feat(skills): add parallel-ops router, trim fleet family discovery surface

Six skills orbit "run parallel/recurring agent work" (fleet-ops, fleet-worker,
fleetflow, loop-ops, iterate, spawn) with overlapping frontmatter descriptions
that forced a cold agent to read five SKILL.mds to route correctly. Adds
parallel-ops as the single router owning cross-family discovery (a decision
table over spawn-vs-land and inner-vs-outer-loop axes), and trims the six
members' descriptions/when_to_use down to their own domain now that the
router owns the comparison prose. Also tightens claude-code-ops' oversized
(>900 char) description and links it to parallel-ops via related-skills.

Resolves the name collision between spawn (authors static agent prompt
files) and the fleet skills (which spawn runtime workers) by pointing spawn
at parallel-ops in its own description.

AGENTS.md

@@ -5,7 +5,7 @@
 This is **claude-mods** - a collection of custom extensions for Claude Code:
 - **3 expert agents** for pure context-isolation/worker roles (git-agent, firecrawl-expert, project-organizer) - every domain-knowledge agent became an `-ops` skill (v3.0, skills-first)
 - **3 commands** for session management and git orchestration (/sync, /save, /git-ops)
-- **101 skills** for CLI tools, patterns, workflows, and development tasks (incl. `fleetflow` for heterogeneous GLM/Codex/Anthropic worker fleets, `repo-doctor` for agentic-quality repo audits, `svg-brand-tint-ops` for zero-dep in-browser SVG brand-recolour + Potrace-stage raster vectorising, `r-ops` for tidyverse-first modern R / data analysis, `loop-ops` for outer-loop design discipline, `ffmpeg-ops` for probe-first media processing and EDL-driven editing, `supply-chain-defense` for behavioural-first dependency security, `prompt-injection-defense` for instruction-integrity scanning, `pypi-ops` for OIDC Trusted Publishing to PyPI, `net-ops` for network troubleshooting, `windows-ops` / `mac-ops` for workstation diagnostics, `fleet-worker` for cheap parallel worker delegation)
+- **102 skills** for CLI tools, patterns, workflows, and development tasks (incl. `parallel-ops` for routing across the parallel/recurring-agent-work skill family, `fleetflow` for heterogeneous GLM/Codex/Anthropic worker fleets, `repo-doctor` for agentic-quality repo audits, `svg-brand-tint-ops` for zero-dep in-browser SVG brand-recolour + Potrace-stage raster vectorising, `r-ops` for tidyverse-first modern R / data analysis, `loop-ops` for outer-loop design discipline, `ffmpeg-ops` for probe-first media processing and EDL-driven editing, `supply-chain-defense` for behavioural-first dependency security, `prompt-injection-defense` for instruction-integrity scanning, `pypi-ops` for OIDC Trusted Publishing to PyPI, `net-ops` for network troubleshooting, `windows-ops` / `mac-ops` for workstation diagnostics, `fleet-worker` for cheap parallel worker delegation)
 - **13 output styles** for response personality (Vesper, Spartan, Mentor, Executive, Pair, Atlas, Coach, Harbour, Meridian, Noir, Roast, Sage, Scout)
 - **13 hooks** for pre-commit linting, post-edit formatting, dangerous command warnings, uv enforcement, dependency-install + manifest-edit supply-chain advisories, hidden-Unicode scanning (session-start + pre-commit), live config-change + worktree guards, mid-session peer-writer guard + touched-files ledger, and pmail notifications - security set auto-wired via plugin hooks.json
 - **Pigeon** inter-session messaging (`pigeon send/read/reply`) - SQLite-backed pmail at `~/.claude/pmail.db`

README.md

@@ -12,13 +12,13 @@
 
 > *A comprehensive extension toolkit that transforms Claude Code into a specialized development powerhouse.*
 
-**claude-mods** is a production-ready plugin that extends Claude Code with 101 specialized skills, 3 expert agents, 13 output styles, 13 hooks, and modern CLI tools designed for real-world development workflows. Whether you're debugging React hooks, optimizing PostgreSQL queries, or building production CLI applications, this toolkit equips Claude with the domain expertise and procedural knowledge to work at expert level across multiple technology stacks.
+**claude-mods** is a production-ready plugin that extends Claude Code with 102 specialized skills, 3 expert agents, 13 output styles, 13 hooks, and modern CLI tools designed for real-world development workflows. Whether you're debugging React hooks, optimizing PostgreSQL queries, or building production CLI applications, this toolkit equips Claude with the domain expertise and procedural knowledge to work at expert level across multiple technology stacks.
 
