docent-pr

docent-pr is a skill for Claude Code, Codex from benelser/docent. It costs 60 tokens per session (1,581 once invoked), scanned A, original, MIT.

A tool that turns a pull-request review into a narrated video. A pull request is a proposed code change submitted for review before it is merged into a project.

In plain words
What is it for?
Use it to review why a change exists, compare the code before and after, trace effects elsewhere in the repository, identify possible breakage, and give a verdict.
Why use it?
It explains the important parts of a change and its risks in a format that can be easier to follow than a long written review.

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/benelser/docent/docent-pr
Any agent
npx skills add benelser/docent --skill docent-pr
Clone the repo
git clone --depth 1 https://github.com/benelser/docent

Made for: Claude Code, Codex.

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 docent-pr

README.md
[![agentmods](https://agentmods.dev/badge/skills/benelser/docent/docent-pr.svg)](https://agentmods.dev/skills/benelser/docent/docent-pr)
Your own site
<a href="https://agentmods.dev/skills/benelser/docent/docent-pr"><img src="https://agentmods.dev/badge/skills/benelser/docent/docent-pr.svg" alt="Measured on agentmods" height="20"></a>
Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,581 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.

ModelPer sessionOnce invoked
Fable 5 $0.00060 $0.01581
Opus 5 $0.00030 $0.00790
Sonnet 5 $0.00012 $0.00316
Haiku 4.5 $0.00006 $0.00158

Measured 4d ago against content hash 57a178e74b35, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

docent-pr 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 4d 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.

packages/agent/skills/docent-pr/SKILL.md · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.

docent-pr — the PR-review film

You are running the entire docent cascade in PR-review mode against a pull request the user named: survey → treatment → spec → tts → clips → render → open. The output is one MP4 that explains the change the way a principal engineer would: why it exists, whether the design is sound, the core before → after, what ripples, what could break, and a verdict.

Arguments

/docent-pr <repo> <pr-number> [--id X] [--scale S] [--no-open]

  • <repo> — a repo path, a GitHub URL (https://github.com/owner/name), or the bare owner/name form.
  • <pr-number> — the pull-request number to review. Can be 123 or #123. If the user pasted a full PR URL as <repo>, extract both.
  • --id X — override the auto-derived film id (default: <repo-name>-pr).
  • --scale S — render scale. Default 1. Pass 0.5 for fast turnarounds.
  • --no-open — render without opening the result in the system player.

What to do

  1. Pre-flight. Confirm bun, ffmpeg, and the agent CLI (claude or codex) are on PATH. If anything obvious is missing, suggest /docent-doctor and stop.

  2. Survey — PR mode:

    docent survey <repo> --mode pr --pr <n> [--id X]
    

    The survey lands at analysis/<id>.md. Surface the path and the load-bearing finding (section 1 of the survey — the triage) before moving on. A PR survey's job is triage: of the diff, what is the load-bearing 5% — that you review with depth — and what is the rest you explicitly deprioritized.

  3. Commit to a style. Before the treatment, decide the visual register the film renders in:

    bun run docent style recommend <id>
    

    For PR films the recommender will almost always return engineering — code-heavy, the dark console look. Take the recommendation unless the survey surfaces something exceptional (an exec-level retrospective of a release-blocking PR, for instance, may want executive). Surface the choice to the user in one line — "rendering in engineering — the load-bearing 5% is in pkg/scheduler/...; rationale: file-level code review." — and move on. The spec compilation reads this off the survey's "Style commitment" section and pins it as the spec's style: {preset, intent, rationale} field. The depth-review judge fails the style-committed dimension if the spec ships without it.

Read the full file on GitHub · 143 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. 4d ago First seen · 143 lines · 60 tokens per session scan A 57a178e74b35

Subscribe to this mod's changes

docent-pr is a skill published in the GitHub repository benelser/docent (6 stars, last pushed 2mo ago), licensed MIT. It adds 60 tokens to every session and 1,581 once invoked, about $0.0003 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 2026-08-31.

Related

Other skills, from other repositories

remocn

Build Remotion videos with remocn — copy-paste animation components and timeline-driven UI primitives from a shadcn registry. Use when composing a video or scene in a Remotion project, adding a single animation, transition, background, or UI-block sim, or reaching for a video-ready UI primitive (button, dialog…

Remocn/remocn · 88 tokens

clean-cut

Step 1 of the AI Video Editor pipeline — turn raw talking-head footage into a clean master cut. Use when the user wants to "clean cut", "cut the raw footage", "remove filler / dead air / bad takes", "tighten the pacing", produce cuts.json, run the cut editor, or render a cleaned preview/master for a video-N project in…

hassancs91/claude-youtube-editor · 189 tokens

migrate-state-management

Migrate Redux or React Context to the correct state option (React Query for server state, nuqs for URL/shareable state, Zustand for global client state). Use when refactoring away from Redux/Context, moving state to the right store, or when the user asks to migrate state management.

SigNoz/signoz · 64 tokens

suggest-sfx

Step 4 of the AI Video Editor pipeline — the SFX pass. Analyze a video's beats + narration and propose tasteful sound effects synced to them, drawing from (and growing) a shared, reusable SFX library, then render an SFX-mixed audition preview. Use when the user wants to "add SFX / sound effects", "suggest sfx", "score…

hassancs91/claude-youtube-editor · 206 tokens

vidtsx-2d-generator

Generate production-ready 2D TSX video files for VidTSX (Remotion-based) from a shot, scene, or video description. Use whenever the user wants to create or generate a VidTSX video, a 2D TSX shot or scene, an animated clip, title card, or rendered motion graphic — including when they describe a visual animation they…

hassancs91/claude-youtube-editor · 225 tokens

brand-setup

Makes this repo's videos look like YOUR channel instead of the house default — interviews you for palette, fonts, wordmark, motion energy, delivery specs and SFX taste, then rewrites brand.md + remotion/src/brand.ts + remotion/src/fonts.ts together and renders a proof card so you SEE it. Use whenever the user wants to…

hassancs91/claude-youtube-editor · 159 tokens