evolve-lite:provenance SKILL.md skillA
evolve-lite:provenance from agenttoolkit/altk-evolve is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add agenttoolkit/altk-evolve/evolve-lite:provenance@git:20261021.2a75491Pins git:20261021.2a75491 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- agenttoolkit/altk-evolve
- Path
platform-integrations/bob/evolve-lite/skills/evolve-lite-provenance/SKILL.md- Versions recorded
- 4
- Latest version
- git:20261021.2a75491, committed Oct 21, 2026
- First version recorded
- May 7, 2026
- Size
- 5,618 bytes
- Repository stars
- 135
- License
- Apache-2.0
Analyze saved trajectories and recall audit events offline to record whether recalled guidelines influenced completed sessions.
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 Analyzer
## Overview
This skill runs after one or more sessions have completed. It reads `recall`
events from `.evolve/audit.log`, locates each session's trajectory, and records
post-hoc `influence` events for the recalled guidelines.
The mechanical work — reading recall rows, skipping already-assessed pairs,
resolving entity files, and locating trajectories — is done deterministically by
`provenance.py candidates`. Your job is the judgment: read each candidate and
decide whether the recalled guideline was `followed`, `contradicted`, or
`not_applicable` — or that the trajectory is `insufficient_evidence` to tell —
then persist that verdict.
Use this skill when you want to compute usage provenance without coupling the
work to the live learn step.
## Workflow
### Step 1: Get candidates
Run the candidate builder. It emits one JSON object per line (JSONL), one per
unresolved `(session_id, entity)` recall pair:
```bash
python3 .bob/skills/evolve-lite-provenance/scripts/provenance.py candidates
```
Each candidate looks like:
```json
{
"session_id": "<session-id>",
"entity_id": "<type>/<name>",
"entity_excerpt": "<frontmatter + content of the entity file>",
…Read the whole file at its exact version.
How to install
mdr add agenttoolkit/altk-evolve/evolve-lite:provenance@sha256:d0a68cedd215cd6eThe line at the top of this page pins the label git:20261021.2a75491, 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_whwhxaru7idlnldp)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 4 versions of this file, between May 7, 2026 and Oct 21, 2026, about one every 56 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261021.2a75491 latest | 2026-10-21 | 2a75491 | 5,618 B | A | view · diff |
| git:20261019.c7a98c1 | 2026-10-19 | c7a98c1 | 5,440 B | A | view · diff |
| git:20260625.6f2bfc0 | 2026-06-25 | 6f2bfc0 | 4,238 B | A | view · diff |
| git:20260507.d7a3f49 | 2026-05-07 | d7a3f49 | 3,013 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 (5618 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
agenttoolkit/altk-evolve · 135 stars · license Apache-2.0 · pushed 2026-10-28 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_whwhxaru7idlnldp GET https://markdownregistry.com/api/v1/resolve?ref=agenttoolkit/altk-evolve/evolve-lite:provenance GET https://markdownregistry.com/api/v1/blob/d0a68cedd215cd6e211bd671ce3ca498283cffd9fc4fb28ae9743f36789951a4
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.