yukta / plugins
CLAUDE.md1 starsChanged 20 days agoApache-2.0View on GitHub
In this repository21 other files it gives its agents.
- architecture/CLAUDE.mdCLAUDE.md
- boot/CLAUDE.mdCLAUDE.md
- build-logic/CLAUDE.mdCLAUDE.md
- .claude/CLAUDE.mdCLAUDE.md
- CLAUDE.mdCLAUDE.md
- cli/CLAUDE.mdCLAUDE.md
- core/CLAUDE.mdCLAUDE.md
- mcp/CLAUDE.mdCLAUDE.md
- messaging/CLAUDE.mdCLAUDE.md
- plugin-api/CLAUDE.mdCLAUDE.md
- plus/CLAUDE.mdCLAUDE.md
- ui/CLAUDE.mdCLAUDE.md
- web/CLAUDE.mdCLAUDE.md
- ide-index-mcpSkill
- pickupSkill
- playwrightSkill
- testsSkill
- ticketSkill
- yuktaSkill
- yukta-supervisorSkill
- yukta-workflowsSkill
The file
We split this CLAUDE.md into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 45
Follow the tiered "Test Execution Policy (speed)" in the root CLAUDE.md: run --tests for the classes you changed first.
≈ “Common” is an estimate: at least 1 in 5 of the 27,641 CLAUDE.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Plugins CLAUDE.md
Overview
Implementations of various Yukta plugins.
Plugin Types
- Processors: Located in
processors/. Modules:process-executor,internal/internal-core,http-request(HTTP_REQUEST),file-io(FILE_READ/FILE_WRITE, sandboxed tobaseDir),AGENT_SESSION(inprocess-executor, EXTENDED + restricted: runs an agent harness (Claude Code) on a prompt throughProcessExecutorGateway; portssuccess/failure/incomplete, payload{status, reason, text, sessionId, turn, exitCode};session(a key; the same key resumes the harness from the token the last turn left; one turn at a time per key,onBusyWAIT or FAIL; in memory behindAgentSessionStore;approvals: ASKruns the harness over a stdin conversation (ProcessExecutorGateway.executeInteractive, presetinteractiveblock: for Claude Code--input-format stream-json --permission-prompt-tool stdio) and turns each tool-use request into anAPPROVALonInputGateway,AgentApprovals; refusal on no answer); a harness is a JSON preset inagent-harnesses/on the classpath or inyukta.ai.presets-dir, adding one needs no Java;harnessoptions and the usage pattern list the presets),sql-query(SQL_QUERY, parameterized JDBC; driver supplied by deployer), internal-core also hasDELAY,WAIT_FOR_SIGNAL(waits forsignal_node/ REST signal; a signal that comes first is kept for the wait; open waits are listed atGET /api/sessions/{s}/approvals),SUB_WORKFLOW(runs a workflow of the same session throughSubWorkflowGateway, results from its terminals),VALIDATE,AGGREGATE,llm-call(LLM_CALL, Spring AI: OpenAI-compatible/Anthropic/Ollama),mcp-tool-call(MCP_LIST_TOOLSlists a server's tools for thetoolsoption ofLLM_CALL, which returns the model's native tool calls inactions;MCP_TOOL_CALL, MCP client over streamable HTTP;allowedToolsrefuses any other tool, e.g. one picked by a model (requireApprovallists tools, or*, that wait for asignal_nodeanswer first (approvalSignal,approvalTimeoutSeconds);LLM_CALLcan refuse prompts and answers withyukta.llm.deny-input-patterns,deny-output-patternsandmax-input-chars, space calls per provider withyukta.llm.rate-limit.<provider>(requests per minute), end the whole run withbudget.hardStop, and send earlier tool exchanges (actionson an assistant turn,{role: tool, toolCallId, toolName, content}turns); gateway-levelyukta.mcp-client.allowed-tools,max-argument-bytesanddeny-argument-patternsapply to every node), and aWAIT_FOR_SIGNALnode in front adds a human approval; session cache, SSE progress heartbeat, cancel, idempotency_meta). Sample chat-agent workflow:bruno/SessionConfigController/Apply Chat Agent Session.bru. - Decision processors (
processors/decision, optional plugindecision): constrained model decisions for routing and gating, with Ollama System One (backend: SYSTEMONE, default, calibrated probabilities, local) or any chat model (backend: LLM+provideropenai/anthropic/ollama, viallm-call'sLlmGateway; probabilities are the model's own estimate, uncalibrated). Types:CLASSIFY(labels, optionalrouteByLabel,uncertainport),GATE(yes/no,pass/reject),SCORE(levels, optionalhigh/low),ASK(up to 64 questions in one call),ANOMALYandDEDUPE(compare with the last N items of the node's run;normal/anomalous,unique/duplicate). Results go in metadata underinto. A model failure fails the message; use the node'senginepolicy (retry,onError) for retries and dead letters. The backends areDecisionBackendbeans (SystemOneModelkindSYSTEMONE,ChatDecisionModelkindLLM), picked byDecisionModelsthrough thebackendoption; they implementAiBackend(plugin-api), whichGET /api/ai/backendsand thelist_ai_backendsMCP tool list with their options. Enabling it also pulls inLLM_CALL. System One needs Ollama 0.35+ and a decision model such astev1:0.8b; keep descriptions of labels/levels explicit, a small model needs them. - Community plugins (
