python-audit-method

<daodan_host_binding host="claude"> This binding governs execution of this package and its loaded references. It takes precedence over executable examples written for another host. Use only registered tools and their actual input schema; an example never creates a tool, argument, permission, model alias or nested worker capability. Preserve the generated worker allowlist, dependency closure, scope and delivery contracts.

Claude binding: repository tools are Read/Glob/Grep and Write/Edit; shell execution uses Bash and network fetch uses WebFetch. Pass the executable string in Bash's command field, and use its registered timeout/background schema. Worker dispatch uses the available native Agent mechanism and its registered agent-selection and prompt fields. Do not turn a prose role label into an invented role argument. Inherit the session model unless the declared workflow and active schema permit an override. Load installed skills by qualified ID; named roles use their owning plugin's agent identity, while workflow entries use /:. Required foreign providers use Claude's marketplace/install commands: claude plugin marketplace add , then claude plugin install @. A provider that is installed but disabled is enabled with claude plugin enable @; check claude plugin list --json before the first phase, and stop with that command when any plugin of this package's dependency closure, direct or transitive, is off. A declared package MCP server is configured through the generated MCP manifest; still check its tools are actually available in the active session.

The executing agent and its coordinator own continuation, recovery, verification and delivery. Skills supply knowledge and method instructions; they are not executors or a runtime persistence mechanism.

Resolve each component by kind and exact installed identity. A role is dispatched as a worker, a skill loads instructions, and a workflow starts its declared method. Kernel owner-qualified skill references are logical provider identities: resolve them to the actual host registry name and verified installed provider path. Do not invent a registry string by adding an owner's prefix when the host does not use it. Do not load an agent identity as a skill or execute a workflow name as a shell command. Named foreign providers remain mandatory. If an installed provider, MCP server or required isolation mechanism is unavailable, stop its dependent phase and report the missing capability. Do not install a different host's plugin or substitute unrelated skills to claim coverage.

Shell execution alone does not establish interactive stdin. Before a capture or checkpoint, use an available session-control mechanism. When stdin is unavailable, keep user-driven capture in a supported background process with bounded output and an explicit stop signal controlled by the coordinator after the user's completion message. Close owned browser/process resources on completion or cancellation.

Continue working within the current authorization while the requested result is achievable. After a tool error, inspect its cause, correct the relevant input or implementation, retry when justified and verify the outcome; never repeat a failing action blindly. Do not close the turn with a promise or a partial result when an authorized next step can still produce or verify the requested result. Stop only for a documented real impediment, a missing required capability, an unresolved human decision or the caller's stop request. At that boundary, report completed results, remaining work and the concrete prerequisite for continuation; continue any independent work that the blocker does not prevent.

A tool's successful exit, a worker stop or an idle session is not the deliverable. Return final text naming observed findings, artifact paths, executed checks and blockers. An empty worker result is missing delivery: inspect or resume that worker when permitted, or record failure. Verify required artifacts and candidate gates before marking the requested outcome complete.