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.
npx agentmods add skills/reidemeister94/development-skills/explain-diffnpx skills add reidemeister94/development-skills --skill explain-diffgit clone --depth 1 https://github.com/reidemeister94/development-skillsWrote 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.
[](https://agentmods.dev/skills/reidemeister94/development-skills/explain-diff)<a href="https://agentmods.dev/skills/reidemeister94/development-skills/explain-diff"><img src="https://agentmods.dev/badge/skills/reidemeister94/development-skills/explain-diff.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00035 | $0.00920 |
| Opus 5 | $0.00017 | $0.00460 |
| Sonnet 5 | $0.00007 | $0.00184 |
| Haiku 4.5 | $0.00003 | $0.00092 |
Grade A, and why
explain-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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Explain diff
Transfer ownership of a change. Manual mode is repository-read-only; --visual may write only to the system temp directory.
Establish the evidence
Parse --visual; the rest is a working tree, branch, range, PR, patch, or packet. Default to the current worktree. Use the available request, plan, chronicle, verification, and details about what was not checked. Do not require a standard packet.
In Full, require the request, plan or chronicle, diff, fresh Verify results, and details about what was not checked. Otherwise inspect read-only.
State verification status. With absent or stale evidence, label Unverified change and separate code facts from unproved behavior.
For --visual, read visual mode. At the automatic Full checkpoint, name the dynamic concept a visual would clarify and ask Continue in chat or Create visual; only the latter activates it.
Teach the change
Assume no project knowledge. Present only what the change needs:
- the minimum background and vocabulary needed;
- the intuition and functional result;
- concrete examples or sanitized toy data;
- a guided diff ordered by concept, not file order;
- decisions, trade-offs, failure modes, and evidence limits;
- the comprehension dialogue below.
Use a small diagram only when clearer than prose.
Check understanding
Merge overlapping concepts and omit filler. Zero questions is valid. Cover relevant business rules, invariants, flows, states, edge cases, architecture, lifecycle, concurrency, trade-offs, failure modes, and evidence—not syntax.
Ask one applied free-response question at a time through AskUserQuestion. Show the text box with I don't know — explain and Proceed without answering, translated to the conversation language. Do not offer answer choices. In the question text, invite the user to answer in the free-text box; never name interface internals such as "Other".
If the interface cannot show selectable actions, list those two actions beside the free-response prompt.
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.
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.
- 3d ago First seen · 82 lines · 35 tokens per session scan A bbc88d7dfdff
explain-diff is a skill published in the GitHub repository reidemeister94/development-skills (11 stars, last pushed 1mo ago), licensed MIT. It adds 35 tokens to every session and 920 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
ring:adopting-lib-commons-huma-wrapper
Adopting the lib-commons/v5 shared Huma (OAS 3.1) OpenAPI wrapper + RFC 9457 problem model (commons/net/http/{openapi,problem}) in a Lerian Go service: wire openapi.New/ServeSpec + problem.Install (central >=500 scrub) on BOTH runtime and spec-gen paths, the per-rail problem.MapError flex seam, and rename-only spec…
ring:applying-composition-patterns
React composition patterns that scale. Avoid boolean prop proliferation by using compound components, lifting state, and composing internals. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or during architecture review. Skip for simple components with 1-2 props…
ring:searching-code
Forensic code search and analysis with optional Chain of Draft (CoD) ultra-concise mode. Five-phase methodology (clarification, planning, execution, analysis, synthesis) with severity assessment. Use for targeted investigation of specific patterns, bugs, or vulnerabilities. Skip for broad architecture mapping (use…
ring:exploring-codebases
Exploring a codebase across phases: scopes the target, detects architecture, components, and layers, deep-dives each discovered perspective, then synthesizes findings into actionable guidance with file:line evidence. Use to understand how a feature or system works before planning changes, or to orient on an unfamiliar…
ring:opening-pull-requests
Open a GitHub Pull Request with automatic base branch detection, scope allowlist enforcement, PR template filling, and post-create base verification. Replaces ring:generating-pr-descriptions. Use after pushing a branch when ready to open a PR. Skip if the branch is not yet pushed or there are uncommitted changes …
ring:cleaning-comments
Cleaning redundant and obvious comments following clean code principles while preserving meaningful documentation. Supports git scope filtering (staged, unstaged, branch, commit-range). Use when code has excessive comments, during code review, or post-refactor cleanup. Skip when reviewing documentation files or…