provenance

An offline review tool that checks whether saved guidelines influenced completed sessions using audit events and conversation records called trajectories.

In plain words
What is it for?
Use it after sessions finish to assess recalled guidelines and save those influence decisions.
Why use it?
It separates guideline-usage review from the live learning process and provides candidates for deciding whether each guideline was followed, contradicted, or irrelevant.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/agenttoolkit/altk-evolve/provenance
Any agent
npx skills add AgentToolkit/altk-evolve --skill provenance
Clone the repo
git clone --depth 1 https://github.com/AgentToolkit/altk-evolve

Made for: Claude Code, Codex.

Per session 21 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,024 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod in the catalogue.
Token cost

What 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.

ModelPer sessionOnce invoked
Fable 5 $0.00021 $0.01024
Opus 5 $0.00010 $0.00512
Sonnet 5 $0.00004 $0.00205
Haiku 4.5 $0.00002 $0.00102

Measured 2d ago against content hash 7ba74e4d155b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

provenance 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 2d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/log_influence.py, scripts/provenance.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Origin

This is a copy

100% identical to evolve-lite:provenance — 8 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

platform-integrations/claude/plugins/evolve-lite/skills/evolve-lite/provenance/SKILL.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

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:

python3 ${CLAUDE_PLUGIN_ROOT}/skills/evolve-lite/provenance/scripts/provenance.py candidates

Each candidate looks like:

{
  "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.

Read the full file on GitHub · 114 lines

Files

What ships with it

2 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.

Changes

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.

  1. 2d ago First seen · 114 lines · 21 tokens per session scan A 7ba74e4d155b

Subscribe to this mod's changes

provenance is a skill published in the GitHub repository AgentToolkit/altk-evolve (105 stars, last pushed 7d ago), licensed Apache-2.0. It adds 21 tokens to every session and 1,024 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to evolve-lite:provenance, differing in 8 lines, and is treated as a copy.

Related

Other skills, from other repositories

agent-recall

Persistent compounding memory for AI agents. 5 default MCP tools: sessionstart, sessionend, remember, recall, check. Full surface (18 tools) available with --full flag. Two-verb model: inhale (sessionstart) and exhale (sessionend). Correction-first memory with decision trail tracking, watchfor warnings, palace rooms…

Goldentrii/AgentRecall-X · 157 tokens

kungfu-agent-onboarding

Discover the exact Kungfu Project, WorkConsole, WorkRef, Skill catalog, and Core Work state admitted to this Amp process.

kungfu-systems/kungfu · 32 tokens

Context Doctor

Identify and repair degradation in system prompt, external memory, and skills preventing you from following instructions or remembering information as well as you should.

letta-ai/letta-code · 30 tokens

generating-mod-envs

Generates and reviews mod learning env JSON files for Letta Code local mods. Use when asked to teach, learn, or optimize a mod behavior; create, draft, validate, improve, or explain envs for /mods learn --env; or design evaluation scenarios, memory fixtures, requiredResultMarkers, requiredTraceMarkers, negative…

letta-ai/letta-code · 79 tokens

letta-guide

Read the official Letta documentation (docs.letta.com) through its cached, ETag-checked fetch route. Load before ANY docs.letta.com retrieval — answering how Letta works, what Letta (or you) can do, setting up providers, models, channels, skills, memory, schedules, permissions, self-hosting, pricing, or billing, AND…

letta-ai/letta-code · 130 tokens

adding-models

Guide for adding new LLM models to Letta Code. Use when the user wants to add support for a new model, needs to know valid model handles, or wants to update model-specific compatibility behavior. Covers runtime catalog sources, CI test matrices, and handle validation.

letta-ai/letta-code · 58 tokens