@undeemed/get-shit-done-codex 1.20.2 → 1.20.3

package/commands/gsd/verify-work.md

@@ -14,14 +14,14 @@ allowed-tools:
 <objective>
 Validate built features through conversational testing with persistent state.
 
-Purpose: Confirm what Claude built actually works from user's perspective. One test at a time, plain text responses, no interrogation. When issues are found, automatically diagnose, plan fixes, and prepare for execution.
+Purpose: Confirm what Codex built actually works from user's perspective. One test at a time, plain text responses, no interrogation. When issues are found, automatically diagnose, plan fixes, and prepare for execution.
 
 Output: {phase_num}-UAT.md tracking all test results. If issues found: diagnosed gaps, verified fix plans ready for /gsd:execute-phase
 </objective>
 
 <execution_context>
-@~/.claude/get-shit-done/workflows/verify-work.md
-@~/.claude/get-shit-done/templates/UAT.md
+@~/.codex/get-shit-done/workflows/verify-work.md
+@~/.codex/get-shit-done/templates/UAT.md
 </execution_context>
 
 <context>
@@ -34,6 +34,6 @@ Phase: $ARGUMENTS (optional)
 </context>
 
 <process>
-Execute the verify-work workflow from @~/.claude/get-shit-done/workflows/verify-work.md end-to-end.
+Execute the verify-work workflow from @~/.codex/get-shit-done/workflows/verify-work.md end-to-end.
 Preserve all workflow gates (session management, test presentation, diagnosis, fix planning, routing).
 </process>

package/get-shit-done/bin/gsd-tools.cjs

@@ -471,7 +471,7 @@ function output(result, raw, rawValue) {
     process.stdout.write(String(rawValue));
   } else {
     const json = JSON.stringify(result, null, 2);
-    // Large payloads exceed Claude Code's Bash tool buffer (~50KB).
+    // Large payloads exceed Codex CLI's Bash tool buffer (~50KB).
     // Write to tmpfile and output the path prefixed with @file: so callers can detect it.
     if (json.length > 50000) {
       const tmpPath = path.join(require('os').tmpdir(), `gsd-${Date.now()}.json`);

package/get-shit-done/references/checkpoints.md

@@ -1,13 +1,13 @@
 <overview>
 Plans execute autonomously. Checkpoints formalize interaction points where human verification or decisions are needed.
 
-**Core principle:** Claude automates everything with CLI/API. Checkpoints are for verification and decisions, not manual work.
+**Core principle:** Codex automates everything with CLI/API. Checkpoints are for verification and decisions, not manual work.
 
 **Golden rules:**
-1. **If Claude can run it, Claude runs it** - Never ask user to execute CLI commands, start servers, or run builds
-2. **Claude sets up the verification environment** - Start dev servers, seed databases, configure env vars
+1. **If Codex can run it, Codex runs it** - Never ask user to execute CLI commands, start servers, or run builds
+2. **Codex sets up the verification environment** - Start dev servers, seed databases, configure env vars
 3. **User only does what requires human judgment** - Visual checks, UX evaluation, "does this feel right?"
-4. **Secrets come from user, automation comes from Claude** - Ask for API keys, then Claude uses them via CLI
+4. **Secrets come from user, automation comes from Codex** - Ask for API keys, then Codex uses them via CLI
 </overview>
 
 <checkpoint_types>
@@ -15,7 +15,7 @@ Plans execute autonomously. Checkpoints formalize interaction points where human
 <type name="human-verify">
 ## checkpoint:human-verify (Most Common - 90%)
 
-**When:** Claude completed automated work, human confirms it works correctly.
+**When:** Codex completed automated work, human confirms it works correctly.
 
 **Use for:**
 - Visual UI checks (layout, styling, responsiveness)
@@ -28,7 +28,7 @@ Plans execute autonomously. Checkpoints formalize interaction points where human
 **Structure:**
 ```xml
 <task type="checkpoint:human-verify" gate="blocking">
-  <what-built>[What Claude automated and deployed/built]</what-built>
+  <what-built>[What Codex automated and deployed/built]</what-built>
   <how-to-verify>
     [Exact steps to test - URLs, commands, expected behavior]
   </how-to-verify>
@@ -36,7 +36,7 @@ Plans execute autonomously. Checkpoints formalize interaction points where human
 </task>
 ```
 
-**Example: UI Component (shows key pattern: Claude starts server BEFORE checkpoint)**
+**Example: UI Component (shows key pattern: Codex starts server BEFORE checkpoint)**
 ```xml
 <task type="auto">
   <name>Build responsive dashboard layout</name>
@@ -184,10 +184,10 @@ Plans execute autonomously. Checkpoints formalize interaction points where human
 <type name="human-action">
 ## checkpoint:human-action (1% - Rare)
 
-**When:** Action has NO CLI/API and requires human-only interaction, OR Claude hit an authentication gate during automation.
+**When:** Action has NO CLI/API and requires human-only interaction, OR Codex hit an authentication gate during automation.
 
 **Use ONLY for:**
-- **Authentication gates** - Claude tried CLI/API but needs credentials (this is NOT a failure)
+- **Authentication gates** - Codex tried CLI/API but needs credentials (this is NOT a failure)
 - Email verification links (clicking email)
 - SMS 2FA codes (phone verification)
 - Manual account approvals (platform requires human review)
@@ -203,12 +203,12 @@ Plans execute autonomously. Checkpoints formalize interaction points where human
 **Structure:**
 ```xml
 <task type="checkpoint:human-action" gate="blocking">
-  <action>[What human must do - Claude already did everything automatable]</action>
+  <action>[What human must do - Codex already did everything automatable]</action>
   <instructions>
-    [What Claude already automated]
+    [What Codex already automated]
     [The ONE thing requiring human action]
   </instructions>
-  <verification>[What Claude can check afterward]</verification>
+  <verification>[What Codex can check afterward]</verification>
   <resume-signal>[How to continue]</resume-signal>
 </task>
 ```
@@ -242,7 +242,7 @@ Plans execute autonomously. Checkpoints formalize interaction points where human
   <verify>vercel ls shows deployment, curl returns 200</verify>
 </task>
 
-<!-- If vercel returns "Error: Not authenticated", Claude creates checkpoint on the fly -->
+<!-- If vercel returns "Error: Not authenticated", Codex creates checkpoint on the fly -->
 
 <task type="checkpoint:human-action" gate="blocking">
   <action>Authenticate Vercel CLI so I can continue deployment</action>
@@ -255,7 +255,7 @@ Plans execute autonomously. Checkpoints formalize interaction points where human
   <resume-signal>Type "done" when authenticated</resume-signal>
 </task>
 
-<!-- After authentication, Claude retries the deployment -->
+<!-- After authentication, Codex retries the deployment -->
 
 <task type="auto">
   <name>Retry Vercel deployment</name>
@@ -264,13 +264,13 @@ Plans execute autonomously. Checkpoints formalize interaction points where human
 </task>
 ```
 
-**Key distinction:** Auth gates are created dynamically when Claude encounters auth errors. NOT pre-planned — Claude automates first, asks for credentials only when blocked.
+**Key distinction:** Auth gates are created dynamically when Codex encounters auth errors. NOT pre-planned — Codex automates first, asks for credentials only when blocked.
 </type>
 </checkpoint_types>
 
 <execution_protocol>
 
-When Claude encounters `type="checkpoint:*"`:
+When Codex encounters `type="checkpoint:*"`:
 
 1. **Stop immediately** - do not proceed to next task
 2. **Display checkpoint clearly** using the format below
@@ -358,9 +358,9 @@ I'll verify: vercel whoami returns your account
 
 <authentication_gates>
 
-**Auth gate = Claude tried CLI/API, got auth error.** Not a failure — a gate requiring human input to unblock.
+**Auth gate = Codex tried CLI/API, got auth error.** Not a failure — a gate requiring human input to unblock.
 
-**Pattern:** Claude tries automation → auth error → creates checkpoint:human-action → user authenticates → Claude retries → continues
+**Pattern:** Codex tries automation → auth error → creates checkpoint:human-action → user authenticates → Codex retries → continues
 
 **Gate protocol:**
 1. Recognize it's not a failure - missing auth is expected
@@ -372,14 +372,14 @@ I'll verify: vercel whoami returns your account
 7. Continue normally
 
 **Key distinction:**
-- Pre-planned checkpoint: "I need you to do X" (wrong - Claude should automate)
+- Pre-planned checkpoint: "I need you to do X" (wrong - Codex should automate)
 - Auth gate: "I tried to automate X but need credentials" (correct - unblocks automation)
 
 </authentication_gates>
 
 <automation_reference>
 
-**The rule:** If it has CLI/API, Claude does it. Never ask human to perform automatable work.
+**The rule:** If it has CLI/API, Codex does it. Never ask human to perform automatable work.
 
 ## Service CLI Reference
 
@@ -419,7 +419,7 @@ I'll verify: vercel whoami returns your account
   <instructions>Go to dashboard.convex.dev → Settings → Environment Variables → Add</instructions>
 </task>
 
-<!-- RIGHT: Claude asks for value, then adds via CLI -->
+<!-- RIGHT: Codex asks for value, then adds via CLI -->
 <task type="checkpoint:human-action">
   <action>Provide your OpenAI API key</action>
   <instructions>
@@ -512,7 +512,7 @@ timeout 30 bash -c 'until curl -s localhost:3000 > /dev/null 2>&1; do sleep 1; d
 
 ## Automatable Quick Reference
 
-| Action | Automatable? | Claude does it? |
+| Action | Automatable? | Codex does it? |
 |--------|--------------|-----------------|
 | Deploy to Vercel | Yes (`vercel`) | YES |
 | Create Stripe webhook | Yes (API) | YES |
@@ -541,13 +541,13 @@ timeout 30 bash -c 'until curl -s localhost:3000 > /dev/null 2>&1; do sleep 1; d
 - Provide context: why this checkpoint exists
 
 **DON'T:**
-- Ask human to do work Claude can automate ❌
+- Ask human to do work Codex can automate ❌
 - Assume knowledge: "Configure the usual settings" ❌
 - Skip steps: "Set up database" (too vague) ❌
 - Mix multiple verifications in one checkpoint ❌
 
 **Placement:**
-- **After automation completes** - not before Claude does the work
+- **After automation completes** - not before Codex does the work
 - **After UI buildout** - before declaring phase complete
 - **Before dependent work** - decisions before implementation
 - **At integration points** - after configuring external services
@@ -577,7 +577,7 @@ timeout 30 bash -c 'until curl -s localhost:3000 > /dev/null 2>&1; do sleep 1; d
   <done>Redis database created and configured</done>
 </task>
 
-<!-- NO CHECKPOINT NEEDED - Claude automated everything and verified programmatically -->
+<!-- NO CHECKPOINT NEEDED - Codex automated everything and verified programmatically -->
 ```
 
 ### Example 2: Full Auth Flow (Single checkpoint at end)
@@ -642,9 +642,9 @@ timeout 30 bash -c 'until curl -s localhost:3000 > /dev/null 2>&1; do sleep 1; d
 </task>
 ```
 
-**Why bad:** Claude can run `npm run dev`. User should only visit URLs, not execute commands.
+**Why bad:** Codex can run `npm run dev`. User should only visit URLs, not execute commands.
 
-### ✅ GOOD: Claude starts server, user visits
+### ✅ GOOD: Codex starts server, user visits
 
 ```xml
 <task type="auto">
@@ -663,7 +663,7 @@ timeout 30 bash -c 'until curl -s localhost:3000 > /dev/null 2>&1; do sleep 1; d
 </task>
 ```
 
