provenance-dag SKILL.md skillA
provenance-dag from docxology/template is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add docxology/template/provenance-dag@git:20261105.00a79ffPins git:20261105.00a79ff in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- docxology/template
- Path
infrastructure/provenance/SKILL.md- Versions recorded
- 6
- Latest version
- git:20261105.00a79ff, committed Nov 5, 2026
- First version recorded
- Jul 6, 2026
- Size
- 4,791 bytes
- Repository stars
- 23
- License
- Apache-2.0
Content-addressed provenance DAG for research lineage tracking. Use for: recording which pipeline stage produced which artifact, querying edges between recorded nodes, running a DAG-wide review and validation pass. CLI: python -m infrastructure.provenance {list,record-artifact,review,validate}. Library: infrastructure.provenance.Provenance (record/link/get/list/query). Orchestrator: scripts/pipeline/stage_09_provenance_record.py --project {name} --stage NAME.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Provenance DAG
Content-addressed provenance DAG for tracking research artifact lineage.
Every artifact node is identified by a SHA-256 content hash; edges record
which pipeline stage produced each artifact from which inputs.
## Quick Start
```python
from infrastructure.provenance import ArtifactNode, EdgeRelation, Provenance, RunNode
store = Provenance.with_path("output/.provenance")
# Record that a run produced an artifact
run = RunNode.create("analysis run", command="uv run python scripts/pipeline/stage_02_analysis.py")
artifact = ArtifactNode.create("results.json", path="output/results.json")
store.record(run)
store.record(artifact)
# Link the artifact to the run that produced it
store.link(run.node_id, artifact.node_id, EdgeRelation.produced_by)
```
## CLI
```bash
# Record an artifact node
uv run python -m infrastructure.provenance record-artifact "results.json" --path output/results.json
# List all recorded nodes (optionally filter by kind: artifact/run/source/claim)
uv run python -m infrastructure.provenance list --kind artifact
# Run the DAG-wide review pass (missing hashes, missing exit codes, etc.)
uv run python -m infrastructure.provenance review --json
…Read the whole file at its exact version.
How to install
mdr add docxology/template/provenance-dag@sha256:3b8a868976048a8aThe line at the top of this page pins the label git:20261105.00a79ff, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_4nj3x4o5jkso365d)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 6 versions of this file, between Jul 6, 2026 and Nov 5, 2026, about one every 24 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261105.00a79ff latest | 2026-11-05 | 00a79ff | 4,791 B | A | view · diff |
| git:20260820.0db2afc | 2026-08-20 | 0db2afc | 4,850 B | A | view · diff |
| git:20260723.890bcd4 | 2026-07-23 | 890bcd4 | 4,702 B | A | view · diff |
| git:20260707.6e77eab | 2026-07-07 | 6e77eab | 4,683 B | A | view · diff |
| git:20260706.ade9b57 | 2026-07-06 | ade9b57 | 3,780 B | A | view · diff |
| git:20260706.11e587f | 2026-07-06 | 11e587f | 3,735 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (4791 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
docxology/template · 23 stars · license Apache-2.0 · pushed 2026-11-08 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_4nj3x4o5jkso365d GET https://markdownregistry.com/api/v1/resolve?ref=docxology/template/provenance-dag GET https://markdownregistry.com/api/v1/blob/3b8a868976048a8a4d8b78545eff77457023d4bc381e07f3276151bd3eeff940
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.