 Built on the [Agent Skills specification](https://agentskills.io/specification) (an open standard backed by Anthropic, Vercel, Google, Microsoft, and 40+ agent platforms), claude-mods fills critical gaps in Claude Code's capabilities: persistent session state that survives across machines, on-demand expert knowledge for specialized domains, token-efficient modern CLI tools (10-100x faster than traditional alternatives), and proven workflow patterns for TDD, code review, and feature development. The toolkit implements Anthropic's [recommended patterns for long-running agents](https://www.anthropic.com/engineering/effective-harnesses-for-long-running-agents), ensuring your development context never vanishes when sessions end.
 
 From Python async patterns to Rust ownership models, from AWS Fargate deployments to Craft CMS development - claude-mods provides the specialized knowledge and tools that transform Claude from a general-purpose assistant into a domain expert who understands your stack, remembers your workflow, and ships production code.
 
-**3 agents. 101 skills. 13 styles. 13 hooks. 14 rules. One install.**
+**3 agents. 102 skills. 13 styles. 13 hooks. 14 rules. One install.**
 
 ## Recent Updates
 
@@ -88,7 +88,7 @@ Claude Code is powerful out of the box, but it has gaps. This toolkit fills them
 
 - **Session continuity** — Tasks vanish when sessions end. We fix that with `/save` and `/sync`, implementing Anthropic's [recommended pattern](https://www.anthropic.com/engineering/effective-harnesses-for-long-running-agents) for long-running agents.
 
-- **Expert-level knowledge on demand** — 101 on-demand skills covering React, TypeScript, Python, Go, Rust, PostgreSQL, and more, plus 3 specialized agents reserved for genuine context-isolation/worker roles (git operations, web scraping, project reorganization). Skills-first: knowledge loads when relevant instead of living in heavyweight agent prompts.
+- **Expert-level knowledge on demand** — 102 on-demand skills covering React, TypeScript, Python, Go, Rust, PostgreSQL, and more, plus 3 specialized agents reserved for genuine context-isolation/worker roles (git operations, web scraping, project reorganization). Skills-first: knowledge loads when relevant instead of living in heavyweight agent prompts.
 
 - **Modern CLI tools** — Stop using `grep`, `find`, and `cat`. Our rules automatically prefer `ripgrep`, `fd`, `eza`, and `bat` — 10-100x faster and token-efficient.
 
@@ -113,7 +113,7 @@ claude-mods/
 ├── .claude-plugin/     # Plugin metadata
 ├── agents/             # Expert subagents (3)
 ├── commands/           # Slash commands (3)
-├── skills/             # Custom skills (101)
+├── skills/             # Custom skills (102)
 ├── output-styles/      # Response personalities
 ├── hooks/              # Hook examples & docs
 ├── rules/              # Claude Code rules
@@ -296,6 +296,7 @@ See [skill-creator](skills/skill-creator/) for the complete guide.
 | [git-ops](skills/git-ops/) | Git orchestrator - commits, PRs, releases, changelog. Routes to background Sonnet agent. |
 | [github-ops](skills/github-ops/) | GitHub remote ops - repo create/metadata/topics, releases + README 'Recent Updates' enforcement, issue/PR management (preview-before-send), and read-only security-posture audit + scored repo-scorecard (single repo or whole `--org`) |
 | [push-gate](skills/push-gate/) | Pre-push safety gate - gitleaks + regex secret scan, forbidden-file check, no bypass |
+| [parallel-ops](skills/parallel-ops/) | Router for parallel/recurring agent work - decision table over fleet-ops, fleet-worker, fleetflow, loop-ops, iterate, spawn |
 | [fleet-ops](skills/fleet-ops/) | Manage a fleet of concurrent Claude sessions - landing queue with test gate, pre-land scrub (experimental) |
 | [fleet-worker](skills/fleet-worker/) | Delegate tasks to cheap headless GLM (or any Anthropic-compatible) workers - per-task git worktree + isolated config, result gating, fan-out that hands winning branches to fleet-ops landing |
 | [fleetflow](skills/fleetflow/) | Orchestrate a heterogeneous worker fleet - GLM (z.ai), Codex (OpenAI), and Anthropic Sonnet/Opus/Haiku process workers under a Fable/Opus orchestrator, porting the native Workflow tool's patterns (hash-keyed journal resume, pipeline-vs-barrier, adversarial verify, judge panels) with an escape guard baked in; ff-spawn / ff-collect / ff-doctor scripts |