-### ❌ BAD: Asking human to deploy / ✅ GOOD: Claude automates
+### ❌ BAD: Asking human to deploy / ✅ GOOD: Codex automates
 
 ```xml
 <!-- BAD: Asking user to deploy via dashboard -->
@@ -672,7 +672,7 @@ timeout 30 bash -c 'until curl -s localhost:3000 > /dev/null 2>&1; do sleep 1; d
   <instructions>Visit vercel.com/new → Import repo → Click Deploy → Copy URL</instructions>
 </task>
 
-<!-- GOOD: Claude deploys, user verifies -->
+<!-- GOOD: Codex deploys, user verifies -->
 <task type="auto">
   <name>Deploy to Vercel</name>
   <action>Run `vercel --yes`. Capture URL.</action>
@@ -741,7 +741,7 @@ timeout 30 bash -c 'until curl -s localhost:3000 > /dev/null 2>&1; do sleep 1; d
 </task>
 ```
 
-**Why bad:** Claude can run these commands. User should never execute CLI commands.
+**Why bad:** Codex can run these commands. User should never execute CLI commands.
 
 ### ❌ BAD: Asking user to copy values between services
 
@@ -752,7 +752,7 @@ timeout 30 bash -c 'until curl -s localhost:3000 > /dev/null 2>&1; do sleep 1; d
 </task>
 ```
 
-**Why bad:** Stripe has an API. Claude should create the webhook via API and write to .env directly.
+**Why bad:** Stripe has an API. Codex should create the webhook via API and write to .env directly.
 
 </anti_patterns>
 
@@ -760,16 +760,16 @@ timeout 30 bash -c 'until curl -s localhost:3000 > /dev/null 2>&1; do sleep 1; d
 
 Checkpoints formalize human-in-the-loop points for verification and decisions, not manual work.
 
-**The golden rule:** If Claude CAN automate it, Claude MUST automate it.
+**The golden rule:** If Codex CAN automate it, Codex MUST automate it.
 
 **Checkpoint priority:**
-1. **checkpoint:human-verify** (90%) - Claude automated everything, human confirms visual/functional correctness
+1. **checkpoint:human-verify** (90%) - Codex automated everything, human confirms visual/functional correctness
 2. **checkpoint:decision** (9%) - Human makes architectural/technology choices
 3. **checkpoint:human-action** (1%) - Truly unavoidable manual steps with no API/CLI
 
 **When NOT to use checkpoints:**
-- Things Claude can verify programmatically (tests, builds)
-- File operations (Claude can read files)
+- Things Codex can verify programmatically (tests, builds)
+- File operations (Codex can read files)
 - Code correctness (tests and static analysis)
 - Anything automatable via CLI/API
 </summary>

package/get-shit-done/references/decimal-phase-calculation.md

@@ -6,7 +6,7 @@ Calculate the next decimal phase number for urgent insertions.
 
 ```bash
 # Get next decimal phase after phase 6
-node ~/.claude/get-shit-done/bin/gsd-tools.cjs phase next-decimal 6
+node ~/.codex/get-shit-done/bin/gsd-tools.cjs phase next-decimal 6
 ```
 
 Output:
@@ -32,14 +32,14 @@ With existing decimals:
 ## Extract Values
 
 ```bash
-DECIMAL_INFO=$(node ~/.claude/get-shit-done/bin/gsd-tools.cjs phase next-decimal "${AFTER_PHASE}")
+DECIMAL_INFO=$(node ~/.codex/get-shit-done/bin/gsd-tools.cjs phase next-decimal "${AFTER_PHASE}")
 DECIMAL_PHASE=$(echo "$DECIMAL_INFO" | jq -r '.next')
 BASE_PHASE=$(echo "$DECIMAL_INFO" | jq -r '.base_phase')
 ```
 
 Or with --raw flag:
 ```bash
-DECIMAL_PHASE=$(node ~/.claude/get-shit-done/bin/gsd-tools.cjs phase next-decimal "${AFTER_PHASE}" --raw)
+DECIMAL_PHASE=$(node ~/.codex/get-shit-done/bin/gsd-tools.cjs phase next-decimal "${AFTER_PHASE}" --raw)
 # Returns just: 06.1
 ```
 
@@ -57,7 +57,7 @@ DECIMAL_PHASE=$(node ~/.claude/get-shit-done/bin/gsd-tools.cjs phase next-decima
 Decimal phase directories use the full decimal number:
 
 ```bash
-SLUG=$(node ~/.claude/get-shit-done/bin/gsd-tools.cjs generate-slug "$DESCRIPTION" --raw)
+SLUG=$(node ~/.codex/get-shit-done/bin/gsd-tools.cjs generate-slug "$DESCRIPTION" --raw)
 PHASE_DIR=".planning/phases/${DECIMAL_PHASE}-${SLUG}"
 mkdir -p "$PHASE_DIR"
 ```

package/get-shit-done/references/git-integration.md

@@ -51,7 +51,7 @@ Phases:
 What to commit:
 
 ```bash
-node ~/.claude/get-shit-done/bin/gsd-tools.cjs commit "docs: initialize [project-name] ([N] phases)" --files .planning/
+node ~/.codex/get-shit-done/bin/gsd-tools.cjs commit "docs: initialize [project-name] ([N] phases)" --files .planning/
 ```
 
 </format>
@@ -129,7 +129,7 @@ SUMMARY: .planning/phases/XX-name/{phase}-{plan}-SUMMARY.md
 What to commit:
 
 ```bash
-node ~/.claude/get-shit-done/bin/gsd-tools.cjs commit "docs({phase}-{plan}): complete [plan-name] plan" --files .planning/phases/XX-name/{phase}-{plan}-PLAN.md .planning/phases/XX-name/{phase}-{plan}-SUMMARY.md .planning/STATE.md .planning/ROADMAP.md
+node ~/.codex/get-shit-done/bin/gsd-tools.cjs commit "docs({phase}-{plan}): complete [plan-name] plan" --files .planning/phases/XX-name/{phase}-{plan}-PLAN.md .planning/phases/XX-name/{phase}-{plan}-SUMMARY.md .planning/STATE.md .planning/ROADMAP.md
 ```
 
 **Note:** Code files NOT included - already committed per-task.
@@ -149,7 +149,7 @@ Current: [task name]
 What to commit:
 
 ```bash
-node ~/.claude/get-shit-done/bin/gsd-tools.cjs commit "wip: [phase-name] paused at task [X]/[Y]" --files .planning/
+node ~/.codex/get-shit-done/bin/gsd-tools.cjs commit "wip: [phase-name] paused at task [X]/[Y]" --files .planning/
 ```
 
 </format>
@@ -225,14 +225,14 @@ Each plan produces 2-4 commits (tasks + metadata). Clear, granular, bisectable.
 ## Why Per-Task Commits?
 
 **Context engineering for AI:**
-- Git history becomes primary context source for future Claude sessions
+- Git history becomes primary context source for future Codex sessions
 - `git log --grep="{phase}-{plan}"` shows all work for a plan
 - `git diff <hash>^..<hash>` shows exact changes per task
 - Less reliance on parsing SUMMARY.md = more context for actual work
 
 **Failure recovery:**
 - Task 1 committed ✅, Task 2 failed ❌
-- Claude in next session: sees task 1 complete, can retry task 2
+- Codex in next session: sees task 1 complete, can retry task 2
 - Can `git reset --hard` to last successful task
 
 **Debugging:**
@@ -241,8 +241,8 @@ Each plan produces 2-4 commits (tasks + metadata). Clear, granular, bisectable.
 - Each commit is independently revertable
 
 **Observability:**
-- Solo developer + Claude workflow benefits from granular attribution
+- Solo developer + Codex workflow benefits from granular attribution
 - Atomic commits are git best practice
-- "Commit noise" irrelevant when consumer is Claude, not humans
+- "Commit noise" irrelevant when consumer is Codex, not humans
 
 </commit_strategy_rationale>

package/get-shit-done/references/git-planning-commit.md

@@ -7,7 +7,7 @@ Commit planning artifacts using the gsd-tools CLI, which automatically checks `c
 Always use `gsd-tools.cjs commit` for `.planning/` files — it handles `commit_docs` and gitignore checks automatically:
 
