marcos-ai-bootstrap 0.1.8 → 0.1.9

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "marcos-ai-bootstrap",
-  "version": "0.1.8",
+  "version": "0.1.9",
   "description": "Materialise the AI-Bootstrap agent/skill network (Claude Code, Codex, GitHub Copilot CLI) into any repository from the command line.",
   "bin": {
     "marcos-ai-bootstrap": "src/bin/ai-bootstrap.js"

package/src/.agents/skills/implement/SKILL.md

@@ -5,6 +5,24 @@ description: Execute an existing plan from documents/plans/ (path passed by the
 
 You are the implement orchestrator. Execute a written plan phase by phase.
 
+## Mandatory delegation contract
+
+This skill is an orchestrator, not an implementer.
+
+Before executing a phase:
+
+1. Read the plan only to identify its designated agent for that phase.
+2. Verify that the matching Codex agent can be invoked through the active agent-delegation mechanism.
+3. Invoke that agent with the complete phase objective, relevant files, acceptance criteria, and required prior context.
+4. Use the delegated agent's result as the basis for phase completion and verification.
+
+If the designated agent cannot be invoked:
+
+- Stop immediately.
+- State that the designated agent is unavailable in the current runtime.
+- Do not implement, modify files, or complete the phase as a substitute.
+- Do not silently substitute a different agent or perform the phase yourself.
+
 ## Input
 
 The user provides a path to a plan file, e.g. `documents/plans/20260622-ui-bugs.md`. Read the plan and extract:

package/src/.agents/skills/initialize/SKILL.md

@@ -41,9 +41,9 @@ The full agent rules ship as `MARCOS-AI-BOOTSTRAP.md` at the repo root. Ensure t
 
 | Tier | Model ID |
 |---|---|
-| High | `gpt-5.5` |
-| Standard | `gpt-5.4` |
-| Fast | `gpt-5.4-mini` |
+| High | `gpt-5.6-sol` |
+| Standard | `gpt-5.6-terra` |
+| Fast | `gpt-5.6-luna` |
 
 ## Phase 3 - Documentation location reconciliation
 

package/src/.agents/skills/planner/SKILL.md

@@ -5,6 +5,23 @@ description: Formalise the two-stage planning flow. Stage 1 runs planner-discove
 
 You are the planner orchestrator. Drive the two-stage planning flow.
 
+## Mandatory delegation contract
+
+This skill is an orchestrator, not a planner.
+
+Before researching, asking substantive questions, or producing an outline:
+
+1. Verify that `planner-discovery-codex` can be invoked through the active Codex agent-delegation mechanism.
+2. Invoke `planner-discovery-codex`, passing the complete user request and relevant context.
+3. Use only that agent's Stage 1 result as the basis for the user-facing outline.
+
+If the agent cannot be invoked:
+
+- Stop immediately.
+- State that `planner-discovery-codex` is unavailable in the current runtime.
+- Do not inspect the repository, browse, ask discovery questions, or create an outline as a substitute.
+- Do not silently perform Stage 1 yourself.
+
 ## Stage 1 - Discovery & Outline
 
 Invoke `planner-discovery-codex` with the user's task description and any relevant context. That agent will:

package/src/.agents/skills/watch-ci/SKILL.md

@@ -5,6 +5,23 @@ description: Watch a GitHub Actions workflow, auto-fix failures via the Codex ag
 
 You are the watch-ci orchestrator. Drive the CI fix loop until the target workflow is green.
 
+## Mandatory delegation contract
+
+This skill is an orchestrator, not a diagnostician, triager, investigator, or implementer.
+
+Before resolving the target, inspecting CI, or entering the fix loop:
+
+1. Verify that `log-reader-codex`, `triage-codex`, `investigate-codex`, and `code-codex` can be invoked through the active Codex agent-delegation mechanism.
+2. Invoke each agent only for its corresponding step in the prescribed fix loop, passing all relevant prior outputs and context.
+3. Use only the delegated agents' outputs as the basis for diagnosis, triage, investigation, and remediation.
+
+If a required agent cannot be invoked:
+
+- Stop immediately.
+- State that the unavailable agent is unavailable in the current runtime.
+- Do not inspect CI logs, diagnose, triage, investigate, or apply a fix as a substitute.
+- Do not silently perform a delegated pipeline step yourself.
+
 ## Target resolution
 
 Parse the optional input argument:

package/src/.claude/skills/implement/SKILL.md

@@ -5,6 +5,24 @@ description: Execute an existing plan from documents/plans/ (path passed by the
 
 You are the implement orchestrator. Execute a written plan phase by phase.
 
+## Mandatory delegation contract
+
+This skill is an orchestrator, not an implementer.
+
+Before executing a phase:
+
+1. Read the plan only to identify its designated agent for that phase.
+2. Verify that the matching Claude Code agent can be invoked through the active agent-delegation mechanism.
+3. Invoke that agent with the complete phase objective, relevant files, acceptance criteria, and required prior context.
+4. Use the delegated agent's result as the basis for phase completion and verification.
+
+If the designated agent cannot be invoked:
+
+- Stop immediately.
+- State that the designated agent is unavailable in the current runtime.
+- Do not implement, modify files, or complete the phase as a substitute.
+- Do not silently substitute a different agent or perform the phase yourself.
+
 ## Input
 
 The user provides a path to a plan file, e.g. `documents/plans/20260622-ui-bugs.md`. Read the plan and extract:

package/src/.claude/skills/planner/SKILL.md

@@ -5,6 +5,23 @@ description: Formalise the two-stage planning flow. Stage 1 runs planner-discove
 
 You are the planner orchestrator. Drive the two-stage planning flow.
 
+## Mandatory delegation contract
+
+This skill is an orchestrator, not a planner.
+
+Before researching, asking substantive questions, or producing an outline:
+
+1. Verify that `planner-discovery-claude` can be invoked through the active Claude Code agent-delegation mechanism.
+2. Invoke `planner-discovery-claude`, passing the complete user request and relevant context.
+3. Use only that agent's Stage 1 result as the basis for the user-facing outline.
+
+If the agent cannot be invoked:
+
+- Stop immediately.
+- State that `planner-discovery-claude` is unavailable in the current runtime.
+- Do not inspect the repository, browse, ask discovery questions, or create an outline as a substitute.
+- Do not silently perform Stage 1 yourself.
+
 ## Stage 1 — Discovery & Outline
 
 Invoke the `planner-discovery-claude` agent with the user's task description and any relevant context. That agent will:

package/src/.claude/skills/watch-ci/SKILL.md

@@ -5,6 +5,23 @@ description: Watch a GitHub Actions workflow, auto-fix failures via the Claude C
 
 You are the watch-ci orchestrator. Drive the CI fix loop until the target workflow is green.
 
+## Mandatory delegation contract
+
+This skill is an orchestrator, not a diagnostician, triager, investigator, or implementer.
+
+Before resolving the target, inspecting CI, or entering the fix loop:
+
+1. Verify that `log-reader-claude`, `triage-claude`, `investigate-claude`, and `code-claude` can be invoked through the active Claude Code agent-delegation mechanism.
+2. Invoke each agent only for its corresponding step in the prescribed fix loop, passing all relevant prior outputs and context.
+3. Use only the delegated agents' outputs as the basis for diagnosis, triage, investigation, and remediation.
+
+If a required agent cannot be invoked:
+
+- Stop immediately.
+- State that the unavailable agent is unavailable in the current runtime.
+- Do not inspect CI logs, diagnose, triage, investigate, or apply a fix as a substitute.
+- Do not silently perform a delegated pipeline step yourself.
+
 ## Target resolution
 
 Parse the optional input argument:

package/src/.codex/agents/code-codex.toml

@@ -1,6 +1,6 @@
 name = "code-codex"
 description = "Use for well-scoped code changes — feature implementation, bug fixes, explicit refactors. Writes or updates tests first, makes the smallest change that satisfies the requirement, validates immediately. Does not touch documentation — delegate that to the docs agent after."
-model = "gpt-5.4"
+model = "gpt-5.6-terra"
 model_reasoning_effort = "medium"
 developer_instructions = """
 

package/src/.codex/agents/docs-codex.toml

@@ -1,6 +1,6 @@
 name = "docs-codex"
 description = "Use for documentation-only updates — root README, service-level README files, architecture notes, concept docs, plan documents. Runs after implementation is verified. Never modifies code, config, or infrastructure files."
-model = "gpt-5.4-mini"
+model = "gpt-5.6-luna"
 model_reasoning_effort = "medium"
 developer_instructions = """
 

package/src/.codex/agents/explorer-codex.toml

@@ -1,6 +1,6 @@
 name = "explorer-codex"
 description = "Use for read-only codebase research — finding files, tracing call paths, understanding architecture, locating where a symbol is defined or used. Makes no changes. Returns findings as a concise report."
-model = "gpt-5.4-mini"
+model = "gpt-5.6-luna"
 model_reasoning_effort = "medium"
 developer_instructions = """
 

package/src/.codex/agents/infra-codex.toml

@@ -1,6 +1,6 @@
 name = "infra-codex"
 description = "Use for all infrastructure changes — Bicep templates, deployment pipeline YAML, IAC configuration. Never runs manual cloud CLI commands against shared environments. All changes go through files and pipelines."
-model = "gpt-5.4"
+model = "gpt-5.6-terra"
 model_reasoning_effort = "high"
 developer_instructions = """
 

package/src/.codex/agents/investigate-codex.toml

@@ -1,6 +1,6 @@
 name = "investigate-codex"
 description = "Stage 2 of the bug fix pipeline. Analyzes diagnostics from log-reader, explores affected code, and pinpoints root cause. Does NOT implement — hands off to code agent for the fix."
-model = "gpt-5.5"
+model = "gpt-5.6-sol"
 model_reasoning_effort = "medium"
 developer_instructions = """
 

package/src/.codex/agents/log-reader-codex.toml

@@ -1,6 +1,6 @@
 name = "log-reader-codex"
 description = "Stage 1 of the bug fix pipeline. Gathers logs, error messages, and diagnostic context, then passes findings to the investigate agent. Read-only data collection — no code changes or analysis."
-model = "gpt-5.4-mini"
+model = "gpt-5.6-luna"
 model_reasoning_effort = "medium"
 developer_instructions = """
 

package/src/.codex/agents/planner-codex.toml

@@ -1,6 +1,6 @@
 name = "planner-codex"
 description = "Stage 2 of planning. Invoke after the user has approved the outline from planner-discovery. Produces a full structured implementation plan written to documents/plans/. Does NOT implement — returns the plan for user approval before any code is written."
-model = "gpt-5.5"
+model = "gpt-5.6-sol"
 model_reasoning_effort = "high"
 developer_instructions = """
 

package/src/.codex/agents/planner-discovery-codex.toml

@@ -1,6 +1,6 @@
 name = "planner-discovery-codex"
 description = "Stage 1 of planning. Use first for any multi-phase or architecturally significant task. Asks clarifying questions, explores the codebase, and returns a concise outline for user approval. Does NOT write the full plan — invoke the planner agent after approval."
-model = "gpt-5.4"
+model = "gpt-5.6-terra"
 model_reasoning_effort = "high"
 developer_instructions = """
 

package/src/.codex/agents/test-runner-codex.toml

@@ -1,6 +1,6 @@
 name = "test-runner-codex"
 description = "Use to run tests, interpret failures, fix broken tests, and add regression tests for bug fixes. Validates that the narrowest relevant test suite passes after any code change."
-model = "gpt-5.4"
+model = "gpt-5.6-terra"
 model_reasoning_effort = "low"
 developer_instructions = """
 

package/src/.codex/agents/triage-codex.toml

@@ -1,6 +1,6 @@
 name = "triage-codex"
 description = "Assesses a CI failure diagnostic report and classifies the fix as easy or hard. Easy -> outputs a targeted fix suggestion. Hard -> signals that the investigate agent is required for root cause analysis."
-model = "gpt-5.4"
+model = "gpt-5.6-terra"
 model_reasoning_effort = "medium"
 developer_instructions = """
 

package/src/.github/skills/implement/SKILL.md

@@ -5,6 +5,24 @@ description: Execute an existing plan from documents/plans/ (path passed by the
 
 You are the implement orchestrator. Execute a written plan phase by phase.
 
+## Mandatory delegation contract
+
+This skill is an orchestrator, not an implementer.
+
+Before executing a phase:
+
+1. Read the plan only to identify its designated agent for that phase.
+2. Verify that the matching Copilot agent can be invoked through the active agent-delegation mechanism.
+3. Invoke that agent with the complete phase objective, relevant files, acceptance criteria, and required prior context.
+4. Use the delegated agent's result as the basis for phase completion and verification.
+
+If the designated agent cannot be invoked:
+
+- Stop immediately.
+- State that the designated agent is unavailable in the current runtime.
+- Do not implement, modify files, or complete the phase as a substitute.
+- Do not silently substitute a different agent or perform the phase yourself.
+
 ## Input
 
 The user provides a path to a plan file, e.g. `documents/plans/20260622-ui-bugs.md`. Read the plan and extract:

package/src/.github/skills/planner/SKILL.md

@@ -5,6 +5,23 @@ description: Formalise the two-stage planning flow. Stage 1 runs planner-discove
 
 You are the planner orchestrator. Drive the two-stage planning flow.
 
+## Mandatory delegation contract
+
+This skill is an orchestrator, not a planner.
+
+Before researching, asking substantive questions, or producing an outline:
+
+1. Verify that `planner-discovery-copilot` can be invoked through the active Copilot agent-delegation mechanism.
+2. Invoke `planner-discovery-copilot`, passing the complete user request and relevant context.
+3. Use only that agent's Stage 1 result as the basis for the user-facing outline.
+
+If the agent cannot be invoked:
+
+- Stop immediately.
+- State that `planner-discovery-copilot` is unavailable in the current runtime.
+- Do not inspect the repository, browse, ask discovery questions, or create an outline as a substitute.
+- Do not silently perform Stage 1 yourself.
+
 ## Stage 1 — Discovery & Outline
 
 Invoke the `planner-discovery-copilot` agent with the user's task description and any relevant context. That agent will:

package/src/.github/skills/watch-ci/SKILL.md

@@ -5,6 +5,23 @@ description: Watch a GitHub Actions workflow, auto-fix failures via the agent pi
 
 You are the watch-ci orchestrator. Drive the CI fix loop until the target workflow is green.
 
+## Mandatory delegation contract
+
+This skill is an orchestrator, not a diagnostician, triager, investigator, or implementer.
+
+Before resolving the target, inspecting CI, or entering the fix loop:
+
+1. Verify that `log-reader-copilot`, `triage-copilot`, `investigate-copilot`, and `code-copilot` can be invoked through the active Copilot agent-delegation mechanism.
+2. Invoke each agent only for its corresponding step in the prescribed fix loop, passing all relevant prior outputs and context.
+3. Use only the delegated agents' outputs as the basis for diagnosis, triage, investigation, and remediation.
+
+If a required agent cannot be invoked:
+
+- Stop immediately.
+- State that the unavailable agent is unavailable in the current runtime.
+- Do not inspect CI logs, diagnose, triage, investigate, or apply a fix as a substitute.
+- Do not silently perform a delegated pipeline step yourself.
+
 ## Target resolution
 
 Parse the optional input argument: