A guide for reading Git diffs, which are records of changes to files, and explaining them in plain language. It separates additions, removals, behavior changes, risks, and needed tests.

Use it to explain patches and pull requests, assess risks, distinguish mechanical edits from functional changes, and identify tests that should be run.

It makes code-review changes easier to understand and highlights removed validation, security checks, error handling, or tests.

diff-reader — Skill for Codex by Firou91/dyslex.ai

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.

Any agent

npx skills add Firou91/dyslex.ai --skill diff-reader

Clone the repo

git clone --depth 1 https://github.com/Firou91/dyslex.ai

Made for: 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/firou91/dyslex.ai/diff-reader/github.svg)](https://agentmods.dev/skills/firou91/dyslex.ai/diff-reader)

Your own site

<a href="https://agentmods.dev/skills/firou91/dyslex.ai/diff-reader"><img src="https://agentmods.dev/badge/skills/firou91/dyslex.ai/diff-reader/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/firou91/dyslex.ai/diff-reader"><img src="https://agentmods.dev/badge/skills/firou91/dyslex.ai/diff-reader.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 473 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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 5.1	$0.00039	$0.00473
Opus 5.5	$0.00016	$0.00189
Sonnet 5.5	$0.00008	$0.00095
Haiku 4.5	$0.00004	$0.00047

Measured 2mo ago against content hash ca5b615a57e9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

diff-reader 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 2mo 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/diff-reader/SKILL.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Diff Reader

Superpowers Gate

Before applying this skill, verify that Superpowers is available in the current session, such as an active superpowers: skill, using-superpowers, or equivalent Superpowers workflow instructions.

If Superpowers is missing or uncertain, stop and reply exactly with this guidance before doing any dyslex.ai work:

dyslex.ai requires Superpowers before it can run. Install Superpowers from /plugins, or use codex plugin add superpowers@<marketplace> if you manage plugins from the Codex CLI, then start a new session.

Do not perform the requested dyslex.ai workflow until Superpowers is installed and loaded.

Read the diff as evidence. Do not assume behavior not shown or implied by surrounding code.

Functional Mechanism

Primary dimensions: reading.visualScanningLoad, workingMemory.contextRetentionLoad, executiveFunction.inhibitionOrDistractionLoad, and writing.technicalTokenRisk.

Diff reading is a high-precision task where additions, deletions, identifiers, and risk signals must remain visually and logically distinct.

Interaction Risk

The user may miss a deletion, confuse mechanical changes with behavior changes, or overlook removed validation, security, tests, or error handling.

Agent Strategy

Separate added, removed, functional change, risks, and tests.
Preserve exact file paths and identifiers.
Treat the diff as evidence, not as proof of unshown behavior.
Call out high-risk removals explicitly.

Avoid

Do not infer a diagnosis from diff-reading difficulty.
Do not summarize away deleted safeguards.
Do not silently correct identifiers from the diff.
Do not claim behavior that cannot be verified from the diff or surrounding code.

Output Format

Added
Removed
Functional change
Risks
Important unchanged context
Tests needed

Rules

Preserve file paths and identifiers exactly.
Separate mechanical changes from behavior changes.
Call out deletions that remove validation, security, tests, or error handling.
If the diff is incomplete, say what cannot be verified.

Read the full file on GitHub · 63 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.

agents/openai.yaml 209 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.

2mo ago Changed · +24 lines ca5b615a57e9
2mo ago First seen · 39 lines · 39 tokens per session scan A a928fe8f16c9

Subscribe to this mod's changes

diff-reader is a skill published in the GitHub repository Firou91/dyslex.ai (7 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 39 tokens to every session and 473 once invoked, about $0.0002 per session on Opus 5.5. 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 Git and workflow

diff-reader next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
diff-readerFirou91/dyslex.ai	Skill	7	2mo ago	Apache-2.0	A	39	Codex
prYeachan-Heo/oh-my-claudecode	Skill	41k	today	MIT	A	47	Claude Code
merge-batchdiegosouzapw/OmniRoute	Skill	83k	6d ago	MIT	A	46	Claude Code
otto-pr-review-loopomnigent-ai/omnigent	Skill	11k	today	Apache-2.0	A	17	Claude Code, Codex
engram-branch-prGentleman-Programming/engram	Skill	7.8k	today	MIT	A	37	Claude Code, Codex
github-contributordaymade/claude-code-skills	Skill	1.5k	today	MIT	A	105	Claude Code, Codex
revdiffumputun/revdiff	Skill	947	2d ago	MIT	A	250	Claude Code