Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add MasonEgger/bpe-claude-code-plugin/plugin install bpeWrote 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/masonegger/bpe-claude-code-plugin/retrofit)<a href="https://agentmods.dev/skills/masonegger/bpe-claude-code-plugin/retrofit"><img src="https://agentmods.dev/badge/skills/masonegger/bpe-claude-code-plugin/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/masonegger/bpe-claude-code-plugin/retrofit"><img src="https://agentmods.dev/badge/skills/masonegger/bpe-claude-code-plugin/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 | $0.00060 | $0.03068 |
| Opus 5.5 | $0.00024 | $0.01227 |
| Sonnet 5.5 | $0.00012 | $0.00614 |
| Haiku 4.5 | $0.00006 | $0.00307 |
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 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Retrofit Command
Add a BPE-compatible spec.md to an existing project that never went through /bpe:brainstorm.
Most of what a spec needs already lives in the repo; read it there instead of asking.
The shortened Q&A covers only the gaps the repo cannot answer: intent, direction, and scope.
The resulting spec.md matches the format /bpe:brainstorm produces, so /bpe:plan consumes either without knowing which skill wrote it.
With --resync, retrofit instead reconciles an existing spec.md to what the code does now, migrates a pre-0.7 spec to the canonical section order, and refreshes any vendored rules (see Resync Mode at the end).
Procedure
-
Guard against clobbering. Check for spec.md at the repo root. If it does not exist, proceed in new-spec mode. If it exists and
--resyncis in $ARGUMENTS, proceed in resync mode (see Resync Mode); the spec is edited in place, never overwritten. If it exists and--replaceis in $ARGUMENTS, proceed in new-spec mode; step 5 overwrites the file. If it exists and neither flag is present, refuse: tell the user a spec.md already exists, that/bpe:retrofit --resyncreconciles it to the code and/bpe:retrofit --replaceoverwrites it, then stop. -
Read repo state. Run
lsat the repo root. Read README.md if present. Read CLAUDE.md if present. Read whichever manifest files exist: package.json, pyproject.toml, go.mod, Cargo.toml. If the language is detectable from the manifests, read the top-level module docstrings (or equivalent package-level docs) of the main source directories. Use what these reveal to pre-fill draft answers, so the Q&A in step 4 asks only about gaps. Derive Invariants candidates from the same read; the repo is a higher-signal source than negating interview answers. The manifests give the tech stack (language, runtime, primary frameworks, package manager) as prose bullets. A lockfile (uv.lock, package-lock.json, Cargo.lock, go.sum) makes- deps: frozena candidate; propose it only when the dependency set looks settled, and never silently. The main source directories make- paths: <dir>/**[, <dir>/**]a candidate. Anything README.md or CLAUDE.md states as mandatory or forbidden is a prose candidate as written. These candidates go to the single confirm in step 4, not to their own question.
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 Changed · +24 lines · +17 tokens per session 35a2b526921a
- 1mo ago Changed · +30 lines · +11 tokens per session d64444d9a74c
- 1mo ago Changed d86d4e58080c
- 2mo ago First seen · 72 lines · 32 tokens per session scan A a84a34702e91
retrofit is a skill published in the GitHub repository MasonEgger/bpe-claude-code-plugin (7 stars, last pushed 27d ago), licensed MIT. It adds 60 tokens to every session and 3,068 once invoked, about $0.0002 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
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…