A command tool for recording and checking the web sources behind tracked files. It stores each source URL with a status such as consulted, accepted, rejected, or stale.

Use it to view, add, verify, list, or initialize provenance records for files.

It makes the origin of file content visible and helps find source links that no longer work.

provenance — Command for Claude Code by cdeust: A command tool for recording and checking the web…

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 commands/cdeust/ai-architect-mcp-codebase/provenance

Clone the repo

git clone --depth 1 https://github.com/cdeust/ai-architect-mcp-codebase

Made for: Claude Code.

Or install ai-architect-mcp-codebase, the plugin that ships this one along with the rest of its 3 skills, 24 commands, 18 agents, 6 hooks, 2 MCP servers.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/commands/cdeust/ai-architect-mcp-codebase/provenance.svg)](https://agentmods.dev/commands/cdeust/ai-architect-mcp-codebase/provenance)

Your own site

<a href="https://agentmods.dev/commands/cdeust/ai-architect-mcp-codebase/provenance"><img src="https://agentmods.dev/badge/commands/cdeust/ai-architect-mcp-codebase/provenance.svg" alt="Measured on agentmods" height="20"></a>

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 406 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found 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.

Model	Per session	Once invoked
Fable 5	$0.00000	$0.00406
Opus 5	$0.00000	$0.00203
Sonnet 5	$0.00000	$0.00081
Haiku 4.5	$0.00000	$0.00041

Measured 3d ago against content hash 504f34f9f11c, 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 3d ago.

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.

.claude/commands/zetetic/provenance.md · 31 lines

What it actually says

Provenance

View, add, or verify provenance records for source-tracked files.

Instructions

Parse $ARGUMENTS for the subcommand:
- provenance show <file> — display the provenance sidecar for a file
- provenance add <file> <url> <status> — add a source record (status: consulted, accepted, rejected, stale)
- provenance verify <file> — check all URLs in provenance are reachable
- provenance list — show all provenance files in the repo
- provenance init <file> — create a new provenance sidecar
Show: Run tools/provenance-manager.sh show <file>. Display the provenance table. If no provenance file exists, suggest running provenance init <file> first.
Add: Validate that <url> looks like a URL (starts with http:// or https://). Validate <status> is one of: consulted, accepted, rejected, stale. Run tools/provenance-manager.sh add <file> <url> <status>. Confirm what was added.
Verify: Run tools/provenance-manager.sh verify <file>. Report results clearly:
- All reachable: confirm clean provenance
- Any stale: list the stale URLs and suggest updating or replacing them
List: Run tools/provenance-manager.sh list. Format as a readable summary showing file count and total sources.
Init: Run tools/provenance-manager.sh init <file>. Confirm creation and remind user to add sources with provenance add.
If no subcommand given, run provenance list as default.
The zetetic standard requires multiple independent sources. If a file has fewer than 2 accepted sources, note this as a gap.

$ARGUMENTS

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.

3d ago First seen · 31 lines · 0 tokens per session scan A 504f34f9f11c

Subscribe to this mod's changes

provenance is a command published in the GitHub repository cdeust/ai-architect-mcp-codebase (4 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 406 tokens. 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 2026-08-31.

Research bm25 claude-code claude-code-plugin clean-architecture code-graph code-intelligence

provenance

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

Provenance

Instructions

What this file has done since we first saw it

Other commands, from other repositories

brooks-audit

brooks-health

daily-standup

fix-issue

simplify

index