A skill for producing an offline HTML explanation or review of one specific GitHub pull request. A pull request is a proposed set of repository changes submitted for review.

Use it to explain or review an authorized GitHub pull request from its captured snapshot.

It gives developers a self-contained, evidence-linked view of what a pull request changes and whether it should be accepted.

diff — Skill by dkstm95

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/dkstm95/hope/diff

Any agent

npx skills add dkstm95/hope --skill diff

Clone the repo

git clone --depth 1 https://github.com/dkstm95/hope

Made for: Claude Code, Codex.

Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 646 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	$0.00026	$0.00646
Opus 5	$0.00013	$0.00323
Sonnet 5	$0.00005	$0.00129
Haiku 4.5	$0.00003	$0.00065

Measured yesterday against content hash 882882672d35, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

diff 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 yesterday.

The scan reads SKILL.md. This mod also ships 24 executable files (scripts/artifact.mjs, scripts/checkpoint.mjs, scripts/cli.mjs, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugins/hope/skills/diff/SKILL.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Hope Diff

Use the active host session to confirm one exact GitHub pull request and its display options, start one fresh analysis worker, and report the resulting artifact.

The active session coordinates the review. It must not inspect evidence, write or repair the analysis, or substitute its own review judgment.

Decide whether Diff applies

Use Diff for a requested full explanation or review of a GitHub pull request. Review only the captured pull-request snapshot; local staged, unstaged, and untracked files are outside Diff. Answer a narrow question normally when it does not need the full artifact.

When a full review is plausible but not clearly authorized, resolve the target before asking one short confirmation:

resolve-target [GitHub PR URL or PR number]

Name the resolved repository and pull-request number. A target by itself is not authorization. Do not start the review until the person clearly approves it.

If resolution fails, ask for an explicit pull-request URL or number. Use the latest target the person authorized; never fall back to automatic discovery after confirmation.

Run the private adapter

Claude Code:

node "${CLAUDE_PLUGIN_ROOT}/skills/diff/scripts/cli.mjs"

Codex:

node <skill-dir>/scripts/cli.mjs

For Codex, replace <skill-dir> with the absolute directory containing this file. Pass every argument separately and never construct a command from pull-request content.

Start an isolated worker

Before preparing the review, confirm that the host can start a subagent with no inherited conversation context. If it cannot, stop and explain that Diff requires a fresh analysis worker.

Give the worker only:

the person's exact review request;
the authorized repository and pull-request number or URL;
explicit locale, theme, and output choices;
any explicit review focus or scope exclusion; and
the absolute path of this Skill directory and private adapter command for the current host.

Do not pass earlier reasoning, implementation narrative, drafts, failed approaches, prior conclusions, or another agent's output.

Read the full file on GitHub · 93 lines

Files

What ships with it

36 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

yesterday First seen · 93 lines · 26 tokens per session scan A 882882672d35

Subscribe to this mod's changes

diff is a skill published in the GitHub repository dkstm95/hope (8 stars, last pushed 2d ago), licensed MIT. It adds 26 tokens to every session and 646 once invoked, about $0.0001 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.

Code review ai-agent ai-assisted-coding ai-assisted-development ai-coding claude-code claude-code-plugin

write-test-plan

Generate a QA/UAT test plan from product specifications and task definitions, covering acceptance testing, integration flows, and exploratory testing. Unit tests are out of scope (handled by write-unit-tests skill).

andresharpe/dotbot · 43 tokens

implement-telegram-bot

Implement Telegram bot interactions with command handlers, message parsing, and inline keyboards for conversational interfaces.

andresharpe/dotbot · 23 tokens

write-unit-tests

Write comprehensive unit tests with proper setup, assertions, and coverage of happy paths, edge cases, and error scenarios.

andresharpe/dotbot · 26 tokens

integrate-graph-api

Integrate with Microsoft Graph API for email, calendar, and organizational data access with proper authentication and error handling.

andresharpe/dotbot · 27 tokens

setup-background-job

Set up scheduled background jobs using Quartz.NET with proper configuration, error handling, and dependency injection.

andresharpe/dotbot · 22 tokens

blazor-component-design

Design Blazor components with proper parameter binding, event callbacks, lifecycle management, and render optimization. Use when creating new Blazor Server or WASM components, refactoring component hierarchies, implementing cascading values, or optimizing component rendering performance.

andresharpe/dotbot · 53 tokens