What is guild-learn-diff?

A code-change analyser that shows which parts of a project are affected by a change between two Git commits. It also lists changed files that cannot be linked to a known part of the project.

Use it to assess the scope of a planned change and check whether every changed file is accounted for before verifying the work.

It helps reveal the likely impact of a change without relying on a raw list of changed lines. It requires an existing project knowledge graph to make those links.

guild-learn-diff — Skill by lookatitude

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/lookatitude/guild/learn-diff

Any agent

npx skills add lookatitude/guild --skill learn-diff

Clone the repo

git clone --depth 1 https://github.com/lookatitude/guild

Made for: Claude Code, Codex.

Per session 175 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,743 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	$0.00175	$0.01743
Opus 5	$0.00088	$0.00872
Sonnet 5	$0.00035	$0.00349
Haiku 4.5	$0.00017	$0.00174

Measured 2d ago against content hash 15bc1f7acd42, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

guild-learn-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 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.

skills/knowledge/learn-diff/SKILL.md · 126 lines

How it starts

The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.

When to use it

Use to produce the DiffUnderstanding artifact — a graph-grounded analysis of what a base→head change set affects. It maps each changed file onto the KnowledgeGraph nodes/layers it touches and surfaces untraced_files (changed files no node explains). It is consumed at P2 by guild:plan (plan-impact) and re-read at P3 by guild:verify-done (scope-check). Part of the lazy, gated deep tier — it requires a built graph.

When not to use it

Not for the cheap-scan map (guild:learn-map), building the graph (guild:learn-graph), narrating the tour (guild:learn-onboard), or explaining a single file/module (guild:learn-explain). Not for a bare git diff with no graph grounding — the value here is mapping the diff onto graph nodes/layers, not printing hunks.

Required inputs

.guild/indexes/knowledge-graph.json (guild.knowledge_graph.v1) from guild:learn-graph. If absent, escalate — DiffUnderstanding is graph-grounded and cannot be synthesised from raw files.
A base commit (merge-base with the integration branch) and optional head.
The active run-id (from .guild/runs/current-run-id).
Frozen contract: guild.diff_understanding.v1 (schema canonical in scripts/learn/lib/schema.ts; do not re-spell field names or version strings). Output-locations table is owned by guild:learn-map.

Output format

.guild/runs/<run-id>/diff-learn.json — guild.diff_understanding.v1: the changed-file set, the affected_layers / affected nodes per file, and untraced_files (changed files no graph node explains). Field names / version are canonical and frozen — conform by pointer, never copy the schema here.

Workflow steps

Assert the knowledge graph exists and is readable; escalate if not.
Run diff-learn.ts --cwd <root> --base <sha> [--head <sha>] [--run-id <id>] (under plugin/scripts/learn/) → the deterministic diff→node mapping.
LLM half (bounded, trust the script — do not re-read source): confirm the affected_layers reading and characterise the blast radius for the plan; flag untraced_files prominently — they are the scope-creep signal P3 acts on.
Write .guild/runs/<run-id>/diff-learn.json. Surface the path; do not consume it here — guild:plan (P2) and guild:verify-done (P3) own their consumption.

Read the full file on GitHub · 126 lines

Files

What ships with it

1 file 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.

evals.json 660 B

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.

2d ago First seen · 126 lines · 175 tokens per session scan A 15bc1f7acd42

Subscribe to this mod's changes

guild-learn-diff is a skill published in the GitHub repository lookatitude/guild (7 stars, last pushed 2d ago), licensed MIT. It adds 175 tokens to every session and 1,743 once invoked, about $0.0009 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.

Git and workflow Planning

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens