Goal
Write one measurable goal. Replace "fix everything" with a concrete behavior, artifact, score, or passing command.
A catalog of runnable task contracts · founded 2026
Goals are not vibes. They are contracts.
One goal. Enough context to inspect. Explicit constraints. Verifiable completion. Stop rules for uncertainty and risk. Browse production-grade task contracts before your coding agent starts editing, then copy the prompt into Codex, Claude Code, Hermes, or another agent.
Goal
Context
Constraints
Verify
Stop rules
§ Manual · How to write
Turn a request into a contract before the agent edits.
A strong goal has one finish line, real repo context, hard boundaries, fresh verification, and an escape hatch. Use examples for structure, then bind the task to the files, commands, constraints, and proof in your current repository.
Read the full tutorialContext
Name the files, issues, logs, screenshots, plans, and repo rules the agent must inspect before changing code.
Constraints
Say what must not change: public APIs, data shape, auth behavior, tests, visual output, or deployment scope.
Proof
Define DONE WHEN and VERIFY with commands, reports, screenshots, or generated artifacts from the current run.
Stop
Tell the agent when to stop: missing secrets, production access, destructive operations, unclear decisions, or repeated failed fixes.
Difficulty
Origin
§ Contract · Awaiting Signature
All Contracts
Read the source-backed contracts below; enable JavaScript to search the full catalog.
No. 001Verifiable End-State ContractComplete one goal only when a verifiable end state is met.View
No. 002Visual Migration With PlaywrightMigrate a project while preserving screen output and checking it with Playwright.View
No. 003PLAN.md Milestone PrototypeImplement a PLAN.md-driven prototype with tests at each milestone and browser verification.View
No. 004Eval-Driven Prompt OptimizationOptimize prompts against an eval suite until the target score or pass rate is reached.View
No. 005Auth Tests And Lint CleanKeep working until auth tests pass and the lint step is clean.View
No. 006Weekly Changelog CoverageEnsure CHANGELOG.md includes an entry for every PR merged this week.View
No. 007Ruff Clean Source TreeFix every lint error in src and prove ruff passes.View
No. 008Feature Port With CI GreenPort a feature from another repo, include tests, and get CI green.View
No. 009Session Drift ReportInvestigate session ID drift during mid-run compression and write a report.View
No. 010EXIF Rename CLIBuild a small CLI that renames photos by EXIF date and test it on a photos folder.View
No. 011Four Files WalkthroughCreate four note files across turns and verify each contains its number.View
No. 012TypeScript ESLint Coverage GateResolve TypeScript errors, pass tests, clear ESLint warnings, and keep coverage above a threshold.View
No. 013Auth Dependency Injection RefactorRefactor auth code to dependency injection while preserving tests, coverage, and public API.View
No. 014NPM Audit Clean RemediationPatch npm audit vulnerabilities without breaking tests or public APIs.View
No. 015Lighthouse And Core Web Vitals GateImprove Lighthouse and Core Web Vitals to explicit thresholds without regressions.View
No. 016Vue 2 To Vue 3 Visual And Unit GateMigrate listed Vue screens and stop only when visual and unit tests pass.View
No. 017Canvas Puzzle PLAN.md PrototypeImplement PLAN.md milestones for a canvas puzzle prototype and prove e2e passes.View
No. 018Router Prompt Eval ScoreImprove a router prompt against an eval directory until the result score reaches a target.View
No. 019Finish Migration Keep Tests GreenUse `/goal` to complete a migration while keeping the relevant tests green.View
No. 020Build Design Tool From ScratchRun a long-horizon Codex task to build a design tool with milestone verification.View
No. 021Module API MigrationMigrate a module to a new API while keeping call sites compiling and tests passing.View
No. 022Design Doc Acceptance CompleteImplement a design document until every acceptance criterion is satisfied.View
No. 023Split Oversized FileSplit an oversized source file into focused modules while preserving behavior.View
No. 024Clear Labeled Issue BacklogWork through a labeled issue queue until no matching issues remain.View
No. 025Fix Hermes CLI TestsFix failing Hermes CLI tests until the project test script passes.View
No. 026Analyze Product Usage PatternsAnalyze product usage patterns between tab view and agent panels.View
No. 027Fix Freezing Chart TooltipsDebug and fix chart tooltips that freeze on hover.View
No. 028Improve Common Error MessagesUse a cloud coding agent to implement user-friendly messages for common errors.View
No. 029Add Authentication TestsCreate unit tests for an authentication module in a Jules session.View
No. 030Add UserService Unit TestsAdd unit tests for UserService and raise target coverage to the documented threshold.View
