Updated AGENTS.md

Author: sfmskywalker

.agents/skills/speckit-plan/SKILL.md

@@ -62,7 +62,7 @@ You **MUST** consider the user input before proceeding (if not empty).
    - Evaluate gates (ERROR if violations unjustified)
    - Phase 0: Generate research.md (resolve all NEEDS CLARIFICATION)
    - Phase 1: Generate data-model.md, contracts/, quickstart.md
-   - Phase 1: Update agent context by running the agent script
+   - Phase 1: Leave repository and agent instruction files unchanged; keep feature context in the plan artifacts
    - Re-evaluate Constitution Check post-design
 
 4. **Stop and report**: Command ends after Phase 2 planning. Report branch, IMPL_PLAN path, and generated artifacts.

.claude/skills/speckit-plan/SKILL.md

@@ -63,7 +63,7 @@ You **MUST** consider the user input before proceeding (if not empty).
    - Evaluate gates (ERROR if violations unjustified)
    - Phase 0: Generate research.md (resolve all NEEDS CLARIFICATION)
    - Phase 1: Generate data-model.md, contracts/, quickstart.md
-   - Phase 1: Update agent context by running the agent script
+   - Phase 1: Leave repository and agent instruction files unchanged; keep feature context in the plan artifacts
    - Re-evaluate Constitution Check post-design
 
 4. **Stop and report**: Command ends after Phase 2 planning. Report branch, IMPL_PLAN path, and generated artifacts.

.github/agents/speckit.plan.agent.md

@@ -30,7 +30,7 @@ You **MUST** consider the user input before proceeding (if not empty).
    - Evaluate gates (ERROR if violations unjustified)
    - Phase 0: Generate research.md (resolve all NEEDS CLARIFICATION)
    - Phase 1: Generate data-model.md, contracts/, quickstart.md
-   - Phase 1: Update agent context by running the agent script
+   - Phase 1: Leave repository and agent instruction files unchanged; keep feature context in the plan artifacts
    - Re-evaluate Constitution Check post-design
 
 4. **Stop and report**: Command ends after Phase 2 planning. Report branch, IMPL_PLAN path, and generated artifacts.

.specify/integrations/claude.manifest.json

@@ -8,11 +8,11 @@
     ".claude/skills/speckit-clarify/SKILL.md": "1a77bd8c24d8dcfa8a883185480ef8a1ee0b68e4059ebe6dac3e66e872407ea5",
     ".claude/skills/speckit-constitution/SKILL.md": "86fd32ace9f5e99b44c6247629f2ef2ddec707459182870b65541e9def309f98",
     ".claude/skills/speckit-implement/SKILL.md": "bba51e30382cdfab8ef97ba924b7a7b879e0a5ac6733e97f14234e5e188ee42b",
-    ".claude/skills/speckit-plan/SKILL.md": "e4b7e372a06a987bb20d2142aea40460525363c2ad89a65fc050a67d6bb45eec",
+    ".claude/skills/speckit-plan/SKILL.md": "f75c339c468a12eeca8ba4a3a3bcc9b3466c2f48e3de25d9c23abdd7bcab4f45",
     ".claude/skills/speckit-specify/SKILL.md": "69ac96ba89ae6832c67e4c8c75393b7d50ef5a75c766e0261205040e9d3a4850",
     ".claude/skills/speckit-tasks/SKILL.md": "67c4419fc40299c9ebd68f677fad362dac7de1041df1bfe14b1d4e5e0adade9d",
     ".claude/skills/speckit-taskstoissues/SKILL.md": "8a8052fd7489424f9d62cc809042b2a2968ccb231466757aeca5bf47d5747222",
-    ".specify/integrations/claude/scripts/update-context.ps1": "8bce5081fe27ebf414d4eaf127d91b5540b00d24dde4fe1e303e8eb26ad5211a",
-    ".specify/integrations/claude/scripts/update-context.sh": "21a5aa3fc644f693a29d35975ce21e5a949cdc1d0258b11c21940754c3644fa6"
+    ".specify/integrations/claude/scripts/update-context.ps1": "e97ba404738b7f5da9f7912b6392e53ac28afa51cf4f925f6c67e01d29b1dde5",
+    ".specify/integrations/claude/scripts/update-context.sh": "c11f50a2744b0339cc21b886c7bd10e916fbfe876123eb99ec903af083145f43"
   }
 }

.specify/integrations/claude/scripts/update-context.ps1

@@ -1,23 +1,5 @@
-# update-context.ps1 — Claude Code integration: create/update CLAUDE.md
-#
-# Thin wrapper that delegates to the shared update-agent-context script.
-# Activated in Stage 7 when the shared script uses integration.json dispatch.
-#
-# Until then, this delegates to the shared script as a subprocess.
+# Retained as a Claude integration compatibility entry point.
+# Plan-derived agent context generation is intentionally disabled.
 
