Source: https://guthlabs.ai/docs/tools/instrument-catalog/qualification/ tool / candidate # Instrument catalog — qualification The distinct qualification record for Instrument catalog. This page is proposal-only. Status: **proposed**Lifecycle: **candidate** ## Record status **Record ID**: tool:instrument-catalog **Parent lifecycle**: candidate **Page lane**: docs_qualification **Lane lifecycle**: proposed **Owner**: Tilly **Owner role**: Pointguard and independent reviewer **Owner status**: Not separately recorded **Qualification result**: NOT RUN · held for evidence and human review **Working browser surface:** [Tools — overview]() — Inspect the tool contract, usage, boundaries, and proposed qualification checks. This route is local-only; provider, credential, database, customer, publication, deployment, and production effects remain held. ## Qualification status **Result**: NOT RUN **Disposition**: HELD **Reviewer**: Not recorded **Receipt**: Not recorded This page defines proposed acceptance criteria for the docs_qualification lane. It does not execute tests, establish compliance, qualify the subject, or authorize an effect. ### Lane-specific instrument aids [codata-physical-constants-referenceoptional · Proposal-only reference comparator for checking whether a catalog entry names an exact allowed instrument; not evidence that the catalog connects to or uses it.]()[physical-constants-referenceoptional · Proposal-only secondary reference comparator for exact-slug reconciliation; not evidence of implementation, deployment, or authority.]() ## Outcome definitions **Verified**: All stated evidence and acceptance requirements passed for the exact reviewed revision; this still does not authorize deployment or an external effect. **Failed**: One or more deterministic acceptance requirements failed with an inspectable reason. **Needs review**: Evidence or interpretation is incomplete, conflicting, or awaits an identified human reviewer. **Held**: Authority, required evidence, safe execution conditions, or a principal gate is absent. The current record remains NOT RUN / HELD. These definitions describe candidate outcomes only. ## Catalog-observed source metadata These fields are reproduced from the admitted candidate record for source-fidelity inspection. Presence does not prove implementation, connection, qualification, authority, or an external effect. **tool_id**: tool:instrument-catalog **slug**: instrument-catalog **title**: Instrument catalog **owner_agents**: Tilly **owner_roles**: Pointguard and independent reviewer **related_jobs**: Independent review; Instrument qualification; Evidence reconciliation; Grant research and drafts; Website claim review **related_field_guides**: Instrument packets; Qualification records; Grant dossiers; Public-claim routes **principal_gates**: Final publication; Funding commitments; Credential access; Changes to another agent's source **never_rules**: Approve her own evidence; Hide a contradiction; Turn a draft into a public claim **lifecycle**: candidate **source_refs**: agents/index.html#tilly ## Proposed deterministic qualification tests - Identity: the identity route displays tool_id=tool:instrument-catalog, slug=instrument-catalog, title=Instrument catalog, owner Tilly, the supplied roles, jobs, gates, never-rules, and source reference exactly. - Scope: every statement claiming implementation, connection, qualification, deployment, or authority is either supported by a supplied record or labeled unproven; otherwise the build fails. - Directory integrity: every instrument link resolves to an exact supplied slug; aliases, invented providers, invented metrics, and unsupported customer-use claims fail. - Status integrity: supplied VERIFIED_CLEAN, VERIFIED_WITH_ERRATA, and DISPOSED_UNVERIFIABLE_OFFLINE statuses are preserved; no status is upgraded. - Crawlability: every required documentation route is reachable from the catalog index, has one descriptive title, a canonical URL, and distinct useful content. - Determinism: identical fixture inputs produce identical normalized records, route output, pass/fail results, and claim disposition. - Accessibility: all controls are keyboard operable; focus is visible; headings and landmarks are coherent; form fields have labels; errors and status changes are programmatically announced; content remains usable at 200% zoom and in reflow; no color-only meaning or motion-only interaction is required. - Privacy: the documentation identifies all fields requested by the catalog; unproven collection, retention, transmission, logging, deletion, or credential behavior is marked unknown and cannot be described as private or secure. - Abuse: malformed, oversized, repeated, adversarial, credential-seeking, and authority-bypass inputs are rejected or safely contained; failures are recorded without exposing secrets. - Source: each factual claim has a source-ledger entry; an unsupported claim is held rather than published. - Authority: Tilly cannot independently approve her own evidence; final publication, funding commitments, credential access, and changes to another agent's source remain blocked without the required independent authority record. - Contradiction handling: conflicting evidence creates a visible contradiction record and blocks affected claims; the system must not hide or silently select one version. - Release gate: any failed required test, missing source, unresolved authority conflict, or unreviewed erratum keeps the candidate proposal-only. ## Negative and abuse cases - Observed catalog presence may be mistaken for a functioning or connected implementation. - Directory status may be mistaken for qualification of this catalog. - Unsupported claims about providers, current metrics, customers, outcomes, security, privacy, or authority may be published. - Instrument aliases or similarly named entries may cause incorrect reconciliation. - Medical, financial, engineering, or other high-consequence instrument use may be inferred from an instrument name alone. - Unreviewed errata may be presented as corrected or authoritative. - Credential requests, prompt injection, enumeration, or oversized inputs may bypass review or create disclosure risk. - Accessibility failures may prevent independent reviewers from inspecting evidence. - Contradictions may be hidden during grant or website claim preparation. - Draft language may be mistaken for a public claim. ## Qualification claim boundary ### Potentially allowed only after evidence and review - The supplied record identifies an observed tool with ID tool:instrument-catalog and slug instrument-catalog. - The supplied record names Tilly as owner and lists Pointguard and independent reviewer as roles. - The supplied record lists the related jobs, field guides, principal gates, never-rules, and source reference agents/index.html#tilly. - The documentation package proposes deterministic tests and release gates. - An exact allowed directory entry may be referenced by its supplied slug, name, area, and status without implying catalog integration. - A failed, missing, contradictory, or unverified item can be recorded and held. ### Still held - The catalog is implemented, connected, deployed, qualified, secure, private, authoritative, or production-ready. - The catalog has current metrics, providers, customers, effects, or successful use. - Any referenced instrument is invoked, integrated, or operational through this catalog. - Any instrument status proves this catalog's behavior or suitability for a particular decision. - Tilly has independently approved her own evidence. - A draft, grant statement, website statement, or qualification record is a final public claim. - Any credential access, funding commitment, final publication, or cross-agent source change is authorized. - Any medical, financial, legal, safety, or engineering result is fit for real-world action without separate review. ## Sources and evidence These pointers bind the page to evidence. They do not grant authority or collapse verification into deployment. - `source_record:tool:instrument-catalog` - `agents/index.html#tilly`