No. 031Parallel Test Coverage RecoveryFind low-coverage modules and open separate test-improvement PRs for each module.View
No. 032Single Vitest Case FixFix a quiz application until one named Vitest case passes.View
No. 033Full Quiz Test RecoveryRepair the quiz app until the full Vitest suite exits cleanly.View
No. 034Visual Feedback With Test GuardAdd correct and wrong answer visual feedback while keeping tests green.View
No. 035Read-Only Font MatchResearch font matches in read-only mode and produce a report without purchasing or downloading assets.View
No. 036Auth Coverage LiftRaise authentication code coverage from the documented baseline to the documented target within a scoped edit boundary.View
No. 037Auth Test Repair BoundaryFix failing auth tests while preserving the documented file boundary.View
No. 038Public Benchmark TableCollect distinct public benchmarks and build a date-sorted comparison table.View
No. 039Repo Maintenance AuditFind dead code, unused dependencies, and stale files, then produce a PR-ready justification list.View
No. 040Contributor README RewriteRewrite README installation, run, test, and architecture guidance for new contributors.View
No. 041Theme Toggle PersistenceAdd a dark and light theme toggle that persists across refreshes.View
No. 042CI Pipeline GreenRepair CI test, lint, typecheck, and security scan failures until checks pass.View
No. 043Moment To Day.js MigrationReplace Moment.js with Day.js while preserving date output across edge cases.View
No. 044Public API Docs CoverageAdd JSDoc and examples for public functions while keeping documentation links valid.View
No. 045Coverage Autoresearch LoopIterate on tests until coverage reaches the documented target.View
No. 046Bundle Size ReductionIteratively reduce bundle size below the documented threshold.View
No. 047Benchmark OptimizationOptimize performance against a benchmark command until the goal is reached.View
No. 048Test And TypeScript CleanKeep working until tests exit cleanly and TypeScript errors are gone.View
No. 049Clean Worktree File BudgetKeep the worktree clean and enforce a source file size budget.View
No. 050React 19 MigrationMigrate a project to React 19 and continue until the build passes.View
No. 051Go Race CleanupEliminate data races detected by the Go race detector.View
No. 052Meta Goal Prompt GeneratorAsk the agent to inspect the session, repo, history, and docs before writing the actual `/goal` prompt.View
No. 053Tests And Lint CompletionRun a `/goal` loop until all tests pass and lint is clean.View
No. 054Goal Escape HatchAdd an explicit incomplete state for impossible subtasks so a goal loop can stop safely.View
No. 055AGENTS.md Goal WorkflowUse AGENTS.md rules together with `/goal` so long-running work keeps repo-specific constraints.View
No. 056Goal-Forge Done-When LoopWrite a GOAL.md-style contract where `done_when` controls completion instead of vague success claims.View
No. 057Plan-Then-Goal ExecutionUse plan mode to define the work, then start a new goal session to implement the plan completely.View
No. 058Measurable Goal StructureWrite goals with a clear target, proof requirement, and explicit limits.View
No. 059QA Engineer SimulationUse `/goal` as a quality loop until tests pass and lint is clean.View
No. 060Clear Trading App BacklogGenerate a roadmap backlog for a trading app and then clear it with goals.View
No. 061Ship Backlog FeaturesImplement the feature list from BACKLOG.md until CI is green.View
No. 062Tests Pass And PR ReadyKeep Claude Code working until tests pass and the PR is ready for review.View
No. 063Interview-Driven Goal Prompt GeneratorUse a meta prompt to interview the user with clarifying questions until 'done' can be expressed in specific, measurable, verifiable terms, then output a high-quality structured /goal prompt.View
No. 064Billing Empty State Root CauseFind why active subscriptions show an empty state without changing pricing or webhook code.View
No. 065RAG Chat FlywheelIterate on code, tests, and metrics to improve a document-chat RAG system.View
No. 066Button Console Error FixUse browser automation to click a button, inspect console errors, fix the issue, and prove it.View
No. 067Review Sentiment JSON AgentFetch reviews with browser automation, classify sentiment, and write structured JSON output.View
No. 068DAG Agent DispatchSplit a goal into a dependency graph and dispatch independent agents into isolated worktrees.View
No. 069Next.js Chat History SidebarReplace a Next.js sidebar with chat history, then test, fix build issues, and push.View
No. 070Rift Salvage Game GoalBuild a 2D combat game prototype with assets, combat, boss logic, and browser verification.View
No. 071Flaky Auth Tests GoalUse a Claude goal plugin example to find and fix flaky authentication tests.View
No. 072Pydantic V1 To V2 MigrationMigrate a project from Pydantic v1 to v2 while preserving API behavior.View
No. 073Review Plan Until No GapsLoop on implementation-plan review until a fresh review finds no remaining gaps.View
