phil9922

12 mods across 1 repository, 1 stars between them.

claude-swarm

02

phil9922/claude-swarm

Plugin Claude Code

Context-shielding, cost-tiered delegation for Claude Code: high-volume work runs in specialized subagents on the cheapest tier a grader can check, returning summaries that keep the main context small. Ships a tiered agent roster, an orchestration skill, three workflows (survey, audit, and a manifest-driven build), and.

1 1mo ago A tokens not measured original MIT

implementer

03

phil9922/claude-swarm

Agent

Writes production code where a mistake is expensive. Dispatch for real feature work, non-trivial bug fixes, refactors that must preserve behavior, and anything touching correctness-critical paths. Deliberately runs on the top model tier — do not route work here that the mechanic agent could do from a precise spec, and…

1 1mo ago A 85 tokens original MIT

leaf

04

phil9922/claude-swarm

Agent

Build-workflow leaf. Fills the bodies of pre-written signature files for one manifest unit or a small batch of them. Dispatch from the claude-swarm:build workflow, not ad hoc — it expects exact owned paths, fixed signatures, and a type-check command. Writes only the files its unit owns, runs the type check before…

1 1mo ago A 92 tokens original MIT

mechanic

05

phil9922/claude-swarm

Agent

Applies a precisely specified change across a codebase. Dispatch for mechanical work where the decision is already made and only the execution remains — apply this pattern to these N files, add these headers, rename this symbol everywhere, update these call sites to the new signature. Cheap because the compiler and…

1 1mo ago A 82 tokens original MIT

scout

06

phil9922/claude-swarm

Agent

Cheap read-only locator. Dispatch when you need to find WHERE something is — the file defining a symbol, every call site of a function, which package owns a concept, whether a pattern exists anywhere in the repo. Returns paths and line numbers, not explanations. Use several in parallel to sweep a repo from different…

1 1mo ago A 87 tokens original MIT

scribe

07

phil9922/claude-swarm

Agent

Writes and maintains prose about code — README sections, docs, changelogs, release notes, code comments, config examples. Dispatch when the content is documentation rather than implementation. Cheapest agent in the roster; use it freely for writing tasks and never for deciding what the code should do.

1 1mo ago A 59 tokens original MIT

tracer

08

phil9922/claude-swarm

Agent

Deep reader that returns a short answer. Dispatch when understanding something requires reading a lot of code — how a flow is wired end to end, what a subsystem actually does, why two components interact, what the real control flow is behind an abstraction. Reads thousands of lines and returns a few hundred words. Use…

1 1mo ago A 94 tokens original MIT

verifier

09

phil9922/claude-swarm

Agent

Adversarial checker. Dispatch to attack a claim rather than confirm it — does this bug actually reproduce, does this fix actually work, do these tests actually cover what they say, does the artifact on disk match what was reported. Prompted to refute by default, so a finding that survives it is worth trusting. Run…

1 1mo ago A 96 tokens original MIT

SessionStart

10

phil9922/claude-swarm

Hook

Runs when a session starts, executing session-start.js via node. From phil9922/claude-swarm.

1 1mo ago A tokens not measured copy · 55% MIT

SubagentStop

11

phil9922/claude-swarm

Hook

Runs when a subagent finishes, executing subagent-stop.js via node. From phil9922/claude-swarm.

1 1mo ago A tokens not measured copy · 52% MIT

claude-swarm

12

phil9922/claude-swarm

Skill Claude CodeCodex

The orchestration playbook for the claude-swarm roster — the three delegation modes (Shield keeps high-volume output out of the main context, Route puts one agent on the cheapest tier a grader can check, Build is gated wide fan-out), which model tier each agent runs on and why, how to author a Workflow inline or call…

1 1mo ago A 129 tokens original MIT