Agent skill

Provenance

by AgentToolkit in AgentToolkit/altk-evolve

Analyze saved trajectories and recall audit events offline to record whether recalled guidelines influenced completed sessions.

Apache-2.0Auto-check passedAgent Workflows

Install Provenance

skills CLI

$ npx skills add AgentToolkit/altk-evolve --skill provenance -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install AgentToolkit/altk-evolve provenance --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/AgentToolkit/altk-evolve.git skills-src && mkdir -p .claude/skills && cp -r skills-src/platform-integrations/codex/plugins/evolve-lite/skills/evolve-lite/provenance .claude/skills/provenance && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "provenance" agent skill from https://github.com/AgentToolkit/altk-evolve/tree/main/platform-integrations/codex/plugins/evolve-lite/skills/evolve-lite/provenance into .claude/skills/provenance/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "provenance", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/AgentToolkit/altk-evolve/tree/main/platform-integrations/codex/plugins/evolve-lite/skills/evolve-lite/provenance

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add AgentToolkit/altk-evolve --skill provenance -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install AgentToolkit/altk-evolve provenance --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/AgentToolkit/altk-evolve.git skills-src && mkdir -p .agents/skills && cp -r skills-src/platform-integrations/codex/plugins/evolve-lite/skills/evolve-lite/provenance .agents/skills/provenance && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "provenance" agent skill from https://github.com/AgentToolkit/altk-evolve/tree/main/platform-integrations/codex/plugins/evolve-lite/skills/evolve-lite/provenance into .agents/skills/provenance/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "provenance", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add AgentToolkit/altk-evolve --skill provenance -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install AgentToolkit/altk-evolve provenance --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/AgentToolkit/altk-evolve.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/platform-integrations/codex/plugins/evolve-lite/skills/evolve-lite/provenance .cursor/skills/provenance && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "provenance" agent skill from https://github.com/AgentToolkit/altk-evolve/tree/main/platform-integrations/codex/plugins/evolve-lite/skills/evolve-lite/provenance into .cursor/skills/provenance/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "provenance", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/AgentToolkit/altk-evolve.git --path platform-integrations/codex/plugins/evolve-lite/skills/evolve-lite/provenance

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add AgentToolkit/altk-evolve --skill provenance -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install AgentToolkit/altk-evolve provenance --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/AgentToolkit/altk-evolve.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/platform-integrations/codex/plugins/evolve-lite/skills/evolve-lite/provenance .gemini/skills/provenance && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "provenance" agent skill from https://github.com/AgentToolkit/altk-evolve/tree/main/platform-integrations/codex/plugins/evolve-lite/skills/evolve-lite/provenance into .gemini/skills/provenance/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "provenance", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install AgentToolkit/altk-evolve provenance

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add AgentToolkit/altk-evolve --skill provenance -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/AgentToolkit/altk-evolve.git skills-src && mkdir -p .github/skills && cp -r skills-src/platform-integrations/codex/plugins/evolve-lite/skills/evolve-lite/provenance .github/skills/provenance && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "provenance" agent skill from https://github.com/AgentToolkit/altk-evolve/tree/main/platform-integrations/codex/plugins/evolve-lite/skills/evolve-lite/provenance into .github/skills/provenance/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "provenance", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add AgentToolkit/altk-evolve --skill provenance -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install AgentToolkit/altk-evolve provenance --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/AgentToolkit/altk-evolve.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/platform-integrations/codex/plugins/evolve-lite/skills/evolve-lite/provenance .opencode/skills/provenance && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "provenance" agent skill from https://github.com/AgentToolkit/altk-evolve/tree/main/platform-integrations/codex/plugins/evolve-lite/skills/evolve-lite/provenance into .opencode/skills/provenance/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "provenance", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: provenance
GitHub stars: 122
Token cost: ~1.1k tokens
SKILL.md length: 431 words
Files: 3 (incl. scripts)
Skills in repo: 21
Repo updated: Oct 7, 2026
First seen: Oct 7, 2026
Licence: Apache-2.0

At a glance

Analyze saved trajectories and recall audit events offline to record whether recalled guidelines influenced completed sessions.

Works in 3 steps: Get candidates → Judge each candidate → Record verdicts
Agent Workflows work in your project
SKILL.md covers Overview and Workflow
Runs Python scripts from its folder; calls python3 and git

What it does

Provenance is an agent skill from AgentToolkit/altk-evolve. Analyze saved trajectories and recall audit events offline to record whether recalled guidelines influenced completed sessions.

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including scripts (for example `scripts/log_influence.py` and `scripts/provenance.py`).

It sits in Agent Workflows. The repository describes itself as: Self improving agents through iterations. The licence is Apache-2.0.

When your agent uses it

Agent Workflows work in your project

Example prompts

“/provenance”

Requirements

Python 3

Workflow steps

3 steps, taken from the step headings in SKILL.md.

Get candidates
Judge each candidate
Record verdicts

What it can do on your machine

Read from SKILL.md and the folder at commit 9e5bb56. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 2 files in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
- python3
- git
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Provenance loads about 1.1k tokens when it runs. Until then it costs about 35 tokens; SKILL.md has 431 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~35
When it runs · the whole SKILL.md, loaded when a task matches: ~1.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from AgentToolkit/altk-evolve at commit 9e5bb56, republished under its Apache-2.0 licence (© AgentToolkit). 431 words, ~1,104 tokens.

Download SKILL.mdSave it as .claude/skills/provenance/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.

name: provenance
description: Analyze saved trajectories and recall audit events offline to record whether recalled guidelines influenced completed sessions.

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, 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 "$(git rev-parse --show-toplevel 2>/dev/null || pwd)/plugins/evolve-lite/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>",
  "trajectory_path": "/path/to/transcript.jsonl",
  "trajectory_excerpt": "<head of the trajectory transcript>",
  "missing": ["trajectory"]
}

Notes:

entity_id is the path relative to .evolve/entities/ without the .md suffix, e.g. feedback/foo, guideline/bar, or subscribed/alice/guideline/baz.
Pairs that already have an influence row are skipped for you — the builder reuses the same dedup rule used when influence rows are written. You will never be handed a duplicate.
The trajectory locator checks .evolve/trajectories/ first, then falls back to the native Claude transcript at ~/.claude/projects/<slug>/<session-id>.jsonl. This means provenance works even when no .evolve/trajectories/ file was written.
If an entity file or trajectory cannot be found, the candidate is still emitted with a missing: [...] field so the gap is visible. When the trajectory is missing you usually cannot judge the pair — skip it (do not guess), unless the entity content alone makes not_applicable certain.

Show full SKILL.md (186 more words)Show less

Step 2: Judge each candidate

For each candidate, read entity_excerpt (and open trajectory_path for the full transcript if the excerpt is not enough). Compare the recalled guideline against the agent's actual actions in the trajectory and pick exactly one verdict:

followed — the agent's actual actions are consistent with the guideline.
contradicted — the guideline applied, but the agent did the opposite or repeated the avoidable dead end.
not_applicable — the guideline was recalled but did not apply to this session.

Keep evidence to one short sentence citing a concrete action, tool call, or absence in the trajectory. This judgment is yours — there is no heuristic fallback.

Step 3: Record verdicts

Persist each verdict. Either pipe one verdict per call to provenance.py record:

bash

echo '{
  "session_id": "<session-id>",
  "entity": "<type>/<name>",
  "verdict": "followed",
  "evidence": "Agent used the saved parser before trying shell fallbacks."
}' | python3 "$(git rev-parse --show-toplevel 2>/dev/null || pwd)/plugins/evolve-lite/skills/evolve-lite/provenance/scripts/provenance.py" record

…or, to batch many assessments for one session in a single call, pipe to the underlying writer directly:

bash

echo '{
  "session_id": "<session-id>",
  "assessments": [
    {"entity": "feedback/foo", "verdict": "followed", "evidence": "Agent followed it."},
    {"entity": "guideline/bar", "verdict": "not_applicable", "evidence": "Did not apply."}
  ]
}' | python3 "$(git rev-parse --show-toplevel 2>/dev/null || pwd)/plugins/evolve-lite/skills/evolve-lite/provenance/scripts/log_influence.py"

Both paths write the identical influence audit row and skip duplicates. The entity value must match the candidate's entity_id exactly, including any subscribed/<source>/ prefix.

It is valid to record nothing when recall events exist but no recalled guideline can be assessed (e.g. every candidate is missing its trajectory).

Files

SKILL.md and 2 other files (scripts) in platform-integrations/codex/plugins/evolve-lite/skills/evolve-lite/provenance of AgentToolkit/altk-evolve.

SKILL.md
scripts/log_influence.py
scripts/provenance.py

Open the folder on GitHubat commit 9e5bb56

Compare with similar skills

Provenance next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Provenance compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Provenance this skillAgentToolkit/altk-evolve	122	—	~1.1k	Automated safety check: Pass	Apache-2.0	today
MCP Server Builderanthropics/skills	180k	62 repos	~2.3k	Automated safety check: Pass	Apache-2.0	2 days ago
Hook Development for Claude Code Pluginsanthropics/claude-plugins-official	37k	11 repos	~4.1k	Automated safety check: Notes	Apache-2.0	today
Using Superpowersfarm-fe/farm	5.6k	34 repos	~1.4k	Automated safety check: Pass	MIT	15 days ago
Executing Plans Inlineobra/superpowers	296k	2 repos	~5.1k	Automated safety check: Pass	MIT	today
Claude Code Agent Developmentanthropics/claude-plugins-official	37k	8 repos	~2.8k	Automated safety check: Pass	Apache-2.0	today

