--- title: "ADR-214: Approved skill versions instruct, load on demand and run processes" manual: "LLM Foundation" version: "0.44" permalink: "https://docs.typo3.org/permalink/netresearch/nr-llm:adr-214@0.44" source: "Adr/Adr214ApprovedSkillVersionsInstruct.rst" rendered: "2026-11-12T17:35:48+00:00" --- # ADR-214: Approved skill versions instruct, load on demand and run processes {#adr-214} - *Status:* Accepted (item 10 amended: the API shape and the lineage store; a running process governs sequence and answer structure — see the [amendment of 2026-10-22](https://docs.typo3.org/permalink/netresearch/nr-llm:adr-214-amendment-process-precedence@0.44); "keep" is a third denial reason — see the [amendment of 2026-10-24](https://docs.typo3.org/permalink/netresearch/nr-llm:adr-214-amendment-keep-reason@0.44); a proposal carries a length only against a configured range — see the [amendment of 2026-10-30](https://docs.typo3.org/permalink/netresearch/nr-llm:adr-214-amendment-length-only-with-range@0.44); the reads beside a question run before a process pauses — see the [amendment of 2026-10-31](https://docs.typo3.org/permalink/netresearch/nr-llm:adr-214-amendment-reads-beside-a-question@0.44)) - *Date:* 2026-10-08 - *Amended:* 2026-10-18 by [ADR-228](https://docs.typo3.org/permalink/netresearch/nr-llm:adr-228@0.44); 2026-10-25 by [ADR-229](https://docs.typo3.org/permalink/netresearch/nr-llm:adr-229@0.44) (items 1 and 3: the frontmatter's `page` is stored and editable like the process marker, but is not part of the version) - *Amends:* [ADR-036](https://docs.typo3.org/permalink/netresearch/nr-llm:adr-036@0.44) (item 3 and the tail drop of item 5, for skills approved as instructions; item 6: the integrity check compares a version digest over body and frontmatter fields, kept in a new column); [ADR-035](https://docs.typo3.org/permalink/netresearch/nr-llm:adr-035@0.44) (items 4 and 5: change detection compares that version digest, so a frontmatter-only change is a change); [ADR-061](https://docs.typo3.org/permalink/netresearch/nr-llm:adr-061@0.44) (items 1 and 4: the trust level also decides the framing, and backend-authored skills are admitted by their source's level); [ADR-038](https://docs.typo3.org/permalink/netresearch/nr-llm:adr-038@0.44) (item 5: the allow-list is resolved once per run over every effective attached skill); [ADR-031](https://docs.typo3.org/permalink/netresearch/nr-llm:adr-031@0.44) (a caller's system message keeps snippet text an administrator marked, on configurations that opt in); [ADR-200](https://docs.typo3.org/permalink/netresearch/nr-llm:adr-200@0.44) (a denial carries an enumerated reason); [ADR-165](https://docs.typo3.org/permalink/netresearch/nr-llm:adr-165@0.44) (resume also re-reads the invoked skill and intersects the stored allow-list); [ADR-169](https://docs.typo3.org/permalink/netresearch/nr-llm:adr-169@0.44) (section 4: the exclude list grows by the skill and skill-source fields of item 3); [ADR-084](https://docs.typo3.org/permalink/netresearch/nr-llm:adr-084@0.44) (in a run holding a process pin, in a turn that suspends for approval, the turn's non-remote reads that need no approval execute before the suspend and every other call is refused); [ADR-105](https://docs.typo3.org/permalink/netresearch/nr-llm:adr-105@0.44) (in such a run, a turn that pauses for input settles the calls beside the question the same way); [ADR-136](https://docs.typo3.org/permalink/netresearch/nr-llm:adr-136@0.44) (an approval-bound write tool also returns its pending target as structured values next to the preview); [ADR-130](https://docs.typo3.org/permalink/netresearch/nr-llm:adr-130@0.44) (the approve grant does not open a run holding a process pin); [ADR-172](https://docs.typo3.org/permalink/netresearch/nr-llm:adr-172@0.44) (on such a run the four-eyes pin rule is checked before the self-approval refusal and stops the run); [ADR-182](https://docs.typo3.org/permalink/netresearch/nr-llm:adr-182@0.44) (`withWriteTarget()` takes a completeness, and the write step carries it and a hook-failure flag); [ADR-150](https://docs.typo3.org/permalink/netresearch/nr-llm:adr-150@0.44) - *Authors:* Netresearch DTT GmbH Approved skill versions may supply instructions, load on demand and pin a process across runs. Approval applies to a version digest over body and frontmatter; a manifest body fingerprint alone is not approval or a publisher signature. Later amendments refine lineage and process precedence. Use these current guides: - Approve or revoke a version: [Approving a skill version as an instruction](https://docs.typo3.org/permalink/netresearch/nr-llm:administration-skills-approval@0.44). - Attach and load skills: [Attaching skills and injecting them into prompts](https://docs.typo3.org/permalink/netresearch/nr-llm:administration-skills-attach@0.44). - Start, resume, cancel or end a process: [Persisted agent runtime](https://docs.typo3.org/permalink/netresearch/nr-llm:api-agent-runtime@0.44). - Review write proposals and partial results: [Running tools](https://docs.typo3.org/permalink/netresearch/nr-llm:administration-tools@0.44). - Integrate stored conversations: [Stored conversations](https://docs.typo3.org/permalink/netresearch/nr-llm:api-conversations@0.44). The runtime rechecks the acting user, configuration, skills and tool policy. A process pin does not bypass permissions. Token admission uses a local estimate, not a guarantee that a provider will accept a request. `AgentRuntimeInterface::endProcess()` explicitly ends a process pin; this is no longer an open product question. The appendices retain the original context, detailed decisions, amendments and alternatives so that existing section links and reasoning remain usable. - [ADR-214 historical appendices](https://docs.typo3.org/permalink/netresearch/nr-llm:adr-214-historical-appendices@0.44)