pr

pr is a skill for Claude Code, Codex from Reikor-Arg/inmemory. It costs 61 tokens per session (840 once invoked), scanned A, original, MIT.

A set of instructions for reviewing, preparing, or monitoring a pull request (PR), which is a proposed code change awaiting review and merge. It compares the change with the project's existing decisions and checks.

In plain words
What is it for?
Use it to review a PR, prepare one, investigate failing continuous-integration checks, or wait for review comments and merge status.
Why use it?
It helps find broken callers, error-path problems, unrelated changes, failed checks, and changes that quietly undo earlier decisions.

Skill for Claude CodeCodex

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the inmemory plugin — 4 skills, 12 commands, 5 hooks shipped together

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/reikor-arg/inmemory/pr
Any agent
npx skills add Reikor-Arg/inmemory --skill pr
Clone the repo
git clone --depth 1 https://github.com/Reikor-Arg/inmemory

Made for: Claude Code, Codex.

Or install inmemory, the plugin that ships this one along with the rest of its 4 skills, 12 commands, 5 hooks.

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 pr

README.md
[![agentmods](https://agentmods.dev/badge/skills/reikor-arg/inmemory/pr.svg)](https://agentmods.dev/skills/reikor-arg/inmemory/pr)
Your own site
<a href="https://agentmods.dev/skills/reikor-arg/inmemory/pr"><img src="https://agentmods.dev/badge/skills/reikor-arg/inmemory/pr.svg" alt="Measured on agentmods" height="20"></a>
Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 840 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 $0.00061 $0.00840
Opus 5 $0.00030 $0.00420
Sonnet 5 $0.00012 $0.00168
Haiku 4.5 $0.00006 $0.00084

Measured 4d ago against content hash 57a737e43708, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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.

skills/pr/SKILL.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pull requests

Reviewing

Read the diff, then read enough of the surrounding files to know what the diff changes. A review based only on the patch catches typos and misses the two things that actually matter: whether the change is correct in context, and whether it contradicts something already settled.

gh pr diff <n>                                                # the change
gh pr view <n> --json title,body,files,reviews,statusCheckRollup
node ${CLAUDE_PLUGIN_ROOT}/hooks/recall.mjs decide --list      # what was already settled
node ${CLAUDE_PLUGIN_ROOT}/hooks/recall.mjs search <topic>     # how this was handled before

A PR that quietly reverses a recorded decision is the most expensive thing to miss, because it looks correct in isolation and only breaks the thing the decision was protecting.

What to look for, in order

  1. Does it do what the description says — and only that. Unrelated changes riding along are how regressions arrive unreviewed.
  2. Every caller of every changed signature. Grep them; do not assume the author did. This is where real breakage hides.
  3. The error paths. Happy path is usually right. What happens on timeout, empty input, a second concurrent call, a partial write?
  4. Data and migrations. Anything that drops, backfills, or reshapes stored data deserves its own scrutiny and a stated rollback.
  5. Secrets and input at trust boundaries. A key in a diff is a stop-everything finding, and it stays in the history after the fix.
  6. Tests that would fail if the change were wrong. A test that passes against both the old and new behaviour tests nothing.

How to write the review

Lead with whether it can merge. The author wants that answer first, not last.

Separate blocking from optional, explicitly. An unlabelled pile of comments makes the author guess, and they will guess wrong in whichever direction costs more.

Quote file and line. State the failure concretely: the input, and what goes wrong with it. "This could break" is not reviewable; "with items = [] this divides by zero on line 40" is.

Read the full file on GitHub · 83 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 · 83 lines · 61 tokens per session scan A 57a737e43708

Subscribe to this mod's changes

pr is a skill published in the GitHub repository Reikor-Arg/inmemory (1 stars, last pushed 1mo ago), licensed MIT. It adds 61 tokens to every session and 840 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

alive:demo

Generate a believable, lived-in ALIVE world from a free-text persona description (custom path) or a deterministic sandbox preset. Routes the create/list/activate/deactivate/delete/status surface and orchestrates the 5-stage subagent generation pipeline.

alivecontext/alive · 52 tokens

alive:save

The human wants to checkpoint. Or: the stash has grown heavy — 5+ items, 30+ minutes, a natural pause in the work. The squirrel doesn't decide when to save. It surfaces the need and lets the human pull the trigger. Runs the full save protocol: confirms stash, writes log, updates state, generates projections…

alivecontext/alive · 78 tokens

alive:system-upgrade

Upgrade ALIVE to the current version. Handles v1/v2/v3.x source states, multi-surface aware (alive-mcp / Hermes / Codex), retroactive version detection, partial-failure resume, dry-run previews, and rollback inspection.

alivecontext/alive · 57 tokens

alive:create-walnut

Something new is emerging. A venture, an experiment, a person entering the orbit, a life area getting serious. It needs its own walnut — its own identity, history, and future. Scaffolds the full structure, maps existing context sources, and optionally migrates files across.

alivecontext/alive · 63 tokens

alive:session-history

Revive sessions (quick or heavy), browse, and search — 'what happened recently?', 'find the session where we discussed X', 'revive yesterday's session'. For single-session recall and multi-session browsing. If the human needs to merge multiple sessions into one working context or detect conflicts between parallel…

alivecontext/alive · 76 tokens

alive:world

The human doesn't know what to work on, or wants to see everything at once. They need the big picture — what's active, what's stale, what needs attention. Renders a live world view grouped by ALIVE domain, then routes to open, tidy, find, history, or map.

alivecontext/alive · 63 tokens