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 retrofitgit 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/retrofit)<a href="https://agentmods.dev/skills/thettwe/nyann/retrofit"><img src="https://agentmods.dev/badge/skills/thettwe/nyann/retrofit/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/retrofit"><img src="https://agentmods.dev/badge/skills/thettwe/nyann/retrofit.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 | $0.00193 | $0.02508 |
| Opus 5 | $0.00097 | $0.01254 |
| Sonnet 5 | $0.00039 | $0.00502 |
| Haiku 4.5 | $0.00019 | $0.00251 |
Grade A, and why
retrofit 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 5d 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 — 238 lines — stays where its author put it; the contents beside it link to each section on GitHub.
retrofit
Audit an existing repo's drift from a profile and remediate what's missing or misconfigured. This is the "fix it" counterpart to doctor's "tell me what's wrong."
1. Resolve the profile
Same logic as doctor — the audit is only meaningful against an intended baseline:
- Check if the repo's CLAUDE.md (inside
<!-- nyann:start -->markers) declares an active profile name. - If the user passed
--profile <name>, use that. - If neither, ask the user which profile to audit against. List available profiles (starters + any user/team profiles). Don't silently default — the wrong baseline produces misleading drift.
Load via bin/load-profile.sh <name>. If exit 2 (not found), show the
list the loader reports and ask again.
2. Run detection
Run bin/detect-stack.sh --path <target> to get the StackDescriptor. This
ensures the remediation step has stack context for gitignore templates, hook
phases, and CLAUDE.md rendering.
3. Run the drift audit
bin/retrofit.sh --target <cwd> --profile <resolved-name>
Do not pass --report-only — that's doctor's flag. Retrofit's default
mode renders the report AND offers remediation guidance.
Pass --json only if the user explicitly asks for machine-readable output.
3a. Narrow scope (v1.7.0+)
If the user said something like "only fix the docs drift", "leave my
hooks alone", "just the gitignore", or otherwise wants to remediate
one part of the audit without touching others, pass --scope <csv>
to retrofit:
| User intent | --scope |
|---|---|
| "fix only the docs" | docs |
| "fix hooks but leave docs alone" | hooks |
| "fix the gitignore" | gitignore |
| "fix only docs and hooks" | docs,hooks |
| "fix the github protection settings" | github |
| "fix everything" / unstated | omit (default all) |
The accepted categories are docs, hooks, branching, gitignore,
editorconfig, github, history, all. Unknown values exit
non-zero; surface the error to the user verbatim.
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.
- 5d ago First seen · 238 lines · 193 tokens per session scan A d64a77f23868
retrofit is a skill published in the GitHub repository thettwe/nyann (6 stars, last pushed 10d ago), licensed MIT. It adds 193 tokens to every session and 2,508 once invoked, about $0.0010 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 2026-09-03.
Other skills, from other repositories
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…
google-ads-audit
Google Ads account audit and business context setup. Run this first — it gathers business information, analyzes account health, and saves context that all other ads skills reuse. Trigger on "audit my ads", "ads audit", "set up my ads", "onboard", "account overview", "how's my account", "ads health check", "what should…
sxo
Search Experience Optimization (SXO) — the bridge between SEO and UX/CRO. Audits the full journey from the SERP click to the on-page goal: SERP click-through factors (title/meta/rich results that win the click), then post-click experience signals that keep users and drive conversions — above-the-fold relevance and…
elixir-idioms
OTP/BEAM patterns and Elixir idioms — GenServer, Supervisor, Task, Registry, pattern matching, with chains, pipes. Use when designing processes or debugging BEAM issues.
security
Enforce Elixir/Phoenix security — auth, OAuth, sessions, CSRF, XSS, SQL injection, input validation, secrets. Use when editing auth files, login flows, RBAC, or API keys.
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.