The page is the provider. Human and browser agent use the same repository identity and skill material. The human chooses a repository, chooses how the agent should work in that repository, and states the desired outcome; Send exposes that exact handoff to the browser agent.
Loading the commit-pinned skill registry and checking browser WebMCP support…
Checking remote MCP health…
Skill source:resolving…
Repository projection: 29 active public repositories
Shared human + agent repository material
1. Choose the repository
The repository establishes the agent's working context before any action or skill is selected. The list is generated from the current active public repositories in The-Interdependency, and the selected repository's exact observed default-branch head travels with the handoff. Selection grants no write permission.
Selected repositoryNo repository selected.
Shared human + agent skill material
2. Choose how the agent should work
Choose a repository first to enable its agent-work choices.
The public skill surface is deliberately narrow: the metadata skills built on the module self-declared metadata convention, the METAPAT consultation router, deterministic refresh of derived artifacts, and receipt-backed EPAC selection/display. The remaining skills stay canonical in the source library rather than becoming competing definitions here.
Metadata skills
metadata skill
Module Self-Declared Metadata in Markdown
Description
Module Self-Declared Metadata in Markdown — native-first collection of metadata already expressed by code, documentation, manifests, schemas, tooling, and evidence formats, with MSDMD blocks only for otherwise unexpressed information. Load this when creating or revising metadata-driven skills, collecting repository metadata, integrating a metadata convention, building parsers or collection consumers, or auditing metadata coverage and provenance.
Native-first documentation coverage built on msdmd
Description
Native-first documentation coverage built on msdmd. Consume docstrings, documentation comments and source-linked documents; supplemental DOCS blocks express remaining obligations. A consuming runner verifies references and reports missing information separately from unsupported extraction. Load this when adding or auditing module documentation, tying code surfaces to docs, or wiring documentation coverage checks into CI.
Native-first capability inventory built on msdmd. Consume signatures, exports, annotations and API schemas; supplemental CAPABILITIES blocks express otherwise unrecorded behavior and boundaries. Keep declared surfaces separate from verified behavior. Load this when declaring module capabilities, building capability registries for agents, or auditing exposed surfaces against declared capabilities.
Native-first dependency topology built on msdmd. Consume imports, package manifests, lockfiles and build declarations at their owning scopes; supplemental DEPENDENCIES blocks express remaining architectural intent. Preserve edge kinds, conditions and resolution uncertainty. Load this when declaring dependencies, auditing architecture drift, checking graph cycles, or wiring dependency topology checks into CI.
Native-first module stewardship built on msdmd. Consume provider-specific CODEOWNERS, OWNERS and other authoritative responsibility declarations; supplemental OWNERS blocks express missing stewardship or escalation information. Keep review assignment, operational ownership and permissions distinct. Load this when assigning module ownership, routing reviews, auditing unowned code, or wiring stewardship coverage into CI.
Native-first contract evidence built on msdmd. Source owners declare behavior obligations and test owners declare accountable witnesses through supported native conventions or supplemental CONTRACTS and CHECKS blocks. Preserve explicit claim linkage and no-exec audit boundaries. Load this when adding tests that use msdmd, refactoring CONTRACTS/CHECKS declarations, or authoring a contract/check audit or executor.
Native-first module planning built on msdmd. Consume existing manifests, schemas and design declarations; supplemental MODULE_BUILD blocks record remaining purpose, surface, boundary, test, rollout and rollback obligations. Load this when turning a capability idea into a bounded module manifest and file plan before implementation.
Native-first runtime risk and permission boundaries built on msdmd
Description
Native-first runtime risk and permission boundaries built on msdmd. Consume existing permission, schema, configuration and effect declarations; supplemental BOUNDARIES blocks express otherwise missing auth, storage, network, user-data and operational effects. Declarations do not prove enforcement. Load this when touching permissions, persistence, network calls, user data, admin behavior, migrations, or other risk-bearing effects.
Self-declaring module composition ratios on msdmd — one comment line at a file's opening and closing source boundaries (never a fenced block), with a valid interpreter shebang allowed before the opening seal. The canonical seal is `The-Interdependency/a0`'s compact positional `N:M C:D I:O` annotation (code:comment · consumed:declared · fan-in:fan-out), computed by a0's `scripts/annotate.py`; the named `loc_comments=… imports_exports=… calls_definitions=…` line is a portable, per-file adaptation for standalone libraries, verified by the stdlib `ratios_check.py` (drift/misplacement failures, visible gaps). JSON/Markdown are out of scope. Load this when recording a module's composition ratios, when authoring or extending the ratio registry, or when wiring ratio verification into CI.
Living-spec generator. Derives the mechanical, observable facts of a repo (package name, version, description, license, authors, repository, build backend, development status, supported Python versions, keywords, runtime dependencies, optional extras, top-level layout, CI workflows) from pyproject.toml + the file tree and splices them into a machine-owned, marked block inside CLAUDE.md
Description
Living-spec generator. Derives the mechanical, observable facts of a repo (package name, version, description, license, authors, repository, build backend, development status, supported Python versions, keywords, runtime dependencies, optional extras, top-level layout, CI workflows) from pyproject.toml + the file tree and splices them into a machine-owned, marked block inside CLAUDE.md — keeping the doc from silently drifting from the code. Ships a stdlib-only generator with --write (refresh), --check (CI drift gate), and --print modes. Load this when: setting up or maintaining a CLAUDE.md / AGENTS.md so its factual half is generated rather than hand-typed; wiring a CI check that fails when docs drift from pyproject/version/deps/layout; deciding which parts of a doc to generate vs. hand-author; or onboarding a new org repo to the living-spec convention.
Native-first LLM instruction publication built on msdmd
Description
Native-first LLM instruction publication built on msdmd. Consume source-owned instruction metadata without requiring a second copy; the shipped stdlib runner generates llms.txt from LLMS blocks, while native-reader integration remains a contract. Load this when creating, updating, or maintaining llms.txt for repositories consumed by LLMs or agents.
TypeScript frontend generation from backend-owned module metadata and living specs
Description
TypeScript frontend generation from backend-owned module metadata and living specs. Load this when building, reviewing, or refactoring a self-building UI that reads backend metadata, exposes every editable field per module, renders each module's living spec, generates TypeScript types/forms/routes from metadata, or keeps admin/editor frontends synchronized with msdmd-style source declarations.
METAPAT consultation router for The Interdependency
Description
METAPAT consultation router for The Interdependency. Load this when deciding which distinctions, relations, boundaries, transformations, scales, or cross-domain correspondences should organize downstream work; when examining available observations or metrics to determine which questions and projections are worth measuring; when the-interdependency skill's METAPAT consultation gate triggers; when an unresolved conceptual choice would constrain architecture, semantics, measurement, ontology, or later claims; or when explicitly asked to consult, apply, or interpret current METAPAT. Do not load merely for routine implementation under already-fixed conceptual contracts.
Deterministic restoration of derived-artifact consistency after authoritative inputs change. Load this when deciding whether generated or derived outputs are current; when regenerating MSDMD collections, documentation, projections, package indexes, calibration artifacts, or other outputs from exact source identities; when computing the minimum affected rebuild closure; when designing retryable regeneration across unreliable executors; or when a system needs to make artifacts provably fresh rather than merely recently rebuilt. Do not load for ordinary one-shot builds whose inputs and outputs have no persistent freshness contract.
Evidence-bound EPAC target selection and display for WebMCP handoffs and other human-facing surfaces. Load this when choosing an EPAC element, molecule, construction receipt, comparison result, or available visualization to present; when preparing a receipt-backed EPAC display packet; when exposing the EPAC workflow as a selectable WebMCP skill; or when a requested EPAC display would require missing or invented geometry so the request can be refused or downgraded to verified source-backed output. Do not load to select EPAC or a UCNS candidate as canon, or for unrelated WebMCP catalogue changes.
Select a repository first, then a skill. No internal repository or skill identifier needs to be typed.
Same material, meaningful human selection
current public repository projection + skill definitions
↓
human chooses repository + reads the applicable skill
↓
explicit SEND
↓
one read-only handoff
↓
agent receives the exact repository, skill set, and human request
↓
agent's separately authorized change tools
For the refresh skill, choosing it automatically supplies the standard make-fresh request; the human may edit it. For EPAC selection/display, the human names the target and representation; the server passes that request but does not construct or render the research artifact. The browser handoff itself remains read-only and page-session-only. Actual repository changes require the agent's separately authorized repository, filesystem, deployment, or other tools.
hmmmRepository observation identifies the target; it does not authenticate the target, grant write authority, prove that every declared freshness executor is available, or prove that a selected EPAC source contains a committed renderer.