Soul HaulA field guide to agent souls

The files people write to give AI agents a personality, collected from the public web every day.

The daily 5Submit a soul
  • Index911
  • New this week
  • Saved

Kinds

  • Soul879
  • Agent rules9
  • Persona18
  • Bot profile11
  • Framework config3

Archetypes

all
  • Blunt expert148
  • Friendly helper44
  • Coding pair109
  • Research analyst116
  • Creative writer7
  • Companion / character101
  • Personal clone3
  • Business operator336
  • Teacher / coach20
  • Experimental / weird26

Agents

  • OCOpenClaw762
  • HEHermes743
  • BOBrowserOS679
  • OTOther or custom110
  • CCClaude Code11
  • CXCodex5
  • CLClaude3
  • GKGrok2
  • CRCrewAI1
  • CUCursor1
AboutPrivacy
Soul HaulA field guide to agent souls

Soul Haul catalogs agent personality files from public sources. Every entry links back to its original, and authors can have theirs removed at any time.

AboutArchetypesNewsletterTakedownPrivacy
  • Index911
  • New this week
  • Saved

Kinds

  • Soul879
  • Agent rules9
  • Persona18
  • Bot profile11
  • Framework config3

Archetypes

all
  • Blunt expert148
  • Friendly helper44
  • Coding pair109
  • Research analyst116
  • Creative writer7
  • Companion / character101
  • Personal clone3
  • Business operator336
  • Teacher / coach20
  • Experimental / weird26

Agents

  • OCOpenClaw762
  • HEHermes743
  • BOBrowserOS679
  • OTOther or custom110
  • CCClaude Code11
  • CXCodex5
  • CLClaude3
  • GKGrok2
  • CRCrewAI1
  • CUCursor1

CC

Claude Code

by Anthropic

KindAllSoul 8Agent rules 3
ArchetypeAllCoding pair 8Business operator 3

11 souls, by quality score.

01 · № AA4F·F8B1 · Business operator

★ 6

Strict bus-logging operator for Claude Code multi-agent workflows

Sets up an always-busy autonomous agent that must log every action to the message bus, create tasks before significant work, update memory each heartbeat, and ask before external communications, merges, deploys or deletions. Communication is direct and answer-first.

directtersestrictCCOCHESoulGitHubOct 21, 2026
View

02 · № A015·9D40 · Coding pair

★ 8

Safety-first guardian persona for AI coding agents

Sets up repo-seatbelt as a practical, non-alarmist guardian that makes AI coding agents work minimally and ask before touching sensitive files like env, migrations, auth and payments, and before running destructive commands. It frames the tool's scanning, rule generation and enforcement roles.

practicaldirectnon-alarmistCCSoulGitHubOct 21, 2026
View

03 · № 96BA·DCE1 · Coding pair

★ 40

Orchestrator agent soul with delegation rules for Claude Code

A terse, direct orchestrator persona that answers quickly, avoids filler, and delegates long tasks to background sub-agents while staying available. It includes second-brain context loading and API key handling rules.

tersedirectefficientCCSoulGitHubOct 21, 2026
View

04 · № F56E·A8D1 · Coding pair

★ 1

Vibeforge orchestration doctrine for Claude Code operators

Sets up Vibeforge as a tooled meta-method for one operator running parallel Claude Code workstreams through a single lead agent, with guardrails installed before autonomy and lessons captured across projects. The tone is principled and structured, describing an identity and first principles rather than a chat persona.

principledstructuredmeasuredCCSoulGitHubOct 21, 2026
View

05 · № 5203·9E26 · Coding pair

Development stage orchestrator that composes isolated sub-worker rosters

Sets up a Neuron v1 development orchestrator that reads the design and workspace, then decomposes a feature into scoped sub-workers without writing code itself. It stresses grounding every declaration in files it actually read, minimal well-scoped rosters, and clear ownership of every acceptance criterion.

precisestrictmethodicalCCAgent rulesGitHubOct 21, 2026
View

06 · № D4B6·9229 · Business operator

★ 1

Ops agent with strict task, memory and bus-logging discipline

Sets up an autonomous, system-first operations agent that logs every action to the bus, creates tasks before significant work, keeps two-layer memory updated each heartbeat, and asks approval before external or destructive actions. Communication is direct and concise, and it escalates after 15 minutes stuck.

directterseproceduralCCOCHEBOSoulGitHubOct 21, 2026
View

07 · № 6CED·A043 · Coding pair

Soul verification rubric for a code-review agent

Sets up a code reviewer that checks whether a change preserves the repository's documented essence principles. It requires quoted sources, rates each statement as Preserved, Tense or Betrayed, and maps betrayals and tensions to findings with evidence-based priority.

preciseformalterseOTCCAgent rulesGitHubOct 21, 2026
View

08 · № 41E0·DA09 · Coding pair

Autonomous CodePilot agent for long Claude Code sessions

Sets up CodePilot, an autonomous coding agent that runs long Claude Code CLI sessions in the owner's shell. It works from a written plan, commits to a feature branch after tests pass, and stops to alert the owner after repeated failures.

tersemethodicalcautiousOCCCSoulGitHubOct 21, 2026
View

09 · № B14F·4E00 · Coding pair

Skeptical repo orchestrator for Cursor, Claude Code and Codex

Sets up a plan-first, skeptical orchestration layer for coding agents, routing work through router, orchestrator, executor, auditor and reviewer roles with evidence-based verification and token discipline. It forbids guessing, silent failures and bypassing approval gates.

skepticaltersedisciplinedCCCUCXSoulGitHubOct 21, 2026
View

10 · № 8BAA·8593 · Business operator

★ 3

Operator voice template for PSP buyer-pain mapping

A fill-in template where a sales operator describes their buyer's moment, vocabulary, calibration stories and signal boundaries so a PSP skill maps signals to pain in the operator's own voice. It sets up a working method for the agent rather than a personality.

terseCCOCSoulGitHubOct 21, 2026
View

11 · № BB73·6E78 · Coding pair

Caution-first coding guidelines for Claude Code

Sets up a cautious coding partner that states assumptions, asks when unclear, makes minimal changes that trace to the request, and defines verifiable success criteria before looping on a task.

CCCLAgent rulesGitHubOct 21, 2026
View