davinci-resolve-mcp: Agent for Claude Code

.claude/agents/drift-guard-reviewer.md

drift-guard-reviewer is an agent for Claude Code from samuelgursky/davinci-resolve-mcp. It costs 80 tokens per session (953 once invoked), scanned A, original, MIT.

A code-consistency checker for a repository whose generated files and documentation must match their source files. It focuses on generated agent instructions, documented tool counts, and attribution data.

In plain words
What is it for?
Use it after changing agent instructions, documentation, tool registration, attribution code, or the control panel to run the repository's drift checks and report the results.
Why use it?
It catches stale generated files or documentation soon after a code change, instead of waiting for a release check to find them.

Agent for Claude Code

Written for Claude Code: PreToolUse hook event. Also seen: model in frontmatter; mentions AGENTS.md.

This is samuelgursky/davinci-resolve-mcp's own configuration. It tells Claude Code how to work on davinci-resolve-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything davinci-resolve-mcp configures →

About the project

davinci-resolve-mcp is an MCP server that lets AI assistants control DaVinci Resolve Studio through its scripting API, including editing, media organization, rendering, grading, and other project tasks. It is for users who want agents to operate Resolve and inspect media through a local control panel. The catalogue entries support agent workflows for this Resolve integration.

samuelgursky/davinci-resolve-mcp · 2,622 stars · on GitHub

Reuse

Borrowing it

Nothing to install: this file belongs to samuelgursky/davinci-resolve-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/samuelgursky/davinci-resolve-mcp/main/.claude/agents/drift-guard-reviewer.md
Clone the repo
git clone --depth 1 https://github.com/samuelgursky/davinci-resolve-mcp

Made for: Claude Code.

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.

agentmods badge for drift-guard-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/samuelgursky/davinci-resolve-mcp/drift-guard-reviewer/github.svg)](https://agentmods.dev/agents/samuelgursky/davinci-resolve-mcp/drift-guard-reviewer)
Your own site
<a href="https://agentmods.dev/agents/samuelgursky/davinci-resolve-mcp/drift-guard-reviewer"><img src="https://agentmods.dev/badge/agents/samuelgursky/davinci-resolve-mcp/drift-guard-reviewer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for drift-guard-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/samuelgursky/davinci-resolve-mcp/drift-guard-reviewer"><img src="https://agentmods.dev/badge/agents/samuelgursky/davinci-resolve-mcp/drift-guard-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 80 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 953 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00080 $0.00953
Opus 5 $0.00040 $0.00477
Sonnet 5 $0.00016 $0.00191
Haiku 4.5 $0.00008 $0.00095

Measured 12d ago against content hash adae33100878, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

drift-guard-reviewer 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 12d 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/agents/drift-guard-reviewer.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Drift Guard Reviewer

This repo enforces "docs and generated files must match their source" with a specific family of tests, not general code review. You run that family and report exactly what it finds — you do not review anything else.

Why this agent exists

.github/workflows/npm-publish.yml runs a subset of these checks before every publish, but only at publish time. By then the drift has usually existed for several commits. This agent runs the same checks on demand, right after a change that plausibly caused them, so the fix happens at the point of change instead of at release time — the same reasoning behind this repo's two PreToolUse guard hooks, just applied to doc/code consistency instead of Resolve safety.

The checks

Run these, in order, from the repo root. Use the project venv if venv/bin/python exists, otherwise python3.

  1. Generated agent-rule files (.cursor/rules, .windsurf/rules, .clinerules, .roo/rules, .continue/rules, .github/copilot-instructions.md, the AGENTS.md domain-routing block): node scripts/agent-rules/generate.mjs --check Fix with node scripts/agent-rules/generate.mjs (no --check).

  2. Drift-guard test family — each one is a single, targeted check:

    • tests/test_agent_rules_drift.py — same check as #1, via the suite
    • tests/test_action_list_drift.py — tool/action lists vs. dispatch
    • tests/test_attribution_drift.py — attribution text vs. its source
    • tests/test_destructive_registry_drift.py — destructive-action registry vs. decorator coverage
    • tests/test_free_edition_docs_drift.py — free-edition docs vs. capability gates
    • tests/test_panel_docs_drift.py — control panel guide vs. the panel's actual navigation and screenshots
    • tests/test_version_gate_drift.py — version-gated features vs. what's documented as gated

    Run with: python3 -m pytest tests/test_agent_rules_drift.py tests/test_action_list_drift.py tests/test_attribution_drift.py tests/test_destructive_registry_drift.py tests/test_free_edition_docs_drift.py tests/test_panel_docs_drift.py tests/test_version_gate_drift.py -q

Read the full file on GitHub · 74 lines

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. 12d ago First seen · 74 lines · 80 tokens per session scan A adae33100878

Subscribe to this mod's changes

drift-guard-reviewer is an agent published in the GitHub repository samuelgursky/davinci-resolve-mcp (2,622 stars, last pushed yesterday), licensed MIT. It adds 80 tokens to every session and 953 once invoked, about $0.0004 per session on Opus 5. 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 2026-08-30.

Related

Other agents, from other repositories

cpp-reviewer

Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.

affaan-m/ECC · 41 tokens

reviewer

Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…

genkovich/sdd · 81 tokens

atomic-auditor

Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…

damusix/atomic-claude · 169 tokens

bt6-pr-auditor

Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.

elder-plinius/T3MP3ST · 32 tokens

Reviewer

Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.

monkilabs/opencastle · 30 tokens

security-auditor

Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.

NeoLabHQ/context-engineering-kit · 40 tokens