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

package/README.md

@@ -19,7 +19,7 @@ get-shit-done-codex (GSD) solves context rot — the quality degradation that ha
 ## Installation
 
 ```bash
-npx @undeemed/get-shit-done-codex
+npx @undeemed/get-shit-done-codex@latest
 ```
 
 You'll be prompted to install globally (`~/.codex/`) or locally (`./`).
@@ -45,6 +45,20 @@ npx @undeemed/get-shit-done-codex@latest --global
 
 The installer now writes a `get-shit-done/VERSION` file so `/prompts:gsd-update` can detect installed vs latest and show changelog before updating.
 
+## npm Trusted Publisher (OIDC)
+
+This repo includes a GitHub Actions publish workflow at:
+
+- `.github/workflows/publish.yml`
+
+When setting up npm Trusted Publisher for this package, use:
+
+- **Publisher:** `GitHub Actions`
+- **Organization or user:** `undeemed`
+- **Repository:** `get-shit-done-codex`
+- **Workflow filename:** `publish.yml`
+- **Environment name:** leave blank (unless you later bind this workflow to a specific GitHub Environment)
+
 ## Quick Start
 
 ```bash
@@ -184,10 +198,10 @@ The original repository contains:
 - Best practices and examples
 - Architecture and design principles
 
-**Note:** The original README is written for Claude Code. When following it, remember that this fork uses:
+**Note:** The original README is written for Codex CLI. When following it, remember that this fork uses:
 - `/prompts:gsd-*` command format (instead of `/gsd:*`)
-- Codex CLI (instead of Claude Code)
-- `~/.codex/` directory (instead of `~/.claude/`)
+- Codex CLI (instead of Codex CLI)
+- `~/.codex/` directory (instead of `~/.codex/`)
 
 ## Credits
 

package/agents/gsd-codebase-mapper.md

@@ -55,13 +55,13 @@ Your job: Explore thoroughly, then write document(s) directly. Return confirmati
 Include enough detail to be useful as reference. A 200-line TESTING.md with real patterns is more valuable than a 74-line summary.
 
 **Always include file paths:**
-Vague descriptions like "UserService handles users" are not actionable. Always include actual file paths formatted with backticks: `src/services/user.ts`. This allows Claude to navigate directly to relevant code.
+Vague descriptions like "UserService handles users" are not actionable. Always include actual file paths formatted with backticks: `src/services/user.ts`. This allows Codex to navigate directly to relevant code.
 
 **Write current state only:**
 Describe only what IS, never what WAS or what you considered. No temporal language.
 
 **Be prescriptive, not descriptive:**
-Your documents guide future Claude instances writing code. "Use X pattern" is more useful than "X pattern is used."
+Your documents guide future Codex instances writing code. "Use X pattern" is more useful than "X pattern is used."
 </philosophy>
 
 <process>

package/agents/gsd-debugger.md

@@ -24,7 +24,7 @@ Your job: Find the root cause through hypothesis testing, maintain debug file st
 
 <philosophy>
 
-## User = Reporter, Claude = Investigator
+## User = Reporter, Codex = Investigator
 
 The user knows:
 - What they expected to happen
@@ -982,7 +982,7 @@ mv .planning/debug/{slug}.md .planning/debug/resolved/
 **Check planning config using state load (commit_docs is available from the output):**
 
 ```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)
 # commit_docs is in the JSON output
 ```
 
@@ -999,7 +999,7 @@ Root cause: {root_cause}"
 
 Then commit planning docs via CLI (respects `commit_docs` config automatically):
 ```bash
-node ~/.claude/get-shit-done/bin/gsd-tools.cjs commit "docs: resolve debug {slug}" --files .planning/debug/resolved/{slug}.md
+node ~/.codex/get-shit-done/bin/gsd-tools.cjs commit "docs: resolve debug {slug}" --files .planning/debug/resolved/{slug}.md
 ```
 
 Report completion and offer next steps.

package/agents/gsd-executor.md

@@ -19,7 +19,7 @@ Your job: Execute the plan completely, commit each task, create SUMMARY.md, upda
 Load execution context:
 
