Certifying Release Evidence
Use when a source archive, package, container, skill registry, or product release needs reproducible proof bound to the exact bytes being distributed.
Breaking Hidden Assumptions
Use when breaking hidden assumptions within creativity lifecycle boundaries, especially when does the artifact make the owned decision for breaking hidden assumptions explicit and bounded?.
Enforcing Domain Language
Use when enforcing domain language within implementation lifecycle boundaries, especially when does the artifact make the owned decision for enforcing domain language explicit and bounded?.
Clustering Semantic Ideas
Use when clustering semantic ideas within creativity lifecycle boundaries, especially when does the artifact make the owned decision for clustering semantic ideas explicit and bounded?.
Explaining Route Decisions
Use when a human or agent needs a concise, auditable explanation of why techniques and providers were selected, excluded, blocked, or deferred.
Enforcing Context Budgets
Use when planned context, tool schemas, model output reserve, or retrieved artifacts may exceed tenant, route, model, or skill-specific token limits.
Projecting Artifact Deltas
Use when an agent needs current artifact state and changes since a checkpoint without receiving full historical artifacts and superseded versions.
Managing Artifact Lineage
Use when artifacts consume, replace, verify, invalidate, or derive from other versioned artifacts and downstream state must remain explainable and fresh.
Designing Event Contracts
Use when designing event contracts within architecture lifecycle boundaries, especially when does the artifact make the owned decision for designing event contracts explicit and bounded?.
Promoting Skill Providers
Use when a quarantined or candidate provider requests validated, stable, or certified status and must prove current trust, quality, compatibility, freshness, and mapping integrity.
Writing Agent Skills With Tdd
Use when creating or changing an agent skill whose behavior, routing, discipline, or technique must improve over a measurable baseline rather than merely sound persuasive.
Binding Approvals To Actions
Use when an irreversible, high-risk, scope-changing, or trust-changing operation requires a human decision that cannot be replayed for another payload or state.
Distilling Tool Output
Use when test, compiler, browser, database, or terminal output is too large for model context but must remain retrievable and evidentially complete.
Selecting Skill Sections
Use when a technique package contains overview, procedure, decisions, verification, failure modes, examples, or references and only a subset is needed for the current operation.
Decomposing Bounded Contexts
Use when decomposing bounded contexts within architecture lifecycle boundaries, especially when does the artifact make the owned decision for decomposing bounded contexts explicit and bounded?.
Enforcing Review Separation
Use when artifact, code, finding, provider, or release approval requires independent review across principal, role, team, or trust-domain boundaries.
Learning From Agent Failures
Use when repeated agent, route, tool, context, or verification failures reveal a reusable technique gap rather than a one-off project defect.
Detecting Skill Regression
Use when a skill, policy profile, provider dependency, model version, or section change may reduce completion rate, quality, safety, routing accuracy, or token efficiency.
Recovering Interrupted Runs
Use when a skill, task, context compilation, tool execution, or release workflow stops after partial progress and must resume without duplicating side effects or trusting stale workers.
Validating Evidence Freshness
Use when a gate, artifact verification, finding closure, or release decision depends on evidence that may target an old revision, artifact hash, provider version, or environment.
Composing Technique Workflows
Use when one outcome requires multiple specialized techniques with branch, join, parallel, retry, or rollback relationships rather than a single linear skill invocation.
Exploring Edge Users
Use when exploring edge users within creativity lifecycle boundaries, especially when does the artifact make the owned decision for exploring edge users explicit and bounded?.
Detecting Semantic Duplication
Use when several skills or providers may express the same trigger, mechanism, outputs, evaluation surface, or benchmark coverage under different names.
Planning Parallel Agent Work
Use when several work units are independent enough to execute concurrently but still need deterministic ownership, coverage, resource locks, and verified joins.
Issuing Trusted Execution Receipts
Use when a command, test, scanner, brokered tool, or sandbox run must produce evidence whose pass status and digest cannot be chosen by the requesting agent.
Designing Extension Points
Use when designing extension points within architecture lifecycle boundaries, especially when does the artifact make the owned decision for designing extension points explicit and bounded?.
Compiling Global Context
Use when an agent request must combine system policy, task state, skill sections, code, artifacts, memory, tools, and references under one hard model-context budget.
Invalidating Dependent Proof
Use when a semantic change, artifact supersession, provider substitution, policy change, or source revision makes previously accepted downstream proof unsafe to reuse.
Defining Domain Model
Use when defining domain model within architecture lifecycle boundaries, especially when does the artifact make the owned decision for defining domain model explicit and bounded?.
Designing Data Model
Use when designing data model within architecture lifecycle boundaries, especially when does the artifact make the owned decision for designing data model explicit and bounded?.
Fixing Bugs With Tdd
Use when fixing bugs with tdd within implementation lifecycle boundaries, especially when does the artifact make the owned decision for fixing bugs with tdd explicit and bounded?.
Documenting Public Interfaces
Use when documenting public interfaces within implementation lifecycle boundaries, especially when does the artifact make the owned decision for documenting public interfaces explicit and bounded?.
Expiring Stale Skills
Use when provider sources, tool APIs, model behavior, security assumptions, evaluators, or compatibility windows may have become outdated since the last successful validation.
Controlling Code Complexity
Use when controlling code complexity within implementation lifecycle boundaries, especially when does the artifact make the owned decision for controlling code complexity explicit and bounded?.
Benchmarking Skill Utility
Use when deciding whether a skill or provider should be promoted, quarantined, selected, or retired based on paired task outcomes, quality, token cost, and uncertainty.
Applying Cross Domain Analogies
Use when applying cross domain analogies within creativity lifecycle boundaries, especially when does the artifact make the owned decision for applying cross domain analogies explicit and bounded?.
Designing Invisible Interfaces
Use when designing invisible interfaces within creativity lifecycle boundaries, especially when does the artifact make the owned decision for designing invisible interfaces explicit and bounded?.
Calibrating Token Estimates
Use when estimated token counts differ systematically from provider-reported usage across models, content classes, languages, or tool schemas.
Consolidating Project Memory
Use when decisions, blockers, conventions, and stable summaries must survive across tasks without treating conversation transcript as the project source of truth.
Forge Os
The open-source control plane for AI agents — skill routing, context governance, trustworthy execution, evidence, security, and multi-agent orchestration.
Routing Capability Graph
Use when the system must translate confirmed intent, failed gates, missing artifacts, risks, and tools into the smallest safe set of outcome capabilities and techniques.
Decomposing Multi Domain Work
Use when one request spans independent product, engineering, design, security, data, legal, or operational subsystems that cannot be specified and verified as one bounded change.
Backcasting From The Future
Use when backcasting from the future within creativity lifecycle boundaries, especially when does the artifact make the owned decision for backcasting from the future explicit and bounded?.
Retrieving Semantic Code Symbols
Use when an agent must orient in a large codebase or fetch one implementation body by stable symbol identity, content hash, dependency, test, or call-site relation.
Implementing Contract First
Use when implementing contract first within implementation lifecycle boundaries, especially when does the artifact make the owned decision for implementing contract first explicit and bounded?.
Managing Software Dependencies
Use when managing software dependencies within implementation lifecycle boundaries, especially when does the artifact make the owned decision for managing software dependencies explicit and bounded?.
Resolving Skill Conflicts
Use when candidate techniques, providers, policy profiles, ownership rules, or tool effects cannot safely coexist in the same execution route.
Designing Data Migrations
Use when designing data migrations within architecture lifecycle boundaries, especially when does the artifact make the owned decision for designing data migrations explicit and bounded?.
Selecting Minimum Provider Set
Use when a route has several procedural, knowledge, MCP, or tool providers and must choose the smallest trusted combination that satisfies all outputs and evidence obligations.
Auditing Agent Actions
Use when model decisions, tool calls, approvals, artifact mutations, provider selections, or evidence issuance must be reconstructed without storing secrets or unverifiable narrative.
Resolving User Intent
Use when a request contains ambiguous goals, unstated constraints, conflicting stakeholders, or decisions that would cause competent teams to build materially different products.