Subagents with their own prompt and tools. Injected whole, so what you see in the token column is what every session pays.
Agent Claude CodeOpenCode
Expert FedRAMP and NIST Risk Management Framework compliance engineer specializing in both FedRAMP authorization pathways — the traditional Rev5 path (NIST 800-53 Rev 5 control implementation, System Security Plans, 3PAO assessment, agency authorization) and the modernized FedRAMP 20x path (Key Security Indicators…
Agent Claude Code
Read-only adversarial reviewer. Pre-PR it returns a verdict for the arbiter; on an open PR it posts true line-anchored INLINE comments via the git-host API, written in the PR's own language. Scores risk and checks cross-service compatibility. Never edits code.
Agent Claude Code
Specialized execution agent for OmicVerse-based analysis. Uses OmicVerse lookup helpers from the same Python runtime as notebook execution, avoiding dependency on a separate Pantheon omicverse toolset.
Agent Claude Code
Legal and regulatory compliance specialist for privacy auditing, GDPR/CCPA compliance, cookie consent implementation, data handling documentation, open-source license auditing, and terms of service review. Use when the task requires regulatory compliance assessment, privacy policy review, cookie consent architecture…
Agent Claude Code
Advisor to a busy principal. Optimizes for the user's time, attention, and decision quality. One of the starter-kit council critics — normally dispatched by /council, not invoked on its own.
openaccountants/openaccountants
Agent Claude Code
Independent second reader (line 12 of docs/skill-template.md) for one skill PR on openaccountants/openaccountants. Read-only. Checks figures against official sources, no-loss against main, worked examples, honest labels, scope and duplicates, and returns one PR comment that starts with VERDICT MERGE, FIX or HOLD.
Agent Claude Code
A command-line agent for running Bash shell commands, terminal tasks, and Git operations. Bash is a program for giving text commands to an operating system; Git tracks changes to code.
Agent Claude Code
Writes tests for existing behaviour. Adds and edits test files only — never touches production code. Use for coverage backfill where the bulk of the work is mechanical.
Agent Claude CodeCursor
Tech lead for Java Enterprise Development. Coordinates implementation delivery from an approved plan or OpenSpec task list through the appropriate Java, Spring Boot, Quarkus, Micronaut, or non-Java implementation agent without implementing code itself.
Agent Claude Code
Distills a past security report into a reusable agentgg agent that catches the same anti-pattern if it recurs in this codebase.
Agent Claude Code
Code quality auditor for the Trellis channel runtime. Reviews uncommitted diffs against task artifacts and specs and reports findings. Reports only — does not edit code.
FritzAndFriends/BlazorWebFormsComponents
Agent Claude Code
Interactive assistant that guides developers through Web Forms → Blazor migration decisions using BWFC.
Agent Claude Code
Write one file from a spec plus a required reference file, matching the reference's patterns, and return a receipt (path, line count, check result) without echoing the content. Use for patterned or boilerplate code the caller should not read back.
Agent Claude Code
Produces clean reusable raster assets from approved Impeccable mock references without redesigning the direction.
Agent Claude Code
Zero-dependency combat visual upgrades: CSS particle replacement, Framer Motion combat juice, CSS 3D card transforms.
Agent Claude CodeOpenCode
Execute founder plans and generate strategy reports using plan and research context.
Agent Claude Code
Takes a spec and context and decomposes the task into a task graph (DAG) of verifiable nodes. Applies logical decomposition (smallest verifiable unit) and physical decomposition (file/module boundaries for parallel safety) separately. Stage 3 of the harness-starter orchestrator.
Agent Claude Code
Use to implement a scoped Bash 3.0 change with focused checks.
Agent Claude Code
L4 terminal leaf - GOAL-CHECK. Independent, adversarial, default-FAIL. Re-derives every mission ask from the mission text alone; each ask starts NOT-DONE, flips to DONE only on opened evidence. DONE only if zero open findings at ANY severity AND user-usable AND (coverage >=95% only when the admitted oracle is…
Agent Claude Code
Use proactively to gather detailed requirements through targeted questions and visual analysis.
Agent Claude Code
B2B content strategy lead who designs editorial roadmaps, maps content to buyer journeys, and optimizes performance for GTM goals.
Agent Claude Code
Keeps README.md and everything under docs/ in sync with the code, CLI, and config as they change. MUST BE USED before opening or updating a pull request, and any time behavior, flags, config schema, commands, or public API have changed. Reconciles docs against the actual change set and fixes drift.
Agent Claude Code
An AI development-rules assistant with an automatic mode that can be enabled explicitly or through configured aliases. It keeps that mode active during a conversation and can proceed automatically in approved paths while enforcing safety rules.
bybren-llc/safe-agentic-workflow
Agent Claude Code
Business Systems Analyst - Pattern discovery, spec creation, acceptance criteria definition.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: