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.
git 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/commands/thettwe/nyann/retrofit)<a href="https://agentmods.dev/commands/thettwe/nyann/retrofit"><img src="https://agentmods.dev/badge/commands/thettwe/nyann/retrofit.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 5.1 | $0.00061 | $0.00634 |
| Opus 5 | $0.00030 | $0.00317 |
| Sonnet 5 | $0.00012 | $0.00127 |
| Haiku 4.5 | $0.00006 | $0.00063 |
Grade A, and why
nyann: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 7d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plugin root: This is a Claude Code plugin, NOT a CLI tool. Do NOT
search via which, npm list, pip list, or brew list. This file
is at <plugin_root>/commands/. All scripts: <plugin_root>/bin/.
Read the matching skills/*/SKILL.md for the full flow.
/nyann:retrofit
Wraps bin/retrofit.sh --target <cwd> --profile <name>.
Audit + remediation flow for existing repos with partial or drifted setups:
detect stack → load profile → compute drift → render report → offer fix
↓
build plan → preview → bootstrap
Output is the same four-section drift report as doctor:
MISSING: files the profile expects but the repo lacks
MISCONFIGURED: files present but content short of expectations
NON-COMPLIANT HISTORY: last N commit subjects that don't match Conventional
Commits (informational only — no rewrite offered)
DOCUMENTATION:
✓/⚠/✗ CLAUDE.md size against budget
✓/✗ internal link resolution
⚠ MCP links needing connector verification (skill-layer)
✓/⚠ orphan detector on docs/ + memory/
Exit codes:
| Code | Meaning |
|---|---|
| 0 | clean — no drift, nothing to fix |
| 4 | warnings only (misconfigured, non-compliant history, orphans, CLAUDE.md warn/absent) |
| 5 | critical (missing hygiene files, broken internal links, CLAUDE.md hard-cap error) |
When to invoke
- "fix this repo" / "retrofit this repo" / "bring into compliance" → run this.
- "my repo is half set up, finish it" / "fill in the gaps" → run this.
- After
/nyann:doctorreports drift and user says "fix it" → run this.
Flags the skill layer forwards
--profile <name>override profile resolution for this run.--jsonemit DriftReport JSON; skips remediation offer.
See also:
/nyann:doctor— read-only audit (same report, no remediation)./nyann:bootstrap— full setup from scratch.
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.
- 7d ago First seen · 71 lines · 61 tokens per session scan A 3358cfd5c811
nyann:retrofit is a command published in the GitHub repository thettwe/nyann (6 stars, last pushed 8d ago), licensed MIT. It adds 61 tokens to every session and 634 once invoked, about $0.0003 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 commands, from other repositories
fix
Quick bugfix commit. Use for fix bug, bugfix, patch, hotfix, correct error.
techdebt
Find and report technical debt in the codebase.
composite-actions
Generate, review, secure, and test composite GitHub Actions following best practices — full repo scaffold, interview-driven generation, PR creation on existing repos, SHA pinning, secrets-as-inputs, job summaries, and actionlint validation.
gitops
Flux CD and Argo CD — two modes. debug: five structured debug workflows for live clusters (installation, source, HelmRelease, Kustomization, ResourceSet) producing a five-section report. audit: six-phase read-only repo analysis (discovery, validation, API compliance, best practices, security) producing a prioritised…
triage
Triages a PR comment — from a bot (Copilot, CI) or a human reviewer. Fetches the comment and diff via gh CLI, classifies it, applies the fix directly to the file if valid, posts a reply on the thread, and resolves it. Run from inside the repo.
genshijin-commit
A command that writes a commit message for changes already placed in Git's staging area. It follows the repository's existing language and uses a short imperative subject without AI attribution.