Similar skills

MCP Server Builder
anthropics/skills
Official
Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.
180k GitHub starsUsed in 62 repos~2.3k tokens
Agent WorkflowsAuto-check passed
Hook Development for Claude Code Plugins
anthropics/claude-plugins-official
Official
Explains how to write Claude Code plugin hooks, both prompt-based checks and bash commands, for events such as PreToolUse, Stop and SessionStart.
37k GitHub starsUsed in 11 repos~4.1k tokens
Agent WorkflowsAuto-check: notes
Using Superpowers
farm-fe/farm
A skill your agent uses when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
5.6k GitHub starsUsed in 34 repos~1.4k tokens
Agent WorkflowsAuto-check passed
Executing Plans Inline
obra/superpowers
Has the agent carry out an implementation plan itself, task by task in the current session, keeping a ledger, proving each step with a test and ending with one whole-branch review.
296k GitHub starsUsed in 2 repos~5.1k tokens
Agent WorkflowsAuto-check passed
Claude Code Agent Development
anthropics/claude-plugins-official
Official
Explains how to write agents for Claude Code plugins: the markdown file with YAML frontmatter, trigger descriptions, model and color settings, and system prompt design.
37k GitHub starsUsed in 8 repos~2.8k tokens
Agent WorkflowsAuto-check passed
Skill Creator
Azure/azqr
Official
Create new skills, modify and improve existing skills, and measure skill performance.
794 GitHub starsUsed in 89 repos~8.2k tokens
Agent WorkflowsAuto-check passed

Questions about Provenance

What does Provenance do?

Analyze saved trajectories and recall audit events offline to record whether recalled guidelines influenced completed sessions. Provenance is an agent skill from AgentToolkit/altk-evolve. Analyze saved trajectories and recall audit events offline to record whether recalled guidelines influenced completed sessions.

When should I use Provenance?

Provenance fits situations like: agent Workflows work in your project.

How do I install Provenance in Claude Code?

Run `npx skills add AgentToolkit/altk-evolve --skill provenance -a claude-code`. Or copy the skill folder (platform-integrations/codex/plugins/evolve-lite/skills/evolve-lite/provenance in AgentToolkit/altk-evolve) into .claude/skills/provenance in your project. Claude Code loads it when a task matches its description.

How do I install Provenance in Codex?

Run `npx skills add AgentToolkit/altk-evolve --skill provenance -a codex`. Or copy the skill folder (platform-integrations/codex/plugins/evolve-lite/skills/evolve-lite/provenance in AgentToolkit/altk-evolve) into .agents/skills/provenance in your project. Codex loads it when a task matches its description.

Can I use Provenance in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add AgentToolkit/altk-evolve --skill provenance -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/provenance, .gemini/skills/provenance, .github/skills/provenance and .opencode/skills/provenance in your project.

What does Provenance need to run?

Going by SKILL.md and its folder, Provenance needs Python for the scripts in its folder and the command-line tools its instructions call (python3 and git). Our summary lists: Python 3.

Does Provenance access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Provenance safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Provenance use?

Provenance is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Provenance use?

About 1.1k tokens (SKILL.md is roughly 4.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Provenance?

Skills that share tags, products or a category with Provenance: MCP Server Builder (anthropics/skills, 180k stars), Hook Development for Claude Code Plugins (anthropics/claude-plugins-official, 37k stars), Using Superpowers (farm-fe/farm, 5.6k stars) and Executing Plans Inline (obra/superpowers, 296k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Provenance?

AgentToolkit (a GitHub organization) maintains it in AgentToolkit/altk-evolve, which has 122 GitHub stars. The repository holds 21 skills in this directory. The repository was last updated on October 7, 2026.

Source: AgentToolkit/altk-evolve on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Provenance

Install Provenance

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Provenance Analyzer

Overview

Workflow

Step 1: Get candidates

Step 2: Judge each candidate

Step 3: Record verdicts

Files

Compare with similar skills

Similar skills

MCP Server Builder

Hook Development for Claude Code Plugins

Using Superpowers

Executing Plans Inline

Claude Code Agent Development

Skill Creator

More from AgentToolkit/altk-evolve

Agent Wiki Compare Outcomes

Trajectory Skill Synthesizer

Evolve Memory Mirror

Agent Wiki Consult

Agent Wiki Guideline Extractor

Agent Wiki Ingest

Questions about Provenance

Install Provenance

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Provenance Analyzer

Overview

Workflow

Step 1: Get candidates

Step 2: Judge each candidate

Step 3: Record verdicts

Files

Compare with similar skills

Similar skills

More from AgentToolkit/altk-evolve

Related

Questions about Provenance