external, optional pluginexternal, depends onprocess-executorviaModuleRules.ALLOWED):ExternalPlugins(aPluginSource) readsyukta-plugin.jsonmanifests fromyukta.plugins.dirand registers anExternalProcessorPluginorExternalTerminalPluginfor each type named inyukta.plugins.enabled(TYPEorTYPE@sha256:<PluginDigest>;alldoes not cover them).CommandRunruns the command once per message throughProcessExecutorGateway.executeInstalled: envelope v1 on stdin (declared config fields only, resolved), stderr to the log, stdout lines checked againstmessage-out.schema.json.run.imageruns<runtime> run --rm -i --name yukta-<type>-<uuid> <yukta.plugins.container.args.TYPE> <image>through the same path (Containers: image inspected or pulled at startup,rm -fon timeout or cancel, only the CLI's own variables such asDOCKER_HOSTadded).run.mcp(McpRun, depends onmcp-tool-callviaModuleRules.ALLOWED): over stdio (commandorimage)StdioMcp, a hand-written JSON-RPC client over one long-lived process started withProcessExecutorGateway.executeInstalledInteractive(clean env; the MCP SDK's stdio transport would pass the whole environment), restarted after it exits; over HTTP (url)HttpMcpthroughMcpClientGateway. At startup the tool's input schema is read: its properties become config fields (McpTools.fields) and the pin isMcpTools.digest(dir digest, schema). Config resolved per message = the tool's arguments; payload =structuredContentor text;isErrorfails the message.ExternalPlugins.close()stops the servers. Guide:../docs/guides/extend/write-a-community-plugin.mdx; design:../design/plans/community-plugins.md. - Triggers: Located in
triggers/. Modules:api-trigger,constant-source,schedule-trigger(SCHEDULE_TRIGGER, interval/cron). - Terminals: Located in
terminals/. Modules:console-terminal,notify-terminal(NOTIFY_TERMINAL, Slack-compatible JSON webhook). - Supervisor engines: Located in
supervisors/. Modules:rules(typerules: declarative JSON/SpEL rules, presetsfailure-guard,stall-watchdog,approval-gate, timedeveryrules; therule-supervisorbean is enabled byyukta.supervisor.rules.filebut owns nothing), andprocess-engine(typeprocess, JSON lines on stdin/stdout;yukta.process.allowed-commands). Engines depend onplugin-apionly (ArchUnit). Rules can also answer or escalate input requests (then.answer,then.escalate; only withcanAnswer/maxRisk, neverHIGH); example:../examples/16-supervisor-profiles/input-requests.json, loaded byInputRulesExampleTest. The control planes (rule,model,rules-first) were removed in S7.
Tiers and enabling
Every plugin has getTier() (CORE, EXTENDED, SPECIFIC; default CORE) and isRestricted() (reaches outside the engine). PluginRegistry registers CORE and unrestricted EXTENDED plugins always; SPECIFIC and restricted ones only when named in yukta.plugins.enabled (env YUKTA_PLUGINS_ENABLED, a list of types, or all). GET /api/plugins and the list_plugins / get_plugin_details MCP tools show every plugin with tier, restricted, enabled and enableWith, and a workflow that uses a disabled type fails validation with the setting to change. PluginTierAcceptanceTest lists every plugin: a new one must be classified there. boot tests run with all.
Config schema
Declare getConfigSchema() (see ConfigField) on a plugin to get a generated config form in the UI. Every plugin that takes configuration declares one (API_TRIGGER and CONSOLE_TERMINAL take none); a new plugin without a schema falls back to the JSON editor and the usage pattern. Keep field names equal to the keys the plugin reads, and add a test pinning the names and which are required.
Conformance kit
boot's PluginConformanceSweepTest runs PluginConformance (plugin-api test fixtures) over every registered plugin: schema vs. config, bad config gives a clear error, minimal config runs, cancel reaches the input and leaks no thread, a 10 MB message, an upstream error, no secret in logs. A new plugin fails that test until you either add a fixture (a minimal hermetic config, plus INPUTS if it reads input fields) to fixtures() in the test, or a reason to boot/src/test/resources/conformance-exemptions.properties. A SECRET schema field gets a canary value, so declare secrets with ConfigField.Type.SECRET.
Build Commands
# Build a specific plugin
yk gradle :plugins:processors:process-executor:buildDevelopment
Each plugin should implement the interfaces defined in plugin-api.
Guide: ../docs/contributing/modules/plugins.mdx (module guide); open risks, bugs and review findings: GitHub issues labelled plugins (gh issue list -l plugins; risks also carry risk); evolution path and quality lenses: ../design/assessments/plugins.md.
Conformance check
boot/.../plugins/PluginConformanceAcceptanceTest checks every registered plugin against the plugin contract (type name, category, config schema, output ports, timeout and buffer defaults, a description, validateConfig rejecting an empty config when a field is required, no crash on validateConfig or shutdown). A new plugin is covered with no test change; PluginCoverageAcceptanceTest still needs its type listed. If a plugin must break a rule, add "TYPE: rule" -> reason to EXEMPT in the conformance test.
Runtime check
boot/.../plugins/PluginRuntimeAcceptanceTest runs every plugin that does not need the outside world and checks that a cancel reaches the upstream, that a 10 MB message is handled or refused cleanly, and that initialize and shutdown can repeat. A new plugin must add a fixture (type to a valid config, in FIXTURES) or a reasoned entry in EXEMPT (for example, it calls an LLM or a URL); the test fails otherwise.
Imports
@.claude/rules/coding-standards.md @.claude/rules/git-workflow.md
Testing speed
Follow the tiered "Test Execution Policy (speed)" in the root CLAUDE.md: run --tests for the classes you changed first; full :plugins:test only when many files changed.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