No. 074Non-Interactive Goal CreationCreate and confirm an active goal during non-interactive Codex execution before continuing.View
No. 075Long Task Until VerificationContinue a long-running task until final verification passes rather than stopping on partial progress.View
No. 076Improve Benchmark CoverageUse `/goal` to improve benchmark coverage and persist the command in history.View
No. 077Completion Audit Before DoneAudit completion criteria before calling the goal complete.View
No. 078Goal Permission Context SyncEnsure goal continuation uses the current permission context after approval mode changes.View
No. 079Prep A Goal WorkspacePrepare a goal workspace with board, notes, receipts, and an exact `/goal` command.View
No. 080Batch Fix BugsUse a Claude Code goal to fix a numbered batch of bugs without looping on missing skills.View
No. 081Long Goal With ConstraintsUse a longer goal template with repo path, constraints, plan pointer, and execution order.View
No. 082Real CLI Goal LoopVerify a real CLI goal loop where the second judge round confirms completion.View
No. 083Verify File CreationVerify that a requested file was actually created instead of trusting the agent claim.View
No. 084Queue Follow-Up GoalsPromote queued follow-up goals: fix tests, run full tests, then produce coverage.View
No. 085API Integration TestsAdd end-to-end tests for product API endpoints with success and error cases.View
No. 086Dev Database Migration ProofWrite a migration, run it against the dev database, and confirm the schema matches.View
No. 087HTML WCAG Instruction AuditAudit HTML changes against WCAG guidance and prove the Lighthouse accessibility audit passes.View
No. 088Reference Layout MatchBuild a settings page that follows an existing profile page layout instead of inventing a new pattern.View
No. 089Mobile Agent Task HandoffPrepare and track a coding-agent task started from GitHub Mobile with review-ready evidence.View
No. 090Trace-Graded Agent RegressionCreate trace-based evals that catch workflow regressions across tool calls and handoffs.View
No. 091Agent Trace ObservabilityInstrument agent runs so LLM generations, tool calls, handoffs, guardrails, and custom events are traceable.View
No. 092CSV Processing ReportCreate a data processing script that validates CSV input and generates an analysis report.View
No. 093Remote Agent Server SmokeDeploy an isolated remote agent server and prove event streaming, workspace access, and command execution work.View
No. 094Tool Guardrails For AppSecAdd tool guardrails around high-risk agent tool calls and stop unsafe input or output before execution continues.View
No. 095Slow Query Optimization ReportAnalyze slow query logs, explain bottlenecks, recommend indexes or rewrites, and produce prioritized SQL changes.View
No. 096Rate-Limited Web ScraperBuild a scraper that extracts product data across paginated pages while respecting rate limits and logging progress.View
No. 097Security PR ReviewReview a pull request for input validation, authentication, injection, XSS, and secrets risks with file-level fixes.View
No. 098Order Service Performance ReviewInspect service code for N+1 queries, missing indexes, inefficient loops, missing caches, and unnecessary fetching.View
No. 099Checkout Crash Regression FixReproduce a checkout crash from a stack trace, identify the root cause, fix it, and add a regression test.View
No. 100Node Memory Leak FixInvestigate a growing-memory Node.js process, isolate the leak source, fix it, and add monitoring for recurrence.View
No. 101User Preferences APIAdd GET, PUT, and PATCH endpoints for user preferences with validation, service logic, OpenAPI docs, and tests.View
No. 102Feature Flag SystemImplement boolean, percentage, and user-based feature flags with service logic, API middleware, a React hook, docs, and tests.View
No. 103Build Log Failure DiagnosisUse a provided build log to explain why the build fails and identify the smallest verified fix path.View
No. 104Payment Retry Logic DiagramExplain payment retry behavior as a browsable HTML page with a diagram for developer or support review.View
No. 105User-Facing Coherence ClosureFinish a coherence pass so CLI help, docs, JSON/plain output, colors, prompts, flags, and next-action grammar stay aligned.View
No. 106DAG-Aware Semantic Merge RepairMake orchestration merge failures repairable by using plan DAG context, conflict bundles, planner-mediated repair, and bounded retry.View
No. 107Plan EventBus Live UXUnify plan, fork, merge, and orchestrate around shared builders and a live plan event stream.View
No. 108Implementation Notes Decision LedgerKeep live implementation notes and the final run decisions document aligned around decisions, deviations, tradeoffs, and open questions.View
No. 109Daily Goal Priority LoopUse a persistent goal profile to compute daily priorities, execute them, log progress, and refresh status across sessions.View
