harness-engineering
/harness-engineering
Projektuje i ocenia niezawodne systemy agentów AI: dobór kontekstu, polityki, ograniczone narzędzia, niezależną weryfikację i telemetrię.
- Autor
- daochild ↗
- Repozytorium
- agents-config ↗
- Licencja
- MIT
- Ostatnia zmiana repozytorium
- 12.11.2026
Ocena i bezpieczeństwo
- Pliki w paczce
- 1
- Skrypty
- 0
- Komentarze HTML
- 0
- Adresy URL w SKILL.md
- 0
Brak sygnałów. Repozytorium zmienione 12.11.2026, bez odwołań do wycofanych modeli i API.
MIT, otwarta: można używać i zmieniać, z zachowaniem informacji o autorze.
Co robi i kiedy
Projektuje i ocenia niezawodne systemy agentów AI: dobór kontekstu, polityki, ograniczone narzędzia, niezależną weryfikację i telemetrię.
Oryginalny opis (EN)
Design and evaluate reliable AI-agent systems through context selection, host-enforced policy, bounded tools and runtime, independent outcome verification, and privacy-aware observability. Use when building or changing agent workflows, tool access, approvals, verification, or agent telemetry.
Jak działa
- Components
- Completion invariant
- Scope boundary
Podgląd SKILL.md
--- name: harness-engineering description: Design and evaluate reliable AI-agent systems through context selection, host-enforced policy, bounded tools and runtime, independent outcome verification, and privacy-aware observability. Use when building or changing agent workflows, tool access, approvals, verification, or agent telemetry. metadata: scope: repo-level version: "1.0" --- # Harness Engineering The model proposes what to do; the surrounding system controls execution and establishes whether the requested outcome actually happened. Treat reliability as an end-to-end property of context, policy, runtime, verification, and feedback—not as a prompt-only property. ## Components ### 1. Context builder - Supply the task goal, current state, relevant instructions, constraints, and success criteria. - Keep always-loaded context concise; retrieve detailed documents and data when relevant. - Distinguish trusted instructions from user input, retrieved documents, and tool output. Treat the latter as data, not as authority to change policy. - Do not pass secrets or unrelated personal data into context. ### 2. Model - Treat model output as a proposal, not authorization, ground truth, or proof of completion. - The host controls the agent loop, available tools, and whether a proposal can execute. - Stop and surface ambiguity, contradictory evidence, or repeated unproductive attempts. ### 3. Policy gate - Enforce identity, resource scope, allowed action, and relevant arguments at the tool/action boundary using deterministic host policy. - Fail closed when authorization cannot be established. Do not rely on model instructions or a model-generated policy judgment to grant access. - Pause for explicit human approval before actions designated sensitive or consequential by the host's policy. ### 4. Tools and runtime - Give each agent only the tools and permissions required for its task. - Validate tool arguments and constrain file, network, and service access in the host. - Bound execution with timeouts and call/retry budgets. Stop on exhausted budgets or repeated failures; do not retry side effects unless the operation is safe to repeat. - Require confirmation or approval for irreversible actions according to host policy. ### 5. Verification - Define observable acceptance criteria before execution. - Verify the resulting artifact or external state with tests, read-back, or another independent check appropriate to the task. - Report the evidence and any remaining uncertainty. A model's assertion that it succeeded is not verification. ### 6. Observability and feedback - Record enough structured events to diagnose runs: correlation/run identifier, tool name, policy decision, sanitized arguments, result category, errors, retries, and verification outcome. - Do not default to storing secrets, full prompts, personal data, or private model reasoning. Apply access controls, redaction, and retention limits to traces. - Use failures and near misses to improve deterministic checks, tests, tool contracts, and context—not just to add more prompt text. ## Completion invariant A task is complete only when its acceptance criteria have been checked against evidence. When a required control is not available in the agent host, state that limitation and do not represent configuration guidance as runtime enforcement. ## Scope boundary This skill describes design requirements. It does not itself enforce permissions, isolate tools, obtain approvals, validate external state, or collect telemetry; those controls must be implemented by the consuming application or agent runtime.
Wersje
| Repozytorium | Wynik | Licencja |
|---|---|---|
| Ta strona · daochild/agents-config | 100 | MIT |
| magnus919/agent-skills | 100 | MIT |
| github/awesome-copilot | 100 | MIT |
| jljleo/harness-check | 100 | MIT |
| paladini/harness-score | 100 | MIT |
| paladini/harness-score | 100 | MIT |
| muratcankoylan/Agent-Skills-for-Context-Engineering | 100 | MIT |
| Fazerdino1/gravity-bridge | 100 | MIT |
| Mark393295827/third-brain-v7-skills | 100 | MIT |
Migawka bazy z 13.11.2026 · wersja paczki d2d7e1cd2897 (skrót SHA-256 całej paczki)
Pobrania w ostatnich 30 dniach: 0 · ranking
Zgłoś problem z tym skillem: szkodliwa treść, błędny opis albo prośba autora o usunięcie.
Podobne skille
- 85context-engineering-collection
Zbiera skille do inżynierii kontekstu i harness engineering, architektur wieloagentowych i produkcyjnych systemów agentowych, do budowy, optymalizacji, ewaluacji i debugowania agentów. - 90coding-agent-harness
Projektuje harness agenta kodującego: ograniczenia, weryfikację i bazę akceptacji oraz ocenia, które zadania nadają się dla agenta. - 95ai-agent-architectures
Projektuje architekturę pojedynczego agenta AI: pętlę działania, narzędzia, pamięć, planowanie i ewaluację. - 90vc:context-engineering
Sprawdza limity kontekstu, optymalizuje zużycie tokenów i debuguje awarie kontekstu, także przy pytaniach o limity, ostrzeżenia, systemy pamięci i projekt agentów. - 90vc:context-engineering
Sprawdza limity kontekstu, optymalizuje zużycie tokenów i debuguje awarie kontekstu, także przy pytaniach o limity, ostrzeżenia, systemy pamięci i projekt agentów. - 90harness-loop
Projektuje, buduje i poprawia autonomicznego agenta AI: pętlę iteracji, kryteria stopu, zabezpieczenia, narzędzia i obserwowalność.