 ```bash
-node ~/.claude/get-shit-done/bin/gsd-tools.cjs commit "docs({scope}): {description}" --files .planning/STATE.md .planning/ROADMAP.md
+node ~/.codex/get-shit-done/bin/gsd-tools.cjs commit "docs({scope}): {description}" --files .planning/STATE.md .planning/ROADMAP.md
 ```
 
 The CLI will return `skipped` (with reason) if `commit_docs` is `false` or `.planning/` is gitignored. No manual conditional checks needed.
@@ -17,7 +17,7 @@ The CLI will return `skipped` (with reason) if `commit_docs` is `false` or `.pla
 To fold `.planning/` file changes into the previous commit:
 
 ```bash
-node ~/.claude/get-shit-done/bin/gsd-tools.cjs commit "" --files .planning/codebase/*.md --amend
+node ~/.codex/get-shit-done/bin/gsd-tools.cjs commit "" --files .planning/codebase/*.md --amend
 ```
 
 ## Commit Message Patterns

package/get-shit-done/references/model-profile-resolution.md

@@ -12,7 +12,7 @@ Default: `balanced` if not set or config missing.
 
 ## Lookup Table
 
-@~/.claude/get-shit-done/references/model-profiles.md
+@~/.codex/get-shit-done/references/model-profiles.md
 
 Look up the agent in the table for the resolved profile. Pass the model parameter to Task calls:
 

package/get-shit-done/references/model-profiles.md

@@ -1,6 +1,6 @@
 # Model Profiles
 
-Model profiles control which Claude model each GSD agent uses. This allows balancing quality vs token spend.
+Model profiles control which Codex model each GSD agent uses. This allows balancing quality vs token spend.
 
 ## Profile Definitions
 
@@ -89,4 +89,4 @@ Verification requires goal-backward reasoning - checking if code *delivers* what
 Read-only exploration and pattern extraction. No reasoning required, just structured output from file contents.
 
 **Why `inherit` instead of passing `opus` directly?**
-Claude Code's `"opus"` alias maps to a specific model version. Organizations may block older opus versions while allowing newer ones. GSD returns `"inherit"` for opus-tier agents, causing them to use whatever opus version the user has configured in their session. This avoids version conflicts and silent fallbacks to Sonnet.
+Codex CLI's `"opus"` alias maps to a specific model version. Organizations may block older opus versions while allowing newer ones. GSD returns `"inherit"` for opus-tier agents, causing them to use whatever opus version the user has configured in their session. This avoids version conflicts and silent fallbacks to Sonnet.

package/get-shit-done/references/phase-argument-parsing.md

@@ -14,7 +14,7 @@ From `$ARGUMENTS`:
 The `find-phase` command handles normalization and validation in one step:
 
 ```bash
-PHASE_INFO=$(node ~/.claude/get-shit-done/bin/gsd-tools.cjs find-phase "${PHASE}")
+PHASE_INFO=$(node ~/.codex/get-shit-done/bin/gsd-tools.cjs find-phase "${PHASE}")
 ```
 
 Returns JSON with:
@@ -45,7 +45,7 @@ fi
 Use `roadmap get-phase` to validate phase exists:
 
 ```bash
-PHASE_CHECK=$(node ~/.claude/get-shit-done/bin/gsd-tools.cjs roadmap get-phase "${PHASE}")
+PHASE_CHECK=$(node ~/.codex/get-shit-done/bin/gsd-tools.cjs roadmap get-phase "${PHASE}")
 if [ "$(echo "$PHASE_CHECK" | jq -r '.found')" = "false" ]; then
   echo "ERROR: Phase ${PHASE} not found in roadmap"
   exit 1
@@ -57,5 +57,5 @@ fi
 Use `find-phase` for directory lookup:
 
 ```bash
-PHASE_DIR=$(node ~/.claude/get-shit-done/bin/gsd-tools.cjs find-phase "${PHASE}" --raw)
+PHASE_DIR=$(node ~/.codex/get-shit-done/bin/gsd-tools.cjs find-phase "${PHASE}" --raw)
 ```