docs/PLAN.md

@@ -16,7 +16,7 @@
 | Component | Count | Notes |
 |-----------|-------|-------|
 | Agents | 3 | Pure context-isolation/worker roles only: git-agent (background commits/PRs), firecrawl-expert (noisy scrapes), project-organizer (bulk restructure) |
-| Skills | 101 | Operational skills, CLI tools, workflows, diagnostics, security |
+| Skills | 102 | Operational skills, CLI tools, workflows, diagnostics, security |
 | Commands | 3 | Session management + git orchestration (sync, save, git-ops) |
 | Rules | 14 | agentic-quality, cli-tools, commit-style, dev-servers, loop-engineering, modern-tools, naming-conventions, prompt-injection, public-posts, release-review, shell-preference, skill-agent-updates, supply-chain, worktree-boundaries |
 | Output Styles | 13 | Vesper, Spartan, Mentor, Executive, Pair, Atlas, Coach, Harbour, Meridian, Noir, Roast, Sage, Scout |

skills/claude-code-ops/SKILL.md

@@ -1,13 +1,13 @@
 ---
 name: claude-code-ops
-description: "Claude Code internals - hooks, skills, subagents, headless mode, and debugging, current as of June 2026. Use for: hooks, hook events, hook not firing, PreToolUse, PostToolUse, SessionStart, Stop hook, hook script, stdin JSON contract, tool validation, audit logging, skill frontmatter, SKILL.md, skill not loading, skill not triggering, disable-model-invocation, context fork, dynamic context injection, skill description budget, headless, claude -p, CLI automation, --print, output-format, stream-json, json-schema structured output, CI/CD scripting, bare mode, background agents, debug, troubleshoot, not working, agent not found, plugin not loading, claude plugin validate, /doctor, --safe-mode, MCP server not connecting, settings precedence, extension architecture, which extension type, agent vs skill vs command vs hook, where to put a skill, extension scope, plugin design, authoring an agent, writing a skill description."
-when_to_use: "Use for questions about Claude Code itself — e.g. 'my hook isn't firing', 'why won't this skill trigger', 'run claude headless in CI', 'plugin fails to validate', 'which settings file wins', 'should this be an agent or a skill', 'how do I design this extension'."
+description: "Claude Code internals - hooks, skill frontmatter, headless mode, and extension debugging, current as of June 2026. Triggers: hooks, hook events, hook not firing, PreToolUse/PostToolUse/SessionStart, skill frontmatter, SKILL.md, skill not triggering, headless, claude -p, CI/CD scripting, plugin validate, MCP server not connecting, agent vs skill vs command vs hook."
+when_to_use: "Use for questions about Claude Code itself - e.g. my hook is not firing, why won't this skill trigger, run claude headless in CI, plugin fails to validate, should this be an agent or a skill."
 license: MIT
 compatibility: "Claude Code CLI v2.1.x (June 2026 docs)"
 allowed-tools: "Bash Read Grep"
 metadata:
   author: claude-mods
-  related-skills: "mcp-ops, setperms"
+  related-skills: "mcp-ops, setperms, parallel-ops"
 ---
 