 $ErrorActionPreference = 'Stop'
-
-# Derive repo root from script location (walks up to find .specify/)
-$scriptDir = Split-Path -Parent $MyInvocation.MyCommand.Definition
-$repoRoot = try { git rev-parse --show-toplevel 2>$null } catch { $null }
-# If git did not return a repo root, or the git root does not contain .specify,
-# fall back to walking up from the script directory to find the initialized project root.
-if (-not $repoRoot -or -not (Test-Path (Join-Path $repoRoot '.specify'))) {
-    $repoRoot = $scriptDir
-    $fsRoot = [System.IO.Path]::GetPathRoot($repoRoot)
-    while ($repoRoot -and $repoRoot -ne $fsRoot -and -not (Test-Path (Join-Path $repoRoot '.specify'))) {
-        $repoRoot = Split-Path -Parent $repoRoot
-    }
-}
-
-& "$repoRoot/.specify/scripts/powershell/update-agent-context.ps1" -AgentType claude
+Write-Output 'Plan-derived agent context generation is disabled; maintain AGENTS.md directly.'

.specify/integrations/claude/scripts/update-context.sh

@@ -1,28 +1,8 @@
 #!/usr/bin/env bash
-# update-context.sh — Claude Code integration: create/update CLAUDE.md
-#
-# Thin wrapper that delegates to the shared update-agent-context script.
-# Activated in Stage 7 when the shared script uses integration.json dispatch.
-#
-# Until then, this delegates to the shared script as a subprocess.
 
-set -euo pipefail
+# Retained as a Claude integration compatibility entry point.
+# Plan-derived agent context generation is intentionally disabled.
 
-# Derive repo root from script location (walks up to find .specify/)
-_script_dir="$(cd "$(dirname "$0")" && pwd)"
-_root="$_script_dir"
-while [ "$_root" != "/" ] && [ ! -d "$_root/.specify" ]; do _root="$(dirname "$_root")"; done
-if [ -z "${REPO_ROOT:-}" ]; then
-  if [ -d "$_root/.specify" ]; then
-    REPO_ROOT="$_root"
-  else
-    git_root="$(git rev-parse --show-toplevel 2>/dev/null || true)"
-    if [ -n "$git_root" ] && [ -d "$git_root/.specify" ]; then
-      REPO_ROOT="$git_root"
-    else
-      REPO_ROOT="$_root"
-    fi
-  fi
-fi
+set -euo pipefail
 
-exec "$REPO_ROOT/.specify/scripts/bash/update-agent-context.sh" claude
+echo "Plan-derived agent context generation is disabled; maintain AGENTS.md directly."

.specify/integrations/codex.manifest.json

@@ -8,7 +8,7 @@
     ".agents/skills/speckit-clarify/SKILL.md": "a429d1af7bf00c65c6be2766a11c2571e9d18ede2b77ec4fd538db4d5ec242d1",
     ".agents/skills/speckit-constitution/SKILL.md": "7310adee465ee6a439a689518e6c133ce851d808c7a6e64d66f659ad8b4bd56e",
     ".agents/skills/speckit-implement/SKILL.md": "b39c4de2e794a96302cd36cc7b6796711aee0f3bcedba0d0c01ccf3b1036f898",
-    ".agents/skills/speckit-plan/SKILL.md": "1cd13274eb35a18d87e6f43bc69801910437ce9543286b13f87c4e3cbc33b9d8",
+    ".agents/skills/speckit-plan/SKILL.md": "d0033856f26b7e5ff683f181ceb20de7ca4f247c290b2c76241719be40e09012",
     ".agents/skills/speckit-specify/SKILL.md": "164542c78d6415ea9e16bb063652e989e14524a9a273176273e6c9b5ffa0b942",
     ".agents/skills/speckit-tasks/SKILL.md": "0b36b19eb61347406afea1953c1e5983f084931eaa34d1b10c6c6e67f828f29f",
     ".agents/skills/speckit-taskstoissues/SKILL.md": "32d8ee0f0482a7b2b9e6bee4dfd6947465754f2f82c404bfc7ef64f4a3b63bdd"

AGENTS.md

@@ -85,3 +85,4 @@ Before handing off changes, verify the following when applicable:
 
 - Keep this file limited to stable, repository-wide guidance. Feature-specific plans and historical change summaries belong in `specs/`, not here.
 - Agent-specific instruction files should defer to this file instead of duplicating or generating plan-derived content.
+- Follow the global Codex workroom model and fallback policy for orchestration and delegation. That policy is authoritative for model order and for distinguishing model unavailability from delegation timeout or failure; do not duplicate its details here.