Skill Claude CodeCodex
Use this skill when importing an external Agent Skill repository into ForgeOS without executing untrusted code.
10 1mo ago A 26 tokens
original MIT
10Stars on the repository
60Mods indexed here, across every type
1mo agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown
Skill Claude CodeCodex
Use this skill when deciding whether a filtered candidate skill should become a stable ForgeOS provider.
10 1mo ago A 25 tokens
original MIT
Skill Claude CodeCodex
Use this skill when a candidate Agent Skill needs semantic security review before ForgeOS can expose it to an agent.
10 1mo ago A 29 tokens
original MIT
Skill Claude CodeCodex
Use when model decisions, tool calls, approvals, artifact mutations, provider selections, or evidence issuance must be reconstructed without storing secrets or unverifiable narrative.
10 1mo ago A 35 tokens
original MIT
Skill Claude CodeCodex
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.
10 1mo ago A 40 tokens
original MIT
Skill Claude CodeCodex
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.
10 1mo ago A 37 tokens
original MIT
Skill Claude CodeCodex
Use when estimated token counts differ systematically from provider-reported usage across models, content classes, languages, or tool schemas.
10 1mo ago A 31 tokens
original MIT
Skill Claude CodeCodex
Use when a source archive, package, container, skill registry, or product release needs reproducible proof bound to the exact bytes being distributed.
10 1mo ago A 34 tokens
original MIT
Skill Claude CodeCodex
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.
10 1mo ago A 38 tokens
original MIT
Skill Claude CodeCodex
Use when one outcome requires multiple specialized techniques with branch, join, parallel, retry, or rollback relationships rather than a single linear skill invocation.
10 1mo ago A 35 tokens
original MIT
Skill Claude CodeCodex
Use when decisions, blockers, conventions, and stable summaries must survive across tasks without treating conversation transcript as the project source of truth.
10 1mo ago A 32 tokens
original MIT
Skill Claude CodeCodex
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.
10 1mo ago A 41 tokens
original MIT
Skill Claude CodeCodex
Use when several skills or providers may express the same trigger, mechanism, outputs, evaluation surface, or benchmark coverage under different names.
10 1mo ago A 34 tokens
original MIT
Skill Claude CodeCodex
Use when a skill, policy profile, provider dependency, model version, or section change may reduce completion rate, quality, safety, routing accuracy, or token efficiency.
10 1mo ago A 40 tokens
original MIT
Skill Claude CodeCodex
Use when test, compiler, browser, database, or terminal output is too large for model context but must remain retrievable and evidentially complete.
10 1mo ago A 35 tokens
original MIT
Skill Claude CodeCodex
Use when planned context, tool schemas, model output reserve, or retrieved artifacts may exceed tenant, route, model, or skill-specific token limits.
10 1mo ago A 36 tokens
original MIT
Skill Claude CodeCodex
Use when artifact, code, finding, provider, or release approval requires independent review across principal, role, team, or trust-domain boundaries.
10 1mo ago A 34 tokens
original MIT
Skill Claude CodeCodex
Use when provider sources, tool APIs, model behavior, security assumptions, evaluators, or compatibility windows may have become outdated since the last successful validation.
10 1mo ago A 37 tokens
original MIT
Skill Claude CodeCodex
Use when a human or agent needs a concise, auditable explanation of why techniques and providers were selected, excluded, blocked, or deferred.
10 1mo ago A 34 tokens
original MIT
Skill Claude CodeCodex
Use when a semantic change, artifact supersession, provider substitution, policy change, or source revision makes previously accepted downstream proof unsafe to reuse.
10 1mo ago A 33 tokens
original MIT
Skill Claude CodeCodex
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.
10 1mo ago A 42 tokens
original MIT
Skill Claude CodeCodex
Use when repeated agent, route, tool, context, or verification failures reveal a reusable technique gap rather than a one-off project defect.
10 1mo ago A 34 tokens
original MIT
Skill Claude CodeCodex
Use when artifacts consume, replace, verify, invalidate, or derive from other versioned artifacts and downstream state must remain explainable and fresh.
10 1mo ago A 35 tokens
original MIT
Skill Claude CodeCodex
Use when several work units are independent enough to execute concurrently but still need deterministic ownership, coverage, resource locks, and verified joins.
10 1mo ago A 32 tokens
original MIT