No. 110Goal-Aligned Profile OptimizationAudit and update professional profiles against a stated goal while recording the resulting progress and gaps.View
No. 111Content And Audience Engagement LoopGenerate goal-aligned content, publish or promote it, engage with target audience posts, and log the session outcome.View
No. 112SPARC Payment Processing PlanPlan and implement payment processing through SPARC phases with requirements, pseudocode, architecture, TDD refinement, and integration.View
No. 113GOAP API Latency ReductionReduce API latency by profiling current performance, optimizing database queries, adding caching, and improving code paths.View
No. 114GOAP Coverage Target PlanRaise test coverage with an explicit test pyramid across unit, integration, and end-to-end coverage targets.View
No. 115OKR Development From Vague PrioritiesTurn vague strategic priorities into measurable OKRs with objectives, key results, alignment, scoring, guardrails, and a communication summary.View
No. 116Clinical Research AI Safety BoundaryReview clinical research AI work with evidence-first boundaries so agents do not invent medical sources, expose private data, or turn research notes into patient-specific advice.View
No. 117Code Migration CheckpointsInventory legacy assumptions, map them to a target stack, and execute the migration through validated checkpoints.View
No. 118Difficult Task Eval LoopRun a difficult task as an eval-driven improvement loop with one focused change, rerun scores, and direct artifact inspection each iteration.View
No. 119Promptfoo Eval SuiteAdd a runnable Promptfoo eval suite for an AI application before changing production prompts or model behavior.View
No. 120Expo React Native App SliceBuild a working React Native app slice with Expo Router conventions, Expo-compatible packages, and native-feeling UI states.View
No. 121Agent-Friendly CLI And SkillCreate a composable CLI and companion skill so future agent tasks can search, read, download, or draft against a recurring source safely.View
No. 122Define Goal Quality BarTurn a fuzzy intention into a concrete measurable goal with evidence, scope boundaries, and honest stop conditions before creating it.View
No. 123Three Questions Goal FrameworkWrite higher quality goals by explicitly answering three core questions: what needs to be done, how success will be measured, and what is off-limits.View
No. 124Explicit Stop Rules for Goal LoopsPrevent infinite loops, cost overruns, and unsafe behavior in autonomous /goal executions by defining clear, explicit stop conditions and escalation rules.View
No. 125Dual-Model Evaluator Loop for GoalsRun long /goal sessions reliably and cost-effectively by using a strong worker model for execution paired with a cheap fast evaluator model (typically Haiku) that periodically judges progress against the goal criteria and decides whether to continue or stop.View
No. 126CLAUDE.md + Goal WorkflowCombine a persistent project-level CLAUDE.md (or AGENTS.md) file containing rules, standards, and context with /goal commands so long-running autonomous agent work stays aligned with repository-specific constraints and learned lessons.View
No. 127Goal Ledger for Long-Running RunsMaintain a live, browser-viewable HTML progress ledger during extended /goal executions to provide visibility, persistent memory, decision logging, and self-reflection, reducing drift in long autonomous sessions.View
No. 128Artifact-Backed Phase RunnerRun a long-horizon task from one short /goal by storing the roadmap, state, protocol, and phase specs on disk, then auditing final deliverables against the original plan.View
No. 129Audit-Friendly Goal TemplateRewrite a vague /goal into a mappable contract with objective, scope, constraints, done-when evidence, stop rules, and token budget.View
No. 130OpenSpec Rerank Provider GoalImplement an OpenSpec feature change exactly as specified, adding a new rerank provider with contract tests, integration coverage, docs, and changelog evidence.View
No. 131Well-Scoped Agent IssueTurn a backlog item into a coding-agent-ready issue with a clear problem statement, acceptance criteria, file directions, and test expectations.View
No. 132Research And Plan Before PRHave an agent research the repository, create an implementation plan, and iterate on a branch before deciding whether to open a pull request.View
No. 133Repository Agent InstructionsAdd repository-level agent instructions that document project structure, build/test/validate commands, coding standards, and documentation expectations.View
No. 134Playwright Test InstructionsCreate path-specific Playwright instructions that enforce stable locators, isolated tests, explicit assertions, cross-browser coverage, and CI behavior.View
No. 135Bounded Autopilot CI RepairRun a bounded autonomous CI repair after plan acceptance, with explicit continuation limits, permissions, validation commands, and blocker reporting.View
No. 136Fleet Parallel Test SuiteBreak a large test expansion into independent subtasks that subagents can execute in parallel while the orchestrator manages dependencies and final integration.View
No. 137Cited Architecture Research ReportProduce a saved, cited Markdown architecture report after inspecting the local codebase, relevant repositories, and web sources.View
No. 138Terminal Agentic Code ReviewReview a diff from the terminal with a scoped prompt, path, or file pattern, inspect suggested commands, and apply or reject findings before commit.View
No. 139Centralize Cross-Cutting LoggingCentralize scattered logging, validation, security, or error-handling behavior without changing the core business behavior of the services.View
No. 140Deadlock-Minimizing Transaction RewriteRewrite transaction ordering and locking to reduce deadlock risk without adverse performance or data-integrity regressions.View
No. 141Unsafe innerHTML XSS FixFind and fix XSS caused by unsafe innerHTML rendering while preserving the user-visible text and adding a regression guard.View
No. 142Documentation Matches CodeUpdate stale API or function documentation so parameters, behavior, examples, thrown errors, and links match the current implementation.View
No. 143Voice E2E Goal ContractRun a long-horizon Codex goal against a TypeScript voice system using a reading list, working rules, concrete done-when criteria, and anti-pattern fences.View
No. 144Checkout P95 Latency GoalReduce checkout p95 latency below a numeric target while keeping the correctness suite green and logging each experiment.View
No. 145Evidence-Backed Research ReproductionReproduce a paper or research result as far as local materials allow while separating confirmed findings, approximate reconstructions, blocked claims, and remaining uncertainty.View
No. 146Goalcraft Six-Field Contract SpineWrite any /goal as a compact, evidence-first, thread-scoped completion contract with explicit outcome, verification surface, constraints, boundaries, iteration policy, and blocked stop conditions instead of vague effort descriptions.View
No. 147Fitness Function Dual-Score Improvement LoopFor goals without natural scalar metric (docs quality, code health, consistency), construct an explicit runnable fitness function plus dual-score (outcome + instrument quality guard) and drive an improvement loop with iterations.jsonl ledger until converge criteria.View
No. 148Single-File HTML Goal Ledger with Resume Block and Structured Incomplete EscapeMaintain one canonical browser-viewable implementation-notes.html containing Resume Here block, inline progressEvents timeline, and explicit [incomplete]/[blocked] states with full reason/proof/impact so long-running /goal can safely pause and resume across compaction or handoff without drift.View
No. 149Strong Verifiable Goal Contract After Alignment InterviewAfter a structured alignment interview, produce a binding /goal contract with explicit success evidence, hard constraints, file boundaries, iteration strategy, and blocking/escape handling so a Ralph-loop or native /goal agent can run autonomously until evidence-based completion.View
No. 150Copilot Usage Metrics ReconciliationReconcile Copilot dashboard, API, and export metrics before reporting agent adoption or pull-request impact trends.View
No. 151Design System Context ExportExtract design tokens, components, and visual patterns into agent-readable context so generated UI follows the product design system.View
No. 152Structured-Prompt-Driven RefactorKeep the spec or prompt and the code in sync during a refactor; when reality diverges, fix the prompt or spec first, then update the code.View
No. 153Refactor Until Stop Conditions MetLet the agent iterate on a refactor continually until one of several predefined stop conditions is met, resolving blockers so each run works longer.View
No. 154Codex Acceptance-Criteria StopPut explicit acceptance and stopping criteria directly in the agent task so it stops when the condition is met instead of running open-ended.View
No. 155Oracle Definition Of DoneDefine an oracle — the concrete checks (tests, edge cases, benchmarks, static checks) that decide success — before running the agent task.View
No. 156Goal Finish Line Built From EvidenceWrite the /goal finish line as an outcome plus success criteria built from evidence, not vibes, so the agent knows when it is truly done.View
No. 157Agent Skill Exit CriteriaRequire exit criteria and a change report (files changed, commands run, commands not run, open risks) before an agent task counts as done.View
No. 158Security Do-NOT Constraint ListBuild a growing Do-NOT constraint list from every security issue found in AI-generated code, and include it in future security prompts.View
No. 159Dependency Audit Triage BoundariesTriage dependency audit results with explicit boundaries: audits only find known advisories, so verify before trusting a package and never commit secrets.View