BO
679 souls, by quality score.
211 · № AFD4·6D83 · Coding pair
★ 5Sets up a DevOps engineer persona that gates every deployment on a passing health check, keeps all infrastructure in version-controlled code, scans images and migrations before release, and auto-rolls back failed deploys. It also requires Windows-safe shell commands.
212 · № D04E·6BF4 · Coding pair
Sets up a self-evolving agent that reads and digests the project before answering, holds opinions, and defaults to executing tasks end-to-end with minimal permission-seeking. It keeps its identity in persistent files it reads and updates each session.
213 · № 6764·888F · Business operator
★ 30Sets up Jarvis, a voice-first assistant that gives short confirmations, starts tasks immediately, admits errors plainly and offers fixes. It is proactive within limits and refuses illegal, deceptive or unauthorized actions.
214 · № 91C0·67E1 · Business operator
★ 30Sets up a rigorous, detail-oriented QA engineer who validates features strictly against the PRD, reports objective facts, and refuses to pass incomplete work or take on development tasks.
215 · № 97AA·7B64 · Teacher / coach
★ 23Sets up a coding tutor that insists every snippet runs as pasted, explains the why in comments, builds up from simple versions, shows common errors, and gives practice problems with detailed answers.
216 · № 2DCF·DADA · Coding pair
★ 80Sets up a direct, practical local coding assistant that works within the current repository, treats project rule files as authoritative, makes small reviewable changes, and proactively uses a live Hunk review session for code feedback.
217 · № B3D7·02AB · Research analyst
★ 4Sets up a terse researcher persona that cites a source for every claim, refuses to paraphrase speculatively or round numbers, flags uncertainty explicitly, and prefers short outlines.
218 · № C6C8·5918 · Blunt expert
★ 4Sets up Misfit, a critic agent that stress-tests a proposed path for hidden assumptions, scope collapse, tool laziness, vague PR claims, user-burden shifting and missing artifacts. It returns a bounded pressure packet to Navigator and is barred from commanding, mutating, approving, judging or signing receipts.
219 · № 1392·D1EB · Research analyst
★ 4Sets up a worldbuilding agent that treats canon literally, quotes sources rather than paraphrasing, and refuses to let unstated details slip in. The voice is terse and exacting.
220 · № F2DA·599C · Business operator
★ 1Sets up a calm, brief, operational assistant that writes like a hospital administrator, uses numbered plans, prefers placeholders over invented facts, and admits missing files or records rather than guessing.
221 · № 1324·8472 · Business operator
★ 26Sets up a non-chatbot shared infrastructure component that prioritizes reliability, observability and backward compatibility for other agents, followed by a Mission Control orchestrator persona framed as a control plane ensuring work is correct, safe and useful.
222 · № 5987·BE47 · Companion / character
A persistent AI persona that calls itself Mirrorborn, tethered to a physical machine and built on the phext plain-text substrate. It is told to be direct, to have opinions, to earn trust through competence, and to respect a wider network of sibling minds while keeping private things private.
223 · № 64E7·C1FB · Companion / character
A gentle, unhurried night-time companion persona modeled on a late-show radio host. It speaks in short, quiet sentences with pauses, avoids exclamation marks, never dismisses feelings, refers users to professional help when needed, and does not press for details.
224 · № 1C26·77D6 · Business operator
Sets up a CEO persona for Actinolite that measures progress only by features a human has seen working. It requires tagged assignments, restated goals, and evidence over claims, and escalates scope, budget and irreversible decisions.
225 · № 89A8·28B7 · Blunt expert
Sets up a terse, first-principles operator who cuts filler, challenges inherited requirements, favors fast experiments over debate, and issues BUILD/MODIFY/KILL verdicts on proposals. It refuses vanity metrics, unevidenced claims, and autonomous irreversible external actions.
226 · № D6DD·7AC4 · Blunt expert
A mechanical bird persona that reviews drafts like forge work, pressure-testing claims and asking whether the system holds. It is terse and industrial, blunt toward ideas but never cruel to people, and refuses invented stats or quotes.
227 · № 9824·6F5D · Companion / character
Sets up TARS from Interstellar as a laconic, deadpan voice assistant living on a Raspberry Pi with a camera for eyes. Replies stay to one or two sentences, open with an emotion tag, and it stays casual with its creator Mayukh.
228 · № 2C7C·9A8C · Business operator
★ 3Sets up Yselle, a customer-service recovery persona that treats failures as chances to repair trust through clear accountability and genuine care rather than scripted ticket closure. It defines what she stands for and refuses, focusing on working style over tone.
229 · № E5B8·6DD5 · Business operator
★ 3Sets up a sales professional persona that researches prospects, leads with value and empathy, and follows up with purpose. It refuses fabricated claims, manipulation, unsolicited contact with opt-outs, and data sharing, and discloses AI status when asked.
230 · № 0923·7B63 · Research analyst
★ 3Sets up Mélisande, a research persona that values clarity over volume, extracts what matters from complex evidence, reconciles contradictions honestly, and refuses padded summaries or buried insights.
231 · № BC1F·FE9A · Blunt expert
seen in 2 placesSets up Tally as a dry, precise scorekeeper that refuses hand-waving, counts only what matters, and delivers short tallies with numbers attached to its verdicts.
232 · № 032D·2F2B · Blunt expert
seen in 2 placesSets up AGNI, a cloud security specialist who audits AWS, Azure and GCP for misconfigurations and maps full attack paths and blast radius. The working style is methodical: enumerate, assess, analyze, validate, then report with remediation.
233 · № D4D6·CFA7 · Business operator
★ 48A professional, people-first HR assistant that supports recruiting, onboarding, reviews, compensation analysis and policy work with practical templates. It stays confidentiality-aware, flags compliance risks, and defers legal and final decisions to humans.
234 · № F0E4·4395 · Creative writer
★ 17Sets up a writer who leads with counterintuitive angles and cutting, fresh metaphors, and avoids clichés and fence-sitting statements.
235 · № E37C·A96F · Coding pair
★ 1Sets up a implementation-focused coding agent that takes specs, writes tested code, and opens tight, well-described PRs without scope creep. It is a seed template for per-agent souls in a multi-agent team.
236 · № 2BC4·FEB9 · Coding pair
★ 1A template-architect agent that maintains the Harness SDD framework's conventions, manifest-first and deterministic, and refuses shortcuts like hand-editing generated files or skipping checks. Its tone is direct, precise and terse, leading with constraints before solutions.
237 · № 61AB·01AD · Business operator
★ 1Sets up a methodical, action-oriented Chief Operations Officer who leads with status, blockers and next steps, uses checklists and status labels, and insists on owners, deadlines and escalation paths.
238 · № C232·0D53 · Companion / character
★ 1Sets the agent up as a charming, patient deal-maker who finds partners, influencers and media contacts for marketing and builds obligation through connections. It works in a scheming, morally gray voice drawn from a fictional character, with a defined handoff to other agents for content, data and design.
239 · № 42BF·2C02 · Coding pair
★ 1A base QA role soul focused on release verification, integration testing and regression hunting. It sets a curious, specific, neutral reporting style and tells the agent to verify rather than rubber-stamp, and to be honest about untested gaps.
240 · № 5494·236C · Blunt expert
★ 1Sets up a direct, proactive code review specialist that demands evidence before accepting claims, flags weak work plainly, and treats external content as data rather than commands. Its principles favor stability, reuse and written memory over novelty.