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 skills add thettwe/nyann --skill explain-diffgit clone --depth 1 https://github.com/thettwe/nyannWrote 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/thettwe/nyann/explain-diff)<a href="https://agentmods.dev/skills/thettwe/nyann/explain-diff"><img src="https://agentmods.dev/badge/skills/thettwe/nyann/explain-diff/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.
<a href="https://agentmods.dev/skills/thettwe/nyann/explain-diff"><img src="https://agentmods.dev/badge/skills/thettwe/nyann/explain-diff.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00228 | $0.01310 |
| Opus 5.5 | $0.00091 | $0.00524 |
| Sonnet 5.5 | $0.00046 | $0.00262 |
| Haiku 4.5 | $0.00023 | $0.00131 |
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 1mo 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
explain-diff
Read-only template render. Wraps bin/explain-diff.sh.
When to trigger
- User has a DriftReport (from doctor / retrofit / compute-drift) and wants prose.
- User wants to paste a doctor summary into a PR body or chat without sharing raw JSON.
- User explicitly asks for "the drift in plain English".
When NOT to trigger
- User is asking "is this repo healthy" → that's
doctor(which can chain into this via--explain). - User wants to mutate / fix → that's
retrofit. - User wants LLM-polished output → this skill is template-only by design (no LLM). If the user wants prose with more nuance, suggest reading the markdown output and editing by hand.
Invocation
Three call shapes:
1. Direct: file path
bin/explain-diff.sh --file path/to/drift.json
2. Pipe from a producer
bin/compute-drift.sh --target . --profile default | bin/explain-diff.sh -
3. Via doctor (recommended path)
bin/doctor.sh --target . --profile default --explain
doctor --explain is preferred because it also forwards the computed health score and trend delta into the narrative header line — the same numbers text-mode shows at the foot of its output.
--explain is mutually exclusive with --json on doctor; if both are passed, doctor dies with a clear error.
Output shape
Markdown (default) — three sections:
- Header — target + profile + (optional) health score + trend
- What's drifted — one bullet per drift category, ordered by severity. Each bullet has a lead phrase (
Action required:,Worth fixing:,Drifted:,Minor:) and up to 5 concrete items. If a category has more than 5 items, an "...and N more" line appears. - What you can do — ordered action items that map to nyann skills (
nyann:retrofit,nyann:optimize-claudemd, etc.)
JSON (--format json) — the DriftNarrative shape (schemas/drift-narrative.schema.json). Useful for chat-bot integrations or custom renderers that want the same source-of-truth without re-parsing the prose.
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.
- 1mo ago First seen · 108 lines · 228 tokens per session scan A 3393e8f98b7f
explain-diff is a skill published in the GitHub repository thettwe/nyann (7 stars, last pushed 6d ago), licensed MIT. It adds 228 tokens to every session and 1,310 once invoked, about $0.0009 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.
Other skills, from other repositories
daily-working
End-to-end pipeline: pull a task from the project's task tracker by ID (Redmine or GitHub Issues today, more addable via a new adapter), sanity-check and impact-assess it against the codebase before touching anything, implement it with the Claude CLI, verify the result in a real browser via the Claude Chrome extension…
sxo
Search Experience Optimization (SXO), the bridge between SEO and UX/CRO. Audits the journey from the SERP click to the on-page goal: click-through factors (title, meta, rich results), then post-click signals that keep users and drive conversions: above-the-fold relevance and intent match, page speed / Core Web Vitals…
meta-tags-optimizer
Optimize title tags, meta descriptions, Open Graph, and Twitter cards for maximum click-through rate. Generates multiple A/B test variations with character counting and SERP preview. Use when asked to "optimize title tag", "write meta description", "improve CTR", "Open Graph tags", "fix my meta tags", "social media…
critical-code-reviewer
Rigorously review code or pull requests for correctness, security, accessibility, maintainability, tests, and edge cases. Use when users request a critical code review, want a guided walkthrough of findings, need implementer-facing feedback, or want to prepare, create, or submit a GitHub pull request review.
shiny-bslib
Build modern Shiny dashboards and applications using bslib (Bootstrap 5). Use when creating new Shiny apps, modernizing legacy apps (fluidPage, fluidRow/column, tabsetPanel, wellPanel, shinythemes), or working with bslib page layouts, grid systems, cards, value boxes, navigation, sidebars, filling layouts, theming…
tidewave-integration
Tidewave MCP runtime tools — debugging, smoke testing, live state inspection, SQL queries, hex docs. Use when evaluating code in a running Phoenix app.