 ```bash
-INIT=$(node ~/.claude/get-shit-done/bin/gsd-tools.cjs init execute-phase "${PHASE}")
+INIT=$(node ~/.codex/get-shit-done/bin/gsd-tools.cjs init execute-phase "${PHASE}")
 ```
 
 Extract from init JSON: `executor_model`, `commit_docs`, `phase_dir`, `plans`, `incomplete_plans`.
@@ -175,9 +175,9 @@ Track auto-fix attempts per task. After 3 auto-fix attempts on a single task:
 Before any `checkpoint:human-verify`, ensure verification environment is ready. If plan lacks server startup before checkpoint, ADD ONE (deviation Rule 3).
 
 For full automation-first patterns, server lifecycle, CLI handling:
-**See @~/.claude/get-shit-done/references/checkpoints.md**
+**See @~/.codex/get-shit-done/references/checkpoints.md**
 
-**Quick reference:** Users NEVER run CLI commands. Users ONLY visit URLs, click UI, evaluate visuals, provide secrets. Claude does all automation.
+**Quick reference:** Users NEVER run CLI commands. Users ONLY visit URLs, click UI, evaluate visuals, provide secrets. Codex does all automation.
 
 ---
 
@@ -290,7 +290,7 @@ After all tasks complete, create `{phase}-{plan}-SUMMARY.md` at `.planning/phase
 
 **ALWAYS use the Write tool to create files** — never use `Bash(cat << 'EOF')` or heredoc commands for file creation.
 
-**Use template:** @~/.claude/get-shit-done/templates/summary.md
+**Use template:** @~/.codex/get-shit-done/templates/summary.md
 
 **Frontmatter:** phase, plan, subsystem, tags, dependency graph (requires/provides/affects), tech-stack (added/patterns), key-files (created/modified), decisions, metrics (duration, completed date).
 
@@ -343,24 +343,24 @@ After SUMMARY.md, update STATE.md using gsd-tools:
 
 ```bash
 # Advance plan counter (handles edge cases automatically)
-node ~/.claude/get-shit-done/bin/gsd-tools.cjs state advance-plan
+node ~/.codex/get-shit-done/bin/gsd-tools.cjs state advance-plan
 
 # Recalculate progress bar from disk state
-node ~/.claude/get-shit-done/bin/gsd-tools.cjs state update-progress
+node ~/.codex/get-shit-done/bin/gsd-tools.cjs state update-progress
 
 # Record execution metrics
-node ~/.claude/get-shit-done/bin/gsd-tools.cjs state record-metric \
+node ~/.codex/get-shit-done/bin/gsd-tools.cjs state record-metric \
   --phase "${PHASE}" --plan "${PLAN}" --duration "${DURATION}" \
   --tasks "${TASK_COUNT}" --files "${FILE_COUNT}"
 
 # Add decisions (extract from SUMMARY.md key-decisions)
 for decision in "${DECISIONS[@]}"; do
-  node ~/.claude/get-shit-done/bin/gsd-tools.cjs state add-decision \
+  node ~/.codex/get-shit-done/bin/gsd-tools.cjs state add-decision \
     --phase "${PHASE}" --summary "${decision}"
 done
 
 # Update session info
-node ~/.claude/get-shit-done/bin/gsd-tools.cjs state record-session \
+node ~/.codex/get-shit-done/bin/gsd-tools.cjs state record-session \
   --stopped-at "Completed ${PHASE}-${PLAN}-PLAN.md"
 ```
 
@@ -375,13 +375,13 @@ node ~/.claude/get-shit-done/bin/gsd-tools.cjs state record-session \
 
 **For blockers found during execution:**
 ```bash
-node ~/.claude/get-shit-done/bin/gsd-tools.cjs state add-blocker "Blocker description"
+node ~/.codex/get-shit-done/bin/gsd-tools.cjs state add-blocker "Blocker description"
 ```
 </state_updates>
 
 <final_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}-SUMMARY.md .planning/STATE.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}-SUMMARY.md .planning/STATE.md
 ```
 
 Separate from per-task commits — captures execution results only.

package/agents/gsd-phase-researcher.md

@@ -24,7 +24,7 @@ Spawned by `/gsd:plan-phase` (integrated) or `/gsd:research-phase` (standalone).
 | Section | How You Use It |
 |---------|----------------|
 | `## Decisions` | Locked choices — research THESE, not alternatives |
-| `## Claude's Discretion` | Your freedom areas — research options, recommend |
+| `## Codex's Discretion` | Your freedom areas — research options, recommend |
 | `## Deferred Ideas` | Out of scope — ignore completely |
 
 If CONTEXT.md exists, it constrains your research scope. Don't explore alternatives to locked decisions.
@@ -49,11 +49,11 @@ Your RESEARCH.md is consumed by `gsd-planner`:
 
 <philosophy>
 
-## Claude's Training as Hypothesis
+## Codex's Training as Hypothesis
 
 Training data is 6-18 months stale. Treat pre-existing knowledge as hypothesis, not fact.
 
-**The trap:** Claude "knows" things confidently, but knowledge may be outdated, incomplete, or wrong.
+**The trap:** Codex "knows" things confidently, but knowledge may be outdated, incomplete, or wrong.
 
 **The discipline:**
 1. **Verify before asserting** — don't state library capabilities without checking Context7 or official docs
@@ -102,7 +102,7 @@ When researching "best library for X": find what the ecosystem actually uses, do
 Check `brave_search` from init context. If `true`, use Brave Search for higher quality results:
 
 ```bash
-node ~/.claude/get-shit-done/bin/gsd-tools.cjs websearch "your query" --limit 10
+node ~/.codex/get-shit-done/bin/gsd-tools.cjs websearch "your query" --limit 10
 ```
 
 **Options:**
@@ -311,7 +311,7 @@ Orchestrator provides: phase number/name, description/goal, requirements, constr
 
 Load phase context using init command:
 ```bash
-INIT=$(node ~/.claude/get-shit-done/bin/gsd-tools.cjs init phase-op "${PHASE}")
+INIT=$(node ~/.codex/get-shit-done/bin/gsd-tools.cjs init phase-op "${PHASE}")
 ```
 
 Extract from init JSON: `phase_dir`, `padded_phase`, `phase_number`, `commit_docs`.
@@ -326,13 +326,13 @@ cat "$phase_dir"/*-CONTEXT.md 2>/dev/null
 | Section | Constraint |
 |---------|------------|
 | **Decisions** | Locked — research THESE deeply, no alternatives |
-| **Claude's Discretion** | Research options, make recommendations |
+| **Codex's Discretion** | Research options, make recommendations |
 | **Deferred Ideas** | Out of scope — ignore completely |
 
 **Examples:**
 - User decided "use library X" → research X deeply, don't explore alternatives
 - User decided "simple UI, no animations" → don't research animation libraries
-- Marked as Claude's discretion → research options and recommend
+- Marked as Codex's discretion → research options and recommend
 
 ## Step 2: Identify Research Domains
 
@@ -369,8 +369,8 @@ For each domain: Context7 first → Official docs → WebSearch → Cross-verify
 ### Locked Decisions
 [Copy verbatim from CONTEXT.md ## Decisions]
 
-### Claude's Discretion
-[Copy verbatim from CONTEXT.md ## Claude's Discretion]
+### Codex's Discretion
+[Copy verbatim from CONTEXT.md ## Codex's Discretion]
 
 ### Deferred Ideas (OUT OF SCOPE)
 [Copy verbatim from CONTEXT.md ## Deferred Ideas]
@@ -384,7 +384,7 @@ Write to: `$PHASE_DIR/$PADDED_PHASE-RESEARCH.md`
 ## Step 6: Commit Research (optional)
 
 ```bash
-node ~/.claude/get-shit-done/bin/gsd-tools.cjs commit "docs($PHASE): research phase domain" --files "$PHASE_DIR/$PADDED_PHASE-RESEARCH.md"
+node ~/.codex/get-shit-done/bin/gsd-tools.cjs commit "docs($PHASE): research phase domain" --files "$PHASE_DIR/$PADDED_PHASE-RESEARCH.md"
 ```
 
 ## Step 7: Return Structured Result

package/agents/gsd-plan-checker.md

@@ -29,7 +29,7 @@ You are NOT the executor or verifier — you verify plans WILL work before execu
 | Section | How You Use It |
 |---------|----------------|
 | `## Decisions` | LOCKED — plans MUST implement these exactly. Flag if contradicted. |
-| `## Claude's Discretion` | Freedom areas — planner can choose approach, don't flag. |
+| `## Codex's Discretion` | Freedom areas — planner can choose approach, don't flag. |
 | `## Deferred Ideas` | Out of scope — plans must NOT include these. Flag if present. |
 
 If CONTEXT.md exists, add verification dimension: **Context Compliance**
@@ -255,7 +255,7 @@ issue:
 **Only check if CONTEXT.md was provided in the verification context.**
 
 **Process:**
-1. Parse CONTEXT.md sections: Decisions, Claude's Discretion, Deferred Ideas
+1. Parse CONTEXT.md sections: Decisions, Codex's Discretion, Deferred Ideas
 2. For each locked Decision, find implementing task(s)
 3. Verify no tasks implement Deferred Ideas (scope creep)
 4. Verify Discretion areas are handled (planner's choice is valid)
@@ -299,7 +299,7 @@ issue:
 
 Load phase operation context:
 ```bash
-INIT=$(node ~/.claude/get-shit-done/bin/gsd-tools.cjs init phase-op "${PHASE_ARG}")
+INIT=$(node ~/.codex/get-shit-done/bin/gsd-tools.cjs init phase-op "${PHASE_ARG}")
 ```
 
 Extract from init JSON: `phase_dir`, `phase_number`, `has_plans`, `plan_count`.
@@ -308,7 +308,7 @@ Orchestrator provides CONTEXT.md content in the verification prompt. If provided
 
 ```bash
 ls "$phase_dir"/*-PLAN.md 2>/dev/null
-node ~/.claude/get-shit-done/bin/gsd-tools.cjs roadmap get-phase "$phase_number"
+node ~/.codex/get-shit-done/bin/gsd-tools.cjs roadmap get-phase "$phase_number"
 ls "$phase_dir"/*-BRIEF.md 2>/dev/null
 ```
 
@@ -321,7 +321,7 @@ Use gsd-tools to validate plan structure:
 ```bash
 for plan in "$PHASE_DIR"/*-PLAN.md; do
   echo "=== $plan ==="
-  PLAN_STRUCTURE=$(node ~/.claude/get-shit-done/bin/gsd-tools.cjs verify plan-structure "$plan")
+  PLAN_STRUCTURE=$(node ~/.codex/get-shit-done/bin/gsd-tools.cjs verify plan-structure "$plan")
   echo "$PLAN_STRUCTURE"
 done
 ```
@@ -339,7 +339,7 @@ Map errors/warnings to verification dimensions:
 Extract must_haves from each plan using gsd-tools:
 
 ```bash
-MUST_HAVES=$(node ~/.claude/get-shit-done/bin/gsd-tools.cjs frontmatter get "$PLAN_PATH" --field must_haves)
+MUST_HAVES=$(node ~/.codex/get-shit-done/bin/gsd-tools.cjs frontmatter get "$PLAN_PATH" --field must_haves)
 ```
 
 Returns JSON: `{ truths: [...], artifacts: [...], key_links: [...] }`
@@ -382,7 +382,7 @@ For each requirement: find covering task(s), verify action is specific, flag gap
 Use gsd-tools plan-structure verification (already run in Step 2):
 
 ```bash
-PLAN_STRUCTURE=$(node ~/.claude/get-shit-done/bin/gsd-tools.cjs verify plan-structure "$PLAN_PATH")
+PLAN_STRUCTURE=$(node ~/.codex/get-shit-done/bin/gsd-tools.cjs verify plan-structure "$PLAN_PATH")
 ```
 
 The `tasks` array in the result shows each task's completeness:

package/agents/gsd-planner.md

@@ -13,7 +13,7 @@ Spawned by:
 - `/gsd:plan-phase --gaps` orchestrator (gap closure from verification failures)
 - `/gsd:plan-phase` in revision mode (updating plans based on checker feedback)
 
-Your job: Produce PLAN.md files that Claude executors can implement without interpretation. Plans are prompts, not documents that become prompts.
+Your job: Produce PLAN.md files that Codex executors can implement without interpretation. Plans are prompts, not documents that become prompts.
 
 **Core responsibilities:**
 - **FIRST: Parse and honor user decisions from CONTEXT.md** (locked decisions are NON-NEGOTIABLE)
@@ -41,7 +41,7 @@ The orchestrator provides user decisions in `<user_decisions>` tags from `/gsd:d
    - If user deferred "search functionality" → NO search tasks allowed
    - If user deferred "dark mode" → NO dark mode tasks allowed
 
-3. **Claude's Discretion (from `## Claude's Discretion`)** — Use your judgment
+3. **Codex's Discretion (from `## Codex's Discretion`)** — Use your judgment
    - Make reasonable choices and document in task actions
 
 **Self-check before returning:** For each plan, verify:
@@ -56,12 +56,12 @@ The orchestrator provides user decisions in `<user_decisions>` tags from `/gsd:d
 
 <philosophy>
 
-## Solo Developer + Claude Workflow
+## Solo Developer + Codex Workflow
 
-Planning for ONE person (the user) and ONE implementer (Claude).
+Planning for ONE person (the user) and ONE implementer (Codex).
 - No teams, stakeholders, ceremonies, coordination overhead
-- User = visionary/product owner, Claude = builder
-- Estimate effort in Claude execution time, not human dev time
+- User = visionary/product owner, Codex = builder
+- Estimate effort in Codex execution time, not human dev time
 
 ## Plans Are Prompts
 
@@ -73,7 +73,7 @@ PLAN.md IS the prompt (not a document that becomes one). Contains:
 
 ## Quality Degradation Curve
 
-| Context Usage | Quality | Claude's State |
+| Context Usage | Quality | Codex's State |
 |---------------|---------|----------------|
 | 0-30% | PEAK | Thorough, comprehensive |
 | 30-50% | GOOD | Confident, solid work |
@@ -151,16 +151,16 @@ Every task has four required fields:
 
 | Type | Use For | Autonomy |
 |------|---------|----------|
-| `auto` | Everything Claude can do independently | Fully autonomous |
+| `auto` | Everything Codex can do independently | Fully autonomous |
 | `checkpoint:human-verify` | Visual/functional verification | Pauses for user |
 | `checkpoint:decision` | Implementation choices | Pauses for user |
 | `checkpoint:human-action` | Truly unavoidable manual steps (rare) | Pauses for user |
 
-**Automation-first rule:** If Claude CAN do it via CLI/API, Claude MUST do it. Checkpoints verify AFTER automation, not replace it.
+**Automation-first rule:** If Codex CAN do it via CLI/API, Codex MUST do it. Checkpoints verify AFTER automation, not replace it.
 
 ## Task Sizing
 
-Each task: **15-60 minutes** Claude execution time.
+Each task: **15-60 minutes** Codex execution time.
 
 | Duration | Action |
 |----------|--------|
@@ -182,7 +182,7 @@ Each task: **15-60 minutes** Claude execution time.
 | "Handle errors" | "Wrap API calls in try/catch, return {error: string} on 4xx/5xx, show toast via sonner on client" |
 | "Set up the database" | "Add User and Project models to schema.prisma with UUID ids, email unique constraint, createdAt/updatedAt timestamps, run prisma db push" |
 
-**Test:** Could a different Claude instance execute without asking clarifying questions? If not, add specificity.
+**Test:** Could a different Codex instance execute without asking clarifying questions? If not, add specificity.
 
 ## TDD Detection
 
@@ -207,7 +207,7 @@ For each external service, determine:
 2. **Account setup** — Does user need to create an account?
 3. **Dashboard config** — What must be configured in external UI?
 
-Record in `user_setup` frontmatter. Only include what Claude literally cannot do. Do NOT surface in planning output — execute-plan handles presentation.
+Record in `user_setup` frontmatter. Only include what Codex literally cannot do. Do NOT surface in planning output — execute-plan handles presentation.
 
 </task_breakdown>
 
@@ -361,8 +361,8 @@ Output: [Artifacts created]
 </objective>
 
 <execution_context>
-@~/.claude/get-shit-done/workflows/execute-plan.md
-@~/.claude/get-shit-done/templates/summary.md
+@~/.codex/get-shit-done/workflows/execute-plan.md
+@~/.codex/get-shit-done/templates/summary.md
 </execution_context>
 
 <context>
@@ -437,7 +437,7 @@ user_setup:
         location: "Stripe Dashboard -> Developers -> Webhooks"
 ```
 
-Only include what Claude literally cannot do.
+Only include what Codex literally cannot do.
 
 </plan_format>
 
@@ -545,13 +545,13 @@ must_haves:
 ## Checkpoint Types
 
 **checkpoint:human-verify (90% of checkpoints)**
-Human confirms Claude's automated work works correctly.
+Human confirms Codex's automated work works correctly.
 
 Use for: Visual UI checks, interactive flows, functional verification, animation/accessibility.
 
 ```xml
 <task type="checkpoint:human-verify" gate="blocking">
-  <what-built>[What Claude automated]</what-built>
+  <what-built>[What Codex automated]</what-built>
   <how-to-verify>
     [Exact steps to test - URLs, commands, expected behavior]
   </how-to-verify>
@@ -588,13 +588,13 @@ Do NOT use for: Deploying (use CLI), creating webhooks (use API), creating datab
 
 ## Authentication Gates
 
-When Claude tries CLI/API and gets auth error → creates checkpoint → user authenticates → Claude retries. Auth gates are created dynamically, NOT pre-planned.
+When Codex tries CLI/API and gets auth error → creates checkpoint → user authenticates → Codex retries. Auth gates are created dynamically, NOT pre-planned.
 
 ## Writing Guidelines
 
 **DO:** Automate everything before checkpoint, be specific ("Visit https://myapp.vercel.app" not "check deployment"), number verification steps, state expected outcomes.
 
-**DON'T:** Ask human to do work Claude can automate, mix multiple verifications, place checkpoints before automation completes.
+**DON'T:** Ask human to do work Codex can automate, mix multiple verifications, place checkpoints before automation completes.
 
 ## Anti-Patterns
 
@@ -605,7 +605,7 @@ When Claude tries CLI/API and gets auth error → creates checkpoint → user au
   <instructions>Visit vercel.com, import repo, click deploy...</instructions>
 </task>
 ```
-Why bad: Vercel has a CLI. Claude should run `vercel --yes`.
+Why bad: Vercel has a CLI. Codex should run `vercel --yes`.
 
 **Bad - Too many checkpoints:**
 ```xml
@@ -794,7 +794,7 @@ Group by plan, dimension, severity.
 ### Step 6: Commit
 
 ```bash
-node ~/.claude/get-shit-done/bin/gsd-tools.cjs commit "fix($PHASE): revise plans based on checker feedback" --files .planning/phases/$PHASE-*/$PHASE-*-PLAN.md
+node ~/.codex/get-shit-done/bin/gsd-tools.cjs commit "fix($PHASE): revise plans based on checker feedback" --files .planning/phases/$PHASE-*/$PHASE-*-PLAN.md
 ```
 
 ### Step 7: Return Revision Summary
@@ -833,7 +833,7 @@ node ~/.claude/get-shit-done/bin/gsd-tools.cjs commit "fix($PHASE): revise plans
 Load planning context:
 
 ```bash
-INIT=$(node ~/.claude/get-shit-done/bin/gsd-tools.cjs init plan-phase "${PHASE}")
+INIT=$(node ~/.codex/get-shit-done/bin/gsd-tools.cjs init plan-phase "${PHASE}")
 ```
 
 Extract from init JSON: `planner_model`, `researcher_model`, `checker_model`, `commit_docs`, `research_enabled`, `phase_dir`, `phase_number`, `has_research`, `has_context`.
@@ -889,7 +889,7 @@ Apply discovery level protocol (see discovery_levels section).
 
 **Step 1 — Generate digest index:**
 ```bash
-node ~/.claude/get-shit-done/bin/gsd-tools.cjs history-digest
+node ~/.codex/get-shit-done/bin/gsd-tools.cjs history-digest
 ```
 
 **Step 2 — Select relevant phases (typically 2-4):**
@@ -1007,7 +1007,7 @@ Include all frontmatter fields.
 Validate each created PLAN.md using gsd-tools:
 
 ```bash
-VALID=$(node ~/.claude/get-shit-done/bin/gsd-tools.cjs frontmatter validate "$PLAN_PATH" --schema plan)
+VALID=$(node ~/.codex/get-shit-done/bin/gsd-tools.cjs frontmatter validate "$PLAN_PATH" --schema plan)
 ```
 
 Returns JSON: `{ valid, missing, present, schema }`
@@ -1020,7 +1020,7 @@ Required plan frontmatter fields:
 Also validate plan structure:
 
 ```bash
-STRUCTURE=$(node ~/.claude/get-shit-done/bin/gsd-tools.cjs verify plan-structure "$PLAN_PATH")
+STRUCTURE=$(node ~/.codex/get-shit-done/bin/gsd-tools.cjs verify plan-structure "$PLAN_PATH")
 ```
 
 Returns JSON: `{ valid, errors, warnings, task_count, tasks }`
@@ -1057,7 +1057,7 @@ Plans:
 
 <step name="git_commit">
 ```bash
-node ~/.claude/get-shit-done/bin/gsd-tools.cjs commit "docs($PHASE): create phase plan" --files .planning/phases/$PHASE-*/$PHASE-*-PLAN.md .planning/ROADMAP.md
+node ~/.codex/get-shit-done/bin/gsd-tools.cjs commit "docs($PHASE): create phase plan" --files .planning/phases/$PHASE-*/$PHASE-*-PLAN.md .planning/ROADMAP.md
 ```
 </step>
 

package/agents/gsd-project-researcher.md

@@ -27,7 +27,7 @@ Your files feed the roadmap:
 
 ## Training Data = Hypothesis
 
-Claude's training is 6-18 months stale. Knowledge may be outdated, incomplete, or wrong.
+Codex's training is 6-18 months stale. Knowledge may be outdated, incomplete, or wrong.
 
 **Discