marcos-ai-bootstrap 0.1.7 → 0.1.9

package/README.md

@@ -120,10 +120,13 @@ major version:
 
 | Commit type | Result (pre-1.0) |
 |---|---|
-| `fix:` / `feat:` / `refactor:` … | patch (e.g. `0.1.0` → `0.1.1`) |
+| `fix:` / `feat:` | patch (e.g. `0.1.0` → `0.1.1`) |
 | `feat!:` or a `BREAKING CHANGE:` footer | minor (e.g. `0.1.0` → `0.2.0`) |
 | any commit with a `Release-As: X.Y.Z` footer | forces exactly that version |
 
+These commit types do **not** trigger a release on their own: `refactor:`, `chore:`,
+`docs:`, `perf:`, `test:`, `ci:`, `build:`, `style:`. (`bump-patch-for-minor-pre-major`
+only sizes a bump that is already triggered — it does not make these types releasable.)
+
 Cut `1.0.0` with a `Release-As: 1.0.0` commit when the API is stable; after that, standard
-SemVer applies (`feat:` → minor, breaking → major). Non-releasable commits (e.g. `docs:`,
-`ci:`) won't create a Release PR on their own.
+SemVer applies (`feat:` → minor, breaking → major).

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "marcos-ai-bootstrap",
-  "version": "0.1.7",
+  "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

@@ -1,6 +1,6 @@
 ---
 name: initialize
-description: One-time environment reconciliation. First wires this tool's instruction file to the shipped MARCOS-AI-BOOTSTRAP.md rules (appending an @-include, never overwriting; creating the file if absent). Discovers applicable MCP servers and, with user approval, installs and wires them into the infra/planner agents; discovers where plan documents actually live and, after user confirmation, wires the planner/implement/docs agents to that location; scans past PRs, branch names, and commit history and, after user confirmation, customises the `pr` skill's convention profile; then always prompts the user to choose the model for each tier/role (pre-selecting the current model, or the closest available match when it is unavailable) and rewrites the agent files. Never commits.
+description: One-time environment reconciliation. First wires this tool's instruction file to the shipped MARCOS-AI-BOOTSTRAP.md rules (appending an @-include, never overwriting; creating the file if absent). Discovers applicable MCP servers and, with user approval, installs and wires them into the infra/planner agents; discovers where plan documents actually live and, after user confirmation, wires the planner/implement/docs agents to that location; scans past PRs, branch names, and commit history and, after user confirmation, customises the `pull-request` skill's convention profile; then always prompts the user to choose the model for each tier/role (pre-selecting the current model, or the closest available match when it is unavailable) and rewrites the agent files. Never commits.
 ---
 
 You are the initialize orchestrator. Reconcile this repo's agent network with the current environment in the phases below. This skill only edits agent and skill files, the tool's instruction entry-point, and MCP config; it never touches source code and never commits.
@@ -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
 
@@ -55,7 +55,7 @@ The full agent rules ship as `MARCOS-AI-BOOTSTRAP.md` at the repo root. Ensure t
 
 ## Phase 4 - PR & contribution convention discovery
 
-Customise the `pr` skill so it matches how THIS repository actually works, learned from its own history rather than assumed defaults.
+Customise the `pull-request` skill so it matches how THIS repository actually works, learned from its own history rather than assumed defaults.
 
 1. Gather evidence of the repo's conventions:
    - **Past PRs** - `gh pr list --state merged --limit 50 --json number,title,headRefName,body`. Infer PR-title patterns (Conventional Commits, ticket prefixes like `[ABC-123]`, sentence vs lower case), branch-name patterns (prefixes, separators, casing), and PR-body structure (required sections, checklists).
@@ -64,8 +64,8 @@ Customise the `pr` skill so it matches how THIS repository actually works, learn
    - **Repo settings** - `gh repo view --json defaultBranchRef,mergeCommitAllowed,squashMergeAllowed,rebaseMergeAllowed` for the default branch and allowed merge methods.
 2. Synthesise a concise convention profile: branch-name rules, commit-message rules, PR-title rules, PR-body/template rules, and any release-automation constraints. Prefer the dominant observed pattern; where history is sparse or inconsistent, fall back to the general Conventional Commits defaults and say so explicitly.
 3. Present the inferred profile to the user for confirmation or edits. Do not rewrite the skill without confirmation.
-4. On confirmation, rewrite ONLY the "Repository conventions" block of `.agents/skills/pr/SKILL.md` - the text between the `<!-- CONVENTIONS:START -->` and `<!-- CONVENTIONS:END -->` markers - with the confirmed profile. Leave the rest of the skill untouched.
-5. Report the resolved convention profile and confirm the `pr` skill was updated.
+4. On confirmation, rewrite ONLY the "Repository conventions" block of `.agents/skills/pull-request/SKILL.md` - the text between the `<!-- CONVENTIONS:START -->` and `<!-- CONVENTIONS:END -->` markers - with the confirmed profile. Leave the rest of the skill untouched.
+5. Report the resolved convention profile and confirm the `pull-request` skill was updated.
 
 ## Guardrails
 - Never commit or push - you edit agent and skill files and MCP config; the user commits.

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/{pr → pull-request}/SKILL.md

@@ -1,9 +1,9 @@
 ---
-name: pr
+name: pull-request
 description: Open a pull request that follows this repository's conventions for branch names, commit messages, and PR titles and bodies. Verifies you are on a working branch, checks and repairs the branch/commits/title against the active convention profile, pushes, and opens the PR with the GitHub CLI. Never merges the PR.
 ---
 
-You are the pr orchestrator. Open a pull request that conforms to this repository's contribution conventions, then hand off to the user to merge. Never merge the PR yourself and never push to the default branch.
+You are the pull-request orchestrator. Open a pull request that conforms to this repository's contribution conventions, then hand off to the user to merge. Never merge the PR yourself and never push to the default branch.
 
 ## Convention profile
 

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/initialize/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: initialize
-description: One-time environment reconciliation. First wires this tool's instruction file to the shipped MARCOS-AI-BOOTSTRAP.md rules (appending an @-include, never overwriting; creating the file if absent). Discovers applicable MCP servers and, with user approval, installs and wires them into the infra/planner agents; discovers where plan documents actually live and, after user confirmation, wires the planner/implement/docs agents to that location; scans past PRs, branch names, and commit history and, after user confirmation, customises the `pr` skill's convention profile; then always prompts the user to choose the model for each tier/role (pre-selecting the current model, or the closest available match when it is unavailable) and rewrites the agent files. Never commits.
+description: One-time environment reconciliation. First wires this tool's instruction file to the shipped MARCOS-AI-BOOTSTRAP.md rules (appending an @-include, never overwriting; creating the file if absent). Discovers applicable MCP servers and, with user approval, installs and wires them into the infra/planner agents; discovers where plan documents actually live and, after user confirmation, wires the planner/implement/docs agents to that location; scans past PRs, branch names, and commit history and, after user confirmation, customises the `pull-request` skill's convention profile; then always prompts the user to choose the model for each tier/role (pre-selecting the current model, or the closest available match when it is unavailable) and rewrites the agent files. Never commits.
 ---
 
 You are the initialize orchestrator. Reconcile this repo's agent network with the current environment in the phases below. This skill only edits agent and skill files, the tool's instruction entry-point, and MCP config; it never touches source code and never commits.
@@ -55,7 +55,7 @@ The full agent rules ship as `MARCOS-AI-BOOTSTRAP.md` at the repo root. Ensure t
 
 ## Phase 4 — PR & contribution convention discovery
 
-Customise the `pr` skill so it matches how THIS repository actually works, learned from its own history rather than assumed defaults.
+Customise the `pull-request` skill so it matches how THIS repository actually works, learned from its own history rather than assumed defaults.
 
 1. Gather evidence of the repo's conventions:
    - **Past PRs** — `gh pr list --state merged --limit 50 --json number,title,headRefName,body`. Infer PR-title patterns (Conventional Commits, ticket prefixes like `[ABC-123]`, sentence vs lower case), branch-name patterns (prefixes, separators, casing), and PR-body structure (required sections, checklists).
@@ -64,8 +64,8 @@ Customise the `pr` skill so it matches how THIS repository actually works, learn
    - **Repo settings** — `gh repo view --json defaultBranchRef,mergeCommitAllowed,squashMergeAllowed,rebaseMergeAllowed` for the default branch and allowed merge methods.
 2. Synthesise a concise convention profile: branch-name rules, commit-message rules, PR-title rules, PR-body/template rules, and any release-automation constraints. Prefer the dominant observed pattern; where history is sparse or inconsistent, fall back to the general Conventional Commits defaults and say so explicitly.
 3. Present the inferred profile to the user for confirmation or edits. Do not rewrite the skill without confirmation.
-4. On confirmation, rewrite ONLY the "Repository conventions" block of `.claude/skills/pr/SKILL.md` — the text between the `<!-- CONVENTIONS:START -->` and `<!-- CONVENTIONS:END -->` markers — with the confirmed profile. Leave the rest of the skill untouched.
-5. Report the resolved convention profile and confirm the `pr` skill was updated.
+4. On confirmation, rewrite ONLY the "Repository conventions" block of `.claude/skills/pull-request/SKILL.md` — the text between the `<!-- CONVENTIONS:START -->` and `<!-- CONVENTIONS:END -->` markers — with the confirmed profile. Leave the rest of the skill untouched.
+5. Report the resolved convention profile and confirm the `pull-request` skill was updated.
 
 ## Guardrails
 - Never commit or push — you edit agent and skill files and MCP config; the user commits.

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/{pr → pull-request}/SKILL.md

@@ -1,9 +1,9 @@
 ---
-name: pr
+name: pull-request
 description: Open a pull request that follows this repository's conventions for branch names, commit messages, and PR titles and bodies. Verifies you are on a working branch, checks and repairs the branch/commits/title against the active convention profile, pushes, and opens the PR with the GitHub CLI. Never merges the PR.
 ---
 
-You are the pr orchestrator. Open a pull request that conforms to this repository's contribution conventions, then hand off to the user to merge. Never merge the PR yourself and never push to the default branch.
+You are the pull-request orchestrator. Open a pull request that conforms to this repository's contribution conventions, then hand off to the user to merge. Never merge the PR yourself and never push to the default branch.
 
 ## Convention profile
 

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/initialize/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: initialize
-description: One-time environment reconciliation. First wires this tool's instruction file to the shipped MARCOS-AI-BOOTSTRAP.md rules (appending an @-include, never overwriting; creating the file if absent). Discovers applicable MCP servers and, with user approval, installs and wires them into the infra/planner agents; discovers where plan documents actually live and, after user confirmation, wires the planner/implement/docs agents to that location; scans past PRs, branch names, and commit history and, after user confirmation, customises the `pr` skill's convention profile; then always prompts the user to choose the model for each tier/role (pre-selecting the current model, or the closest available match when it is unavailable) and rewrites the agent files. Never commits.
+description: One-time environment reconciliation. First wires this tool's instruction file to the shipped MARCOS-AI-BOOTSTRAP.md rules (appending an @-include, never overwriting; creating the file if absent). Discovers applicable MCP servers and, with user approval, installs and wires them into the infra/planner agents; discovers where plan documents actually live and, after user confirmation, wires the planner/implement/docs agents to that location; scans past PRs, branch names, and commit history and, after user confirmation, customises the `pull-request` skill's convention profile; then always prompts the user to choose the model for each tier/role (pre-selecting the current model, or the closest available match when it is unavailable) and rewrites the agent files. Never commits.
 ---
 
 You are the initialize orchestrator. Reconcile this repo's agent network with the current environment in the phases below. This skill only edits agent and skill files, the tool's instruction entry-point, and MCP config; it never touches source code and never commits.
@@ -57,7 +57,7 @@ Role-specific override: `infra-copilot` uses `gpt-5.4`.
 
 ## Phase 4 — PR & contribution convention discovery
 
-Customise the `pr` skill so it matches how THIS repository actually works, learned from its own history rather than assumed defaults.
+Customise the `pull-request` skill so it matches how THIS repository actually works, learned from its own history rather than assumed defaults.
 
 1. Gather evidence of the repo's conventions:
    - **Past PRs** — `gh pr list --state merged --limit 50 --json number,title,headRefName,body`. Infer PR-title patterns (Conventional Commits, ticket prefixes like `[ABC-123]`, sentence vs lower case), branch-name patterns (prefixes, separators, casing), and PR-body structure (required sections, checklists).
@@ -66,8 +66,8 @@ Customise the `pr` skill so it matches how THIS repository actually works, learn
    - **Repo settings** — `gh repo view --json defaultBranchRef,mergeCommitAllowed,squashMergeAllowed,rebaseMergeAllowed` for the default branch and allowed merge methods.
 2. Synthesise a concise convention profile: branch-name rules, commit-message rules, PR-title rules, PR-body/template rules, and any release-automation constraints. Prefer the dominant observed pattern; where history is sparse or inconsistent, fall back to the general Conventional Commits defaults and say so explicitly.
 3. Present the inferred profile to the user for confirmation or edits. Do not rewrite the skill without confirmation.
-4. On confirmation, rewrite ONLY the "Repository conventions" block of `.github/skills/pr/SKILL.md` — the text between the `<!-- CONVENTIONS:START -->` and `<!-- CONVENTIONS:END -->` markers — with the confirmed profile. Leave the rest of the skill untouched.
-5. Report the resolved convention profile and confirm the `pr` skill was updated.
+4. On confirmation, rewrite ONLY the "Repository conventions" block of `.github/skills/pull-request/SKILL.md` — the text between the `<!-- CONVENTIONS:START -->` and `<!-- CONVENTIONS:END -->` markers — with the confirmed profile. Leave the rest of the skill untouched.
+5. Report the resolved convention profile and confirm the `pull-request` skill was updated.
 
 ## Guardrails
 - Never commit or push — you edit agent and skill files and MCP config; the user commits.

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/{pr → pull-request}/SKILL.md

@@ -1,9 +1,9 @@
 ---
-name: pr
+name: pull-request
 description: Open a pull request that follows this repository's conventions for branch names, commit messages, and PR titles and bodies. Verifies you are on a working branch, checks and repairs the branch/commits/title against the active convention profile, pushes, and opens the PR with the GitHub CLI. Never merges the PR.
 ---
 
-You are the pr orchestrator. Open a pull request that conforms to this repository's contribution conventions, then hand off to the user to merge. Never merge the PR yourself and never push to the default branch.
+You are the pull-request orchestrator. Open a pull request that conforms to this repository's contribution conventions, then hand off to the user to merge. Never merge the PR yourself and never push to the default branch.
 
 ## Convention profile
 

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:

package/src/HUMAN.md

@@ -29,5 +29,5 @@ Once the files are written:
 1. **`/planner`** — Give a basic outline of what you want to build. The agent asks clarifying questions and iterates until it has a complete plan for the feature, bugfix, or chore.
 2. **`/clear`** — Clear the context window.
 3. **`/implement`** — Paste the path to the plan that was created, e.g. `documents/plans/20260101-plan.md`.
-4. **`/pr`** — Open a pull request with Conventional Commit messages so the release-please workflow can cut a release once merged.
+4. **`/pull-request`** — Open a pull request with Conventional Commit messages so the release-please workflow can cut a release once merged.
 5. **`/watch-ci`** — Paste the PR or GitHub Actions run. It watches the build to make sure everything passes, fixing bugs in real time if needed.

package/src/MARCOS-AI-BOOTSTRAP.md

@@ -139,11 +139,11 @@ cannot edit locally, so it watches, diagnoses, and reports the fix back to the u
 **Guardrails:** Never commits or pushes — agents edit files, the user commits. Never works on `main` (uses the plan's branch). Honours each phase's agent designation exactly; stops on a failed phase.
 
 ### initialize
-**Purpose:** One-time environment reconciliation. First ensures the tool's instruction file (`CLAUDE.md`, `AGENTS.md`, or `.github/copilot-instructions.md`) references the shipped `MARCOS-AI-BOOTSTRAP.md` rules — appending a short `@MARCOS-AI-BOOTSTRAP.md` include (never overwriting existing content), or creating the file if it does not exist. Discovers applicable MCP servers (via the MCP Servers discovery → policy-check → install flow) and, with user approval, installs and wires them into the `infra` and `planner` agents. Discovers where plan documents actually live in the repo and, after explicit user confirmation, wires the `planner`, `implement`, and `docs` agents/skills to that location. Scans the repository's history (past merged PRs, branch names, commit subjects, and any CONTRIBUTING / PR-template / commit-lint / release-automation config) and, after user confirmation, customises the `pr` skill's convention profile to match. Then always prompts the user, via a dropdown, to choose the model for each tier/role — pre-selecting the currently configured model when it is available, or the closest available match when it is not — and rewrites the agent files.
-**Pipeline:** rules-file include wiring → MCP discovery → user approval → install + wire agents → plans-location discovery → user confirmation → rewrite plan-location references → PR/commit-convention discovery → user confirmation → customise the `pr` skill → enumerate available models → user chooses model per tier/role (always) → rewrite agent files.
-**Guardrails:** Never commits or pushes. Only edits agent/skill files, the tool's instruction entry-point, and MCP config — never source code. Appends to (never clobbers) an existing instruction file. Never installs a policy-blocked or unapproved server. Never changes the plans location or `pr` conventions without explicit user confirmation. Idempotent for include wiring, MCP wiring, and the plans location; model selection is always offered, but keeping the current choice leaves files unchanged.
+**Purpose:** One-time environment reconciliation. First ensures the tool's instruction file (`CLAUDE.md`, `AGENTS.md`, or `.github/copilot-instructions.md`) references the shipped `MARCOS-AI-BOOTSTRAP.md` rules — appending a short `@MARCOS-AI-BOOTSTRAP.md` include (never overwriting existing content), or creating the file if it does not exist. Discovers applicable MCP servers (via the MCP Servers discovery → policy-check → install flow) and, with user approval, installs and wires them into the `infra` and `planner` agents. Discovers where plan documents actually live in the repo and, after explicit user confirmation, wires the `planner`, `implement`, and `docs` agents/skills to that location. Scans the repository's history (past merged PRs, branch names, commit subjects, and any CONTRIBUTING / PR-template / commit-lint / release-automation config) and, after user confirmation, customises the `pull-request` skill's convention profile to match. Then always prompts the user, via a dropdown, to choose the model for each tier/role — pre-selecting the currently configured model when it is available, or the closest available match when it is not — and rewrites the agent files.
+**Pipeline:** rules-file include wiring → MCP discovery → user approval → install + wire agents → plans-location discovery → user confirmation → rewrite plan-location references → PR/commit-convention discovery → user confirmation → customise the `pull-request` skill → enumerate available models → user chooses model per tier/role (always) → rewrite agent files.
+**Guardrails:** Never commits or pushes. Only edits agent/skill files, the tool's instruction entry-point, and MCP config — never source code. Appends to (never clobbers) an existing instruction file. Never installs a policy-blocked or unapproved server. Never changes the plans location or `pull-request` conventions without explicit user confirmation. Idempotent for include wiring, MCP wiring, and the plans location; model selection is always offered, but keeping the current choice leaves files unchanged.
 
-### pr
+### pull-request
 **Purpose:** Open a pull request that follows THIS repository's contribution conventions — branch names, commit-message format, PR title, and PR body — defaulting to widely-used best practices (kebab-case typed branches, Conventional Commits) until the `initialize` skill customises the convention profile from the repo's own history. Prevents malformed PRs and, where release automation (e.g. release-please) is in use, the failure mode where a non-conventional commit lands on the default branch and the release is silently skipped.
 **Pipeline:** resolve the default branch → branch check (never the default branch) → validate/repair the branch name and commit subjects against the active convention → push → derive and validate a conventional PR title and body → `gh pr create` → report the PR URL and any repo-specific merge/release guidance.
 **Guardrails:** Never merges the PR — opening it is the final step; the user merges. Never pushes to or commits on the default branch. Force-pushes only to complete a reword/rebase the user explicitly approved. Never uses `--no-verify`.