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/MasonEgger/bpe-claude-code-pluginWrote 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/plugins/masonegger/bpe-claude-code-plugin/bpe)<a href="https://agentmods.dev/plugins/masonegger/bpe-claude-code-plugin/bpe"><img src="https://agentmods.dev/badge/plugins/masonegger/bpe-claude-code-plugin/bpe/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/plugins/masonegger/bpe-claude-code-plugin/bpe"><img src="https://agentmods.dev/badge/plugins/masonegger/bpe-claude-code-plugin/bpe.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
bpe 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.
What it actually says
{
"name": "bpe",
"version": "0.7.1",
"description": "BPE (Brainstorm-Plan-Execute) development workflow: a permanent spec with invariants and deferred work, spec-driven TDD, autonomous multi-step runs with a validation gate, vendored rules for contributors, and cross-session continuity",
"author": {
"name": "Mason Egger",
"url": "https://mason.dev"
},
"repository": "https://github.com/MasonEgger/bpe-claude-code-plugin",
"license": "MIT",
"hooks": "./hooks/profile-check.json",
"keywords": ["workflow", "tdd", "session-management", "autonomous-execution", "orchestration", "subagents", "development"]
}
What it installs
The manifest is a name and a version. 13 skills, 3 agents travel with it, and installing the plugin installs all of them — 777 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill plan A 27 tokens
- Skill goal A 126 tokens
- Skill retrofit A 60 tokens
- Skill review A 44 tokens
- Skill handoff A 17 tokens
- Skill apply-review A 20 tokens
- Skill session-summary A 16 tokens
- Skill lessons A 20 tokens
- Skill wtf-wid A 32 tokens
- Skill commit-message A 18 tokens
- Skill execute-plan A 45 tokens
- Skill gh-issue A 19 tokens
- Skill brainstorm B 27 tokens
- Agent step-executor A 132 tokens
- Agent validator A 123 tokens
- Agent cheap-research A 51 tokens
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 30868cc116a4
- 1mo ago Changed 6ddb16c8edcf
- 2mo ago First seen · 14 lines scan A eb6493e5a585
bpe is a plugin published in the GitHub repository MasonEgger/bpe-claude-code-plugin (7 stars, last pushed 27d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
knowledge-virtuoso
6 knowledge skills: accessibility, context engineering, debugging, docs lookup, performance, and security.
jira-pack
Issue-tracker pack: /jira-fix takes a ticket link of any type, verifies tracker access, classifies it as a defect or a change, reproduces the defect or writes a failing acceptance test for the change, routes the work to core executors, comments back with evidence and moves the ticket to the QA column. Opt-in; requires.
whetstone
Engineering-craft skills: red-green TDD, flaky-test audit, diagnosis, doubt review, grilling, merge-conflict resolution, research reports with grounded claims, HTML reports, skill linting and a column budget. Every gate among them carries a deterministic self-verify.
superpowers-deepseek-v4
Superpowers DeepSeek v4: composable agent skills for TDD, debugging, and collaboration. Independently maintained; not identical to obra/superpowers.
safeword
AI coding agent workflows: BDD, auto-linting, quality reviews, debugging, and refactoring. Run safeword install in a project to enroll it.
twdd
Test-Window-Driven Development skill for scarce validation windows, hard abort boundaries, replayable evidence, and batched repair.