docs-pr-reviewer

A command for letting a non-developer edit an already-open documentation pull request, which is a proposed set of code changes, without installing development tools.

In plain words
What is it for?
Use it when a subject-matter expert wants to change text in an existing Sumo Logic documentation pull request and check the result on its staging site.
Why use it?
It removes the need to learn Git or set up the documentation project just to make a requested edit.

Command for Claude Code

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/sumologic/sumologic-documentation/docs-pr-reviewer
Clone the repo
git clone --depth 1 https://github.com/SumoLogic/sumologic-documentation

Made for: Claude Code.

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 3,923 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 $0.00000 $0.03923
Opus 5 $0.00000 $0.01962
Sonnet 5 $0.00000 $0.00785
Haiku 4.5 $0.00000 $0.00392

Measured 2d ago against content hash 04b7940264b2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

docs-pr-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 2d 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/docs-pr-reviewer.md · 261 lines

How it starts

The opening of the file, as written. The whole thing — 261 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Docs PR Reviewer — Apply an SME's Edit to an Existing PR

Lets a PM, engineer, or other Sumo Logic stakeholder (an SME) apply their own requested change directly to an already-open sumologic-documentation PR, without git experience and without a local dev environment. Claude does the git and build work; the SME just says what to change and looks at a quick screenshot to confirm it.

This is not a preview tool and not an approval tool. Docs PRs at Sumo Logic are opened on a review/**-named branch, which already triggers a live staging deploy (.github/workflows/workflow_deploy-to-pantheon-review.yml) the moment the PR is opened — the tech writer shares that staging link directly, and the SME clicks around it in their own browser. None of that involves Claude Code. Likewise, if the SME has no changes, they approve directly on the PR page — also nothing to do with Claude Code. This command exists for exactly one case: the SME wants to make the edit themselves instead of leaving a comment for the tech writer to apply. Once pushed, the commit lands on the same review/** branch, which automatically redeploys the same staging site the SME was already looking at.

This command assumes you're running in a Claude Code cloud/remote session — that's the point of it. This is about the environment, not which interface you're typing into: desktop's cloud mode, Claude Code on the web, and Claude Code CLI pointed at a remote/cloud environment all qualify equally, since the CLI is just as capable of running against a remote container as it is against a local machine. The container already has Git, Node, Yarn, and a headless Chromium preinstalled, and it authenticates to GitHub as the reviewer's own connected account, so there's no SSH key, Homebrew, or Node/Yarn setup to walk anyone through. If you're ever running this in a session pointed at the reviewer's own local machine instead (Desktop or CLI, it doesn't matter which), the same steps still work against whatever clone is already on disk — you just can't assume a fresh, pre-provisioned container.

Read the full file on GitHub · 261 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. 2d ago First seen · 261 lines · 0 tokens per session scan A 04b7940264b2

Subscribe to this mod's changes

docs-pr-reviewer is a command published in the GitHub repository SumoLogic/sumologic-documentation (42 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,923 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 2026-08-30.