adversary
by bobtat · ★ 2 · updated today
Adversarial review of a PR, plan or document by an isolated reviewer that never sees the author's context, with a triage pane deciding which findings reach the author
Install
/plugin marketplace add bobtat/claude-plugins/plugin install adversary@bobtat-pluginsThen run /reload-plugins or start a new session. Requires Claude Code 2.1.287+.
What it hooks into
From an automated scan with claude plugin validate, not a security review. Mods run with your permissions; read the code before installing.
- Events
tool.callprompt.submitui.rendersession.startagent.offercommand.runprompt.attachmentturn.completeui.closesession.end- API calls
$.agent.list$.agent.register$.agent.spawn$.clock.now$.command.register$.env.get$.fs.exists$.fs.list$.fs.read$.fs.stat$.fs.write$.mcp.call$.mcp.connect$.process.run$.prompt.fill$.session.id$.session.root$.state.get$.state.set$.tool.call$.tool.list$.ui.close$.ui.log$.ui.open$.ui.resolve$.ui.toast- Draws
AbovePromptPane- Can see
ExitPlanMode callsevery promptRead|Grep|Glob callsevery tool call- Reach
- level 3 of 3 MCP serversruns processeswrites filesdrives Claudewrites the prompt boxreads filesreads env varsreads mod statedraws
Origin
- How it got here
- Automated scan of public GitHub repos, via the CC0 dataset awesome-claude-code-mods (scan of ).
- Repository
- github.com/bobtat/claude-plugins
- Path in repo
plugins/adversary- Source commit
1e9bcd8the exact code the scan read- Author
- @bobtat
- License
- MIT
- First published
- Last pushed
- First listed here
Name and description come from the mod's own manifest. We link to the code; we don't host it, and it stays under its author's license.
More from bobtat/claude-plugins
cost-ledger
bobtat/claude-plugins
Tracks what Claude Code costs — session, calendar-week and calendar-month totals with the month's pace and week-over-week change, a /costs pane with a spend calendar, the most expensive prompts and what filled the context, plus prompt-cache awareness: a cache warm/cold countdown, warnings before a prompt, model switch or large write re-caches the context, a per-category breakdown priced at...
subagent-tree
bobtat/claude-plugins
A live /agents-tree pane showing the session's subagents as a tree — status, how long each has run, its tool calls and steps, the tool it is on now and the output tokens it used