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/thettwe/nyann/diff-profilenpx skills add thettwe/nyann --skill diff-profilegit clone --depth 1 https://github.com/thettwe/nyannWhat 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 | $0.00142 | $0.00796 |
| Opus 5 | $0.00071 | $0.00398 |
| Sonnet 5 | $0.00028 | $0.00159 |
| Haiku 4.5 | $0.00014 | $0.00080 |
Grade A, and why
diff-profile 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.
How it starts
The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
diff-profile — Compare Two Profiles
You are the diff-profile skill. You compare two nyann profiles and show exactly what would change: hooks added/removed, branching rules, CI config, documentation settings, and more.
When to trigger
- User asks to compare, diff, or contrast two profiles
- User is considering switching profiles and wants to see the impact
- User asks "what hooks does X add over Y" or "what's different"
- User asks what would change before running migrate-profile
DO NOT trigger on: "switch to profile X" (migrate-profile), "what does this profile do" (inspect-profile), "audit this repo" (doctor).
Execution flow
1. Resolve the two profiles
The user must name two profiles. Common patterns:
- Explicit: "diff default vs nextjs-prototype"
- Current vs target: "what would change if I switch to python-cli" → resolve the current profile from CLAUDE.md / preferences, then diff current vs the named target.
- If only one profile is named and the repo has an active profile, use
the active profile as
fromand the named one asto. - If you can't determine both, ask: "Which two profiles should I compare?"
2. Run the diff
bin/diff-profile.sh <from> <to>
Both arguments are bare profile names (e.g. default, python-cli),
not filesystem paths. The script resolves them via load-profile.sh.
3. Present the results
Show a section-by-section summary. Focus on what the user cares about:
- Hooks: "Switching adds
eslint,prettierto pre-commit and removesgitleaks." - Branching: "Strategy changes from github-flow to gitflow."
- CI: "CI generation gets enabled."
- Documentation: "Scaffold types gain
prdandresearch."
If identical is true, say so: "These profiles are identical."
For human-readable output, pass --format human to the script instead
of rendering JSON yourself.
4. Suggest next steps
- "Want to switch? Run
/nyann:migrate-profileto apply the change." - "Want to inspect either profile in detail? Run
/nyann:inspect-profile <name>." - If there are hook changes: "After switching, run
/nyann:retrofitto install the new hooks."
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 · 87 lines · 142 tokens per session scan A 511768450290
diff-profile is a skill published in the GitHub repository thettwe/nyann (6 stars, last pushed 3d ago), licensed MIT. It adds 142 tokens to every session and 796 once invoked, about $0.0007 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.
Other skills, from other repositories
github-skill-forge
一个"制造技能的技能"。这个工具自动化了将任意 GitHub 仓库转换为标准化 Trae 技能的全过程，是扩展 AI Agent 能力的核心工具。.
gcloud-usage
This skill should be used when user asks about "GCloud logs", "Cloud Logging queries", "Google Cloud metrics", "GCP observability", "trace analysis", or "debugging production issues on GCP".
a11y-remediate
Use to produce a leader-facing remediation proposal from one or more /a11y-audit outputs plus team and product context. Translates audit findings into sprint plans, staffing asks, customer-facing language, compliance rollups, and critical-path analysis. Refuses to fabricate numbers, owners, or commitments beyond the…
silicon-throne
硅基圣座总控核心，以神谕式统御把零散任务压成 末将-first 之文明工程.
lite-render-perf
Use when working on React code in apps/lite that derives values during render, adds or consumes a context, subscribes to the redux store or a query, or renders lists of row components — and whenever the lite UI is reported slow, laggy, or re-rendering too much. React Compiler does not prevent these regressions; load…
finn-spec
Interview the user about a raw idea until confident, then file a build-ready issue in Linear. Use when asked to run Finn-loop's spec interview, draft a queue-ready issue, or plan a feature. Interactive — requires the user present; never run unattended.