOT.datachain/. The.datachain/directory is the internal database; the knowledge base lives atdc-knowledge/. - Never pass
update=Truetodc.read_storage()in Task or exploration code unless the user explicitly asks to refresh the listing. L1/L2/L3 build scripts are the exception (CAST.md§5). - Prefer DataChain operations over plain Python for all metadata analysis.
- Bounded output — JSON and markdown files stay small regardless of data size.
- Stop on auth/connection errors —
bucket_scan.pyruns a fast access check. If it exits with an error JSON on stderr, stop immediately and show the error to the user. Do not retry with different regions, profiles, or endpoints — ask for the missing credentials. - Follow the enrichment prompt template literally in Step 4. Downstream tooling (
render_index.py,cast_layerresolution) parses the exact frontmatter the prompt prescribes.
Common gotchas in UDF scripts
parallel=Nvsworkers=N.parallel=Nis local multiprocessing (works anywhere).workers=Nis Studio-only and MUST be guarded:chain = chain.settings(parallel=N); if dc.is_studio(): chain = chain.settings(workers=N).- No
from __future__ import annotationsin UDF modules. It stringifies type hints and DataChain's signal-schema resolution rejects the string-vs-class mismatch. - Type the UDF return precisely.
Iterator[object]/Iterator[Any]/ baredictfail schema resolution. Return a specificIterator[T], a PydanticBaseModel, or a primitive. - Generators aren't subscriptable. Iterators returned by file APIs do not support
[:N]. Useenumerate+break, orlist(...)only when the result is genuinely small. - Use
datachain.__version__to get the package version (e.g.dc.__version__).
What ships with it
21 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- __init__.py 0 B runs code
- CAST.md 46 KB
- collect.py 1.9 KB runs code
- prompts/enrich_bucket.md 5.4 KB
- prompts/enrich.md 8.4 KB
- scripts/__init__.py 0 B runs code
- scripts/bucket_overview.py 3.9 KB runs code
- scripts/bucket_scan.py 17 KB runs code
- scripts/changes.py 2.0 KB runs code
- scripts/cleanup_json.py 1.8 KB runs code
- scripts/dataset_all.py 12 KB runs code
- scripts/dataset.py 7.2 KB runs code
- scripts/db_mtime.py 815 B runs code
- scripts/list_datasets.py 1.1 KB runs code
- scripts/plan.py 8.2 KB runs code
- scripts/render_index.py 11 KB runs code
- scripts/schema.py 2.6 KB runs code
- scripts/summary.py 18 KB runs code
- scripts/utils.py 17 KB runs code
- snapshot.py 7.5 KB runs code
- types.py 3.1 KB runs code
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.
- yesterday First seen · 219 lines · 104 tokens per session scan A de52962a5066
datachain-knowledge is a skill published in the GitHub repository datachain-ai/datachain (2,811 stars, last pushed yesterday), licensed Apache-2.0. It adds 104 tokens to every session and 2,455 once invoked, about $0.0005 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
mcp-builder
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
comet-hotfix
Comet 预设 —— 通过 open-build-verify-archive 短流程修复已有行为 bug。.
comet-verify
Comet Phase 4: Verify and Close. Invoke with /comet-verify. Verify implementation matches design, handle development branch.
comet-design
Comet Classic 阶段 2 —— 为 change 产出深度技术 Design Doc。.
comet-hotfix
Comet preset path: Bug fix / hotfix. Skip brainstorming, directly open → build → verify → archive. Applicable for behavior fixes, scenarios not involving new capability design.
comet-tweak
Comet preset path: Non-bug small changes (tweak). Skip brainstorming and full plan, directly open → lightweight build → light verify → archive. Applicable for copy, configuration, documentation or prompt local optimization.