 # Claude Code Internals

skills/fleet-ops/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: fleet-ops
-description: "Landing discipline for parallel work. Native primitives (agent teams, background agents, worktree isolation) spawn and run parallel sessions — fleet-ops governs how their branches LAND: a sequential landing queue with test gate, pre-land scrub, auto-rebase of remaining lanes, fleet status across worktrees, one-shot revert. Triggers on: landing queue, land branches, merge queue, test gate, parallel work landing, integrate worktrees, land parallel branches, merge multiple branches, branch queue, land agent team work, land background agent branches, fleet status, sequential merge."
+description: "Landing discipline for parallel work: sequential test-gated landing queue, pre-land scrub, auto-rebase of in-flight lanes, fleet status, one-shot revert. Native primitives spawn; fleet-ops lands. Triggers: landing queue, land branches, merge queue, test gate, fleet status, land agent-team/background-agent branches, sequential merge."
 license: MIT
 allowed-tools: "Read Bash Glob Grep AskUserQuestion"
 metadata:

skills/fleet-worker/SKILL.md

@@ -1,7 +1,6 @@
 ---
 name: fleet-worker
-description: "Delegate tool-using, multi-step agent tasks to a cheaper headless Claude Code worker on a cheaper model — Anthropic Sonnet/Haiku or a non-Anthropic endpoint (GLM via z.ai by default) — a 'grunt worker' an Opus orchestrator fans out in parallel and verifies. Each worker is a real `claude -p` carrying Claude Code's full tool harness (Read/Write/Edit/Bash/Glob/Grep/Task) but a cheaper brain, isolated in its own git worktree + CLAUDE_CONFIG_DIR. Pairs with fleet-ops for test-gated landing. Triggers on: fleet-worker, delegate to GLM, spin up a GLM worker, cheap parallel agent, grunt worker, offload to glm, headless GLM, z.ai worker, GLM-5.2 worker, sonnet worker, haiku worker, cheap coding agent, fan out workers, non-Anthropic model in Claude Code, ANTHROPIC_BASE_URL worker."
-when_to_use: "Use when you have independent, well-scoped, tool-using subtasks (refactors, test-writing, doc edits, mechanical multi-file changes) that don't need Opus-level judgment, and you want them done cheaply in parallel while the orchestrator reviews and gates the results before they land. Not for tasks needing the orchestrator's conversation context or expensive-if-wrong unreviewed changes."
+description: "One cheap headless Claude Code worker on a cheaper brain (GLM via z.ai, or Sonnet/Haiku) - full tool harness, isolated git worktree + CLAUDE_CONFIG_DIR - fanned out and gated by an Opus orchestrator. Triggers: fleet-worker, GLM worker, grunt worker, cheap parallel agent, offload to GLM, sonnet worker, haiku worker."
 license: MIT
 allowed-tools: "Read Bash Glob Grep AskUserQuestion"
 metadata:

skills/fleetflow/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: fleetflow
-description: "Orchestrate a heterogeneous worker fleet — GLM (z.ai), Codex (OpenAI), and Anthropic Sonnet/Opus/Haiku — from one Claude session, porting the native Workflow tool's proven patterns (phases, pipeline-vs-barrier, adversarial verify, judge panels, hash-keyed journal resume) to OS-process workers that can run DIFFERENT provider brains. Triggers on: fleetflow, heterogeneous fleet, mixed-model fleet, codex worker, orchestrate glm and codex, cross-provider fan-out, multi-provider workers, workflow across providers, codex second opinion, fable orchestrator, mixed fleet, cross-model verify."
-when_to_use: "Use when a fan-out wants DIFFERENT brains per work class — e.g. 'fan this backlog out to GLM and Codex workers', 'mixed fleet with cross-model adversarial verify', 'Codex second opinion on each lane'. Same-provider in-process fan-out → native Workflow tool; one cheap worker → fleet-worker; landing branches → fleet-ops."
+description: "Heterogeneous cross-provider fleet - GLM (z.ai), Codex (OpenAI), Anthropic Sonnet/Opus/Haiku - from one session, porting the native Workflow tool's patterns (adversarial verify, judge panels, journal resume) to OS-process workers. Triggers: fleetflow, heterogeneous/mixed-model fleet, codex worker, cross-provider fan-out, cross-model verify."
+when_to_use: "Use when a fan-out wants DIFFERENT brains per work class - e.g. 'fan this backlog out to GLM and Codex workers', 'mixed fleet with cross-model adversarial verify', 'Codex second opinion on each lane'."
 license: MIT
 allowed-tools: "Read Write Edit Bash Glob Grep Task"
 metadata:

skills/iterate/SKILL.md

@@ -1,7 +1,6 @@
 ---
 name: iterate
-description: "Autonomous improvement loop - modify, measure, keep or discard, repeat. Inspired by Karpathy's autoresearch. Triggers on: iterate, improve autonomously, run overnight, keep improving, autoresearch, improvement loop, iterate until done, autonomous iteration, batch experiments."
-when_to_use: "Use when the user wants an autonomous improvement loop against one mechanical metric — e.g. 'iterate until coverage hits 90%', 'run overnight reducing bundle size', 'keep improving X until Y'."
+description: "Autonomous single-metric improvement loop - modify, measure, keep or discard, repeat (Karpathy autoresearch). One session, git as memory, bisect-on-regression. Triggers: iterate, improve autonomously, run overnight, keep improving, improvement loop, iterate until done."
 argument-hint: "[goal] [inline config: Scope/Verify/Direction/Guard/Batch/Iterations/Until/Stagnation/Branch]"
 effort: high
 license: MIT

skills/loop-ops/SKILL.md

@@ -1,7 +1,6 @@
 ---
 name: loop-ops
-description: "Design, scaffold, and safely run OUTER loops — scheduled discover→triage→implement→verify→escalate-or-land agent loops, the orchestration layer above a single run. Risk-tier ladder (L1 report → L2 assisted → L3 unattended) mapped onto Claude Code's permission model, a persistent STATE/run-log/budget spine, a production pattern catalog, multi-loop coordination, and a kill switch. Composes iterate (inner loop), fleet-worker (spawn), fleet-ops (land), and native /loop + /schedule. Triggers on: loop engineering, outer loop, loop design, design a loop, scheduled agent, autonomous loop, background agent loop, PR watch, CI watch, dependency bump, changelog gen, issue sort, daily scan, metric chase, regression watch, digest loop, backfill, monitor loop, freshness check, event-driven loop, channel webhook, loop check, loop estimate, loop readiness, ralph loop, agent harness, escalation gate, risk tier, kill switch, run it overnight on a schedule."
-when_to_use: "Use when designing or running a recurring/scheduled agent loop rather than a one-shot task — e.g. 'set up a loop that triages PRs every 10 minutes', 'design an autonomous CI-failure recovery loop', 'how risky is this loop / is it ready to run unattended', 'estimate what this loop costs per month', 'build a loop-engineering setup'. For a single-session improvement loop against one metric, use iterate instead."
+description: "Design and safely run OUTER loops - scheduled discover-triage-implement-verify-escalate agent loops. Risk-tier ladder (L1 report -> L3 unattended), STATE/run-log/budget spine, kill switch, pattern catalog. Triggers: outer loop, scheduled/autonomous agent loop, PR watch, CI watch, dep-bump loop, run on a schedule, kill switch, risk tier."
 license: MIT
 allowed-tools: "Read Write Edit Bash Glob Grep"
 metadata:

skills/parallel-ops/SKILL.md

@@ -0,0 +1,64 @@
+---
+name: parallel-ops
+description: "Router for parallel or recurring agent work across six skills. Covers: parallel agents, fan out work, delegate to workers, run overnight, scheduled loop, land branches, mixed-model fleet, orchestrate workers, background agents at scale. Triggers on: which skill for parallel work, fan out agents, spawn workers, run this overnight, schedule a loop, land my branches, heterogeneous fleet, delegate to cheaper model, autonomous loop."
+when_to_use: "Use first when parallel or recurring agent work is needed but the right skill among fleet-ops, fleet-worker, fleetflow, loop-ops, iterate, spawn is unclear - e.g. run several agents at once, set up something that runs overnight, delegate this cheaply."
+license: MIT
+allowed-tools: "Read"
+metadata:
+  author: claude-mods
+  related-skills: "fleet-ops, fleet-worker, fleetflow, loop-ops, iterate, spawn"
+---
+
+# Parallel Ops — router
+
+You have parallel or recurring agent work and don't know which skill owns it.
+Six skills orbit this space and their names alone don't disambiguate. This
+router owns cross-family discovery; read the table, jump to the one skill
+you need, and stop reading here.
+
+## The decision table
+
+| You want | Go to | Not this, because |
+|---|---|---|
+| One-off parallel subtasks, same provider, this session | native Workflow tool / `Agent` subagents (`isolation: worktree`) | not a fleet skill at all — no dedicated skill needed |
+| Cheap delegation — a few well-scoped tool-using subtasks on a cheaper brain | [fleet-worker](../fleet-worker/) | [fleetflow](../fleetflow/) is overkill for one brain |
+| Brains differ by work class, or you need cross-provider dissent in verify | [fleetflow](../fleetflow/) | [fleet-worker](../fleet-worker/) is same-provider only |
+| Recurring / scheduled / unattended loop | [loop-ops](../loop-ops/) | [iterate](../iterate/) is one session, not scheduled |
+| Drive ONE mechanical metric to a target, in one session | [iterate](../iterate/) | [loop-ops](../loop-ops/) is the scheduler *around* this |
+| Land/merge branches that parallel work produced | [fleet-ops](../fleet-ops/) | always the terminus — every row above ends here |
+| Author a static expert-agent prompt FILE (not a runtime worker) | [spawn](../spawn/) | listed only to catch the name collision with "spawn workers" |
+
+## Two axes that confuse cold agents
+
+**Spawn vs. land.** fleet-worker and fleetflow *spawn* workers and produce
+branches; fleet-ops *lands* those branches through a test-gated queue.
+Every fleet lane ends at fleet-ops regardless of how it was spawned —
+agent team, background agent, `claude -p` worker, or human.
+
+**Inner loop vs. outer loop.** iterate is the *inner* loop: one session,
+one metric, git as memory, runs until a stop condition. loop-ops is the
+*outer* loop: the scheduler and risk-tier discipline that decides when
+and whether to fire a run (inner loop or otherwise) unattended.
+
+## Composition chain
+
+```
+iterate (inner loop)  →  loop-ops (outer loop / scheduler)
+                              ↓
+        fleet-worker / fleetflow (spawn workers)
+                              ↓
+                fleet-ops (land branches)
+```
+
+Not every task uses the whole chain — most use exactly one link. Read the
+table above first; only compose when the task genuinely spans spawn +
+land or inner + outer.
+
+## See also
+
+- [fleet-ops](../fleet-ops/) — landing discipline: test-gated queue, pre-land scrub, auto-rebase, revert
+- [fleet-worker](../fleet-worker/) — one cheap headless worker (GLM, Sonnet, Haiku) fanned out and gated
+- [fleetflow](../fleetflow/) — heterogeneous cross-provider fleet (GLM + Codex + Anthropic)
+- [loop-ops](../loop-ops/) — outer-loop design: risk tiers, kill switch, scheduling
+- [iterate](../iterate/) — autonomous single-metric improvement loop
+- [spawn](../spawn/) — generates expert-agent prompt files (authoring, not runtime)

skills/spawn/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: spawn
-description: "Generate PhD-level expert agent prompts for Claude Code. Creates comprehensive 500-1000 line agents with detailed patterns, code examples, and best practices. Triggers on: spawn agent, create agent, generate expert, new agent, agent genesis."
+description: "Generate PhD-level expert-agent prompt files (.md) for Claude Code - authoring, not runtime. For spawning parallel RUNTIME workers use fleet-worker/fleetflow (via parallel-ops). Triggers: spawn agent, create agent file, generate expert prompt, new agent persona."
 license: MIT
 compatibility: "Requires internet access for WebSearch/WebFetch to research official docs."
 allowed-tools: "Read Write Bash WebSearch WebFetch AskUserQuestion"