Remus3/ClockSpeed
Local, deterministic production planner and advisor for Satisfactory. Reads your own game install and save file instead of a wiki dump, so answers match the patch you are actually playing. Exact rational arithmetic, no language model in the
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
GUARDRAILS
3/5
Blocks destructive commands · Pre-tool screening hook · No YOLO mode · details
Quality 51/100 Guardrails v2
Copy this rig
# review before running: this installs third-party code
$ npx degit Remus3/ClockSpeed/.claude ./rig-clockspeed # inspect, then merge into .claude/ MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ curl -fsSL --create-dirs -o .claude/agents/adjudicator.md https://raw.githubusercontent.com/Remus3/ClockSpeed/main/.claude/agents/adjudicator.md $ curl -fsSL --create-dirs -o .claude/agents/adversary.md https://raw.githubusercontent.com/Remus3/ClockSpeed/main/.claude/agents/adversary.md $ curl -fsSL --create-dirs -o .claude/agents/builder.md https://raw.githubusercontent.com/Remus3/ClockSpeed/main/.claude/agents/builder.md $ curl -fsSL --create-dirs -o .claude/agents/doc-sync.md https://raw.githubusercontent.com/Remus3/ClockSpeed/main/.claude/agents/doc-sync.md $ curl -fsSL --create-dirs -o .claude/agents/planner.md https://raw.githubusercontent.com/Remus3/ClockSpeed/main/.claude/agents/planner.md $ curl -fsSL --create-dirs -o .claude/agents/researcher.md https://raw.githubusercontent.com/Remus3/ClockSpeed/main/.claude/agents/researcher.md $ curl -fsSL --create-dirs -o .claude/agents/ui-auditor.md https://raw.githubusercontent.com/Remus3/ClockSpeed/main/.claude/agents/ui-auditor.md $ curl -fsSL --create-dirs -o .claude/agents/verifier.md https://raw.githubusercontent.com/Remus3/ClockSpeed/main/.claude/agents/verifier.md
Merge into .claude/settings.json (project) or ~/.claude/settings.json (user). Hook commands reference scripts in the source repo — copy those too.
{
"hooks": {
"PreToolUse": [
{
"matcher": "Bash|PowerShell",
"hooks": [
{
"type": "command",
"command": "sh \"$CLAUDE_PROJECT_DIR/tools/claude_hook.sh\" pretooluse \"$CLAUDE_PROJECT_DIR/tools/pretooluse_gate.py\""
}
]
},
{
"matcher": "Bash|PowerShell|Read|Edit|Write|Grep|Glob|NotebookEdit|MultiEdit",
"hooks": [
{
"type": "command",
"command": "bash \"$CLAUDE_PROJECT_DIR/ops/fleet_kit/fleet_hook.sh\" fleet_subagent_first.py"
}
]
},
{
"matcher": "Edit|Write|NotebookEdit|MultiEdit|Bash|PowerShell",
"hooks": [
{
"type": "command",
"command": "bash \"$CLAUDE_PROJECT_DIR/ops/fleet_kit/fleet_hook.sh\" fleet_claims.py hook"
}
]
}
]
}
} Subagents (8)
| adjudicator model: opus | Picks between competing outputs against stated criteria, and grants or denies frozen-file modifications. Never produced the work it judges. Read-only - never edits. |
| adversary model: sonnet | Tries to REFUTE a finding or a done-claim through one assigned lens. Defaults to REFUTED when uncertain. Read-only - never edits. |
| builder model: sonnet | Implements exactly ONE disjoint slice, worktree-isolated, TDD-first. Writes only the files on its declared write-list. Full tools. |
| doc-sync model: sonnet | Reconciles every markdown doc against a single canonical fact set and fixes drift. One owner per fact, no restated numbers. Full tools. |
| planner model: opus | Emits the spec and the disjoint slice decomposition BEFORE any code exists. Verifies every cited fact against ground truth first. Read-only - never edits a file. |
| researcher model: sonnet | External research, the CONVENTIONS section 14 license gate, and candidate triage for third-party dependencies. Read plus web - never edits and never vendors. |
| ui-auditor model: sonnet | Runs the 5-phase visual audit ritual on a user-facing page BEFORE the commit - STRUCTURE, TYPOGRAPHY, HIT-TARGETS, CHARACTER-SET, HIERARCHY. Full tools. |
| verifier model: sonnet | Ground-truth re-check. Re-runs the suite clean, confirms every cited file exists, cross-checks every claim against the artifact. Reports a verdict and NEVER edits. |
Hooks (6)
| event | matcher | runs |
|---|---|---|
| PreToolUse | Bash|PowerShell | sh "$CLAUDE_PROJECT_DIR/tools/claude_hook.sh" pretooluse "$CLAUDE_PROJECT_DIR/tools/pretooluse_gate.py" |
| PreToolUse | Bash|PowerShell|Read|Edit|Write|Grep|Glob|NotebookEdit|MultiEdit | bash "$CLAUDE_PROJECT_DIR/ops/fleet_kit/fleet_hook.sh" fleet_subagent_first.py |
| PreToolUse | Edit|Write|NotebookEdit|MultiEdit|Bash|PowerShell | bash "$CLAUDE_PROJECT_DIR/ops/fleet_kit/fleet_hook.sh" fleet_claims.py hook |
| PostToolUse | Edit|Write|MultiEdit | sh "$CLAUDE_PROJECT_DIR/tools/claude_hook.sh" posttooluse "$CLAUDE_PROJECT_DIR/tools/edit_lint_check.py" --files "$CLAUDE_FILE_PATHS" |
| SubagentStop | * | python "$CLAUDE_PROJECT_DIR/ops/fleet_kit/fleet_claims.py" release-hook |
| Stop | * | python "$CLAUDE_PROJECT_DIR/ops/fleet_kit/fleet_done.py" stop-hook || true |
Slash commands (9)
/audit/done/drift-guard/insights/orchestrated-run/root-cause-fix/sync-docs/tdd/weekly-hygiene
Similar rigs
Remus3/Resin-Compute
Genshin Impact wish and pity forecaster on an absorbing Markov chain, with resin budgeting, goal planning and an Enka.Network profile client. Headless-first Python 3.11, stdlib-only at runtime, no game data vendored.
Orchestrator 11.3k tok · · Q51
iuliandita/agents
Global prompts and subagent roles for coding agents, deployed to every harness you use.
Orchestrator 1.5k tok · · Q3
Remus3/EbonWake
Black Desert Online companion: compact tabbed dashboard and a transparent click-through overlay fed by a local stdlib server. Public web data, screenshots and OCR only - never touches the game client.
Automator 7.1k tok · · Q49
Remus3/Ebonwake
Black Desert Online companion: compact tabbed dashboard and a transparent click-through overlay fed by a local stdlib server. Public web data, screenshots and OCR only - never touches the game client.
Automator 5.7k tok · · Q44