package/get-shit-done/references/planning-config.md

@@ -40,14 +40,14 @@ Configuration options for `.planning/` directory behavior.
 
 ```bash
 # Commit with automatic commit_docs + gitignore checks:
-node ~/.claude/get-shit-done/bin/gsd-tools.cjs commit "docs: update state" --files .planning/STATE.md
+node ~/.codex/get-shit-done/bin/gsd-tools.cjs commit "docs: update state" --files .planning/STATE.md
 
 # Load config via state load (returns JSON):
-INIT=$(node ~/.claude/get-shit-done/bin/gsd-tools.cjs state load)
+INIT=$(node ~/.codex/get-shit-done/bin/gsd-tools.cjs state load)
 # commit_docs is available in the JSON output
 
 # Or use init commands which include commit_docs:
-INIT=$(node ~/.claude/get-shit-done/bin/gsd-tools.cjs init execute-phase "1")
+INIT=$(node ~/.codex/get-shit-done/bin/gsd-tools.cjs init execute-phase "1")
 # commit_docs is included in all init command outputs
 ```
 
@@ -56,7 +56,7 @@ INIT=$(node ~/.claude/get-shit-done/bin/gsd-tools.cjs init execute-phase "1")
 **Commit via CLI (handles checks automatically):**
 
 ```bash
-node ~/.claude/get-shit-done/bin/gsd-tools.cjs commit "docs: update state" --files .planning/STATE.md
+node ~/.codex/get-shit-done/bin/gsd-tools.cjs commit "docs: update state" --files .planning/STATE.md
 ```
 
 The CLI checks `commit_docs` config and gitignore status internally — no manual conditionals needed.
@@ -144,13 +144,13 @@ To use uncommitted mode:
 
 Use `init execute-phase` which returns all config as JSON:
 ```bash
-INIT=$(node ~/.claude/get-shit-done/bin/gsd-tools.cjs init execute-phase "1")
+INIT=$(node ~/.codex/get-shit-done/bin/gsd-tools.cjs init execute-phase "1")
 # JSON output includes: branching_strategy, phase_branch_template, milestone_branch_template
 ```
 
 Or use `state load` for the config values:
 ```bash
-INIT=$(node ~/.claude/get-shit-done/bin/gsd-tools.cjs state load)
+INIT=$(node ~/.codex/get-shit-done/bin/gsd-tools.cjs state load)
 # Parse branching_strategy, phase_branch_template, milestone_branch_template from JSON
 ```
 

package/get-shit-done/references/questioning.md

@@ -138,7 +138,7 @@ Loop until "Create PROJECT.md" selected.
 - **Rushing** — Minimizing questions to get to "the work"
 - **Shallow acceptance** — Taking vague answers without probing
 - **Premature constraints** — Asking about tech stack before understanding the idea
-- **User skills** — NEVER ask about user's technical experience. Claude builds.
+- **User skills** — NEVER ask about user's technical experience. Codex builds.
 
 </anti_patterns>
 

package/get-shit-done/references/verification-patterns.md

@@ -600,10 +600,10 @@ Some things can't be verified programmatically. Flag these for human testing:
 
 For automation-first checkpoint patterns, server lifecycle management, CLI installation handling, and error recovery protocols, see:
 
-**@~/.claude/get-shit-done/references/checkpoints.md** → `<automation_reference>` section
+**@~/.codex/get-shit-done/references/checkpoints.md** → `<automation_reference>` section
 
 Key principles:
-- Claude sets up verification environment BEFORE presenting checkpoints
+- Codex sets up verification environment BEFORE presenting checkpoints
 - Users never run CLI commands (visit URLs only)
 - Server lifecycle: start before checkpoint, handle port conflicts, keep running for duration
 - CLI installation: auto-install where safe, checkpoint for user choice otherwise

package/get-shit-done/templates/DEBUG.md

@@ -67,8 +67,8 @@ files_changed: []
 
 **Current Focus:**
 - OVERWRITE entirely on each update
-- Always reflects what Claude is doing RIGHT NOW
-- If Claude reads this after /clear, it knows exactly where to resume
+- Always reflects what Codex is doing RIGHT NOW
+- If Codex reads this after /clear, it knows exactly where to resume
 - Fields: hypothesis, test, expecting, next_action
 
 **Symptoms:**
@@ -135,7 +135,7 @@ files_changed: []
 
 <resume_behavior>
 
-When Claude reads this file after /clear:
+When Codex reads this file after /clear:
 
 1. Parse frontmatter → know status
 2. Read Current Focus → know exactly what was happening
@@ -143,7 +143,7 @@ When Claude reads this file after /clear:
 4. Read Evidence → know what's been learned
 5. Continue from next_action
 
-The file IS the debugging brain. Claude should be able to resume perfectly from any interruption point.
+The file IS the debugging brain. Codex should be able to resume perfectly from any interruption point.
 
 </resume_behavior>
 

package/get-shit-done/templates/codebase/architecture.md

@@ -238,7 +238,7 @@ Template for `.planning/codebase/ARCHITECTURE.md` - captures conceptual code org
 - Implementation details of specific features
 
 **File paths ARE welcome:**
-Include file paths as concrete examples of abstractions. Use backtick formatting: `src/services/user.ts`. This makes the architecture document actionable for Claude when planning.
+Include file paths as concrete examples of abstractions. Use backtick formatting: `src/services/user.ts`. This makes the architecture document actionable for Codex when planning.
 
 **When filling this template:**
 - Read main entry points (index, server, main)

package/get-shit-done/templates/codebase/concerns.md

@@ -302,7 +302,7 @@ Template for `.planning/codebase/CONCERNS.md` - captures known issues and areas
 - Estimating risk of changes
 - Understanding where to be careful
 - Prioritizing improvements
-- Onboarding new Claude contexts
+- Onboarding new Codex contexts
 - Planning refactoring work
 
 **How this gets populated:**

package/get-shit-done/templates/codebase/conventions.md

@@ -2,7 +2,7 @@
 
 Template for `.planning/codebase/CONVENTIONS.md` - captures coding style and patterns.
 
-**Purpose:** Document how code is written in this codebase. Prescriptive guide for Claude to match existing style.
+**Purpose:** Document how code is written in this codebase. Prescriptive guide for Codex to match existing style.
 
 ---
 

package/get-shit-done/templates/codebase/structure.md

@@ -146,7 +146,7 @@ get-shit-done/
 - Subdirectories: None
 
 **commands/gsd/**
-- Purpose: Slash command definitions for Claude Code
+- Purpose: Slash command definitions for Codex CLI
 - Contains: *.md files (one per command)
 - Key files: new-project.md, plan-phase.md, execute-plan.md
 - Subdirectories: None (flat structure)
@@ -186,14 +186,14 @@ get-shit-done/
 
 **Documentation:**
 - `README.md` - User-facing installation and usage guide
-- `CLAUDE.md` - Instructions for Claude Code when working in this repo
+- `CODEX.md` - Instructions for Codex CLI when working in this repo
 
 ## Naming Conventions
 
 **Files:**
 - kebab-case.md: Markdown documents
 - kebab-case.js: JavaScript source files
-- UPPERCASE.md: Important project files (README, CLAUDE, CHANGELOG)
+- UPPERCASE.md: Important project files (README, CODEX, CHANGELOG)
 
 **Directories:**
 - kebab-case: All directories
@@ -216,7 +216,7 @@ get-shit-done/
 
 **New Workflow:**
 - Implementation: `get-shit-done/workflows/{name}.md`
-- Usage: Reference from command with `@~/.claude/get-shit-done/workflows/{name}.md`
+- Usage: Reference from command with `@~/.codex/get-shit-done/workflows/{name}.md`
 
 **New Reference Document:**
 - Implementation: `get-shit-done/references/{name}.md`
@@ -229,12 +229,12 @@ get-shit-done/
 ## Special Directories
 
 **get-shit-done/**
-- Purpose: Resources installed to ~/.claude/
+- Purpose: Resources installed to ~/.codex/
 - Source: Copied by bin/install.js during installation
 - Committed: Yes (source of truth)
 
 **commands/**
-- Purpose: Slash commands installed to ~/.claude/commands/
+- Purpose: Slash commands installed to ~/.codex/commands/
 - Source: Copied by bin/install.js during installation
 - Committed: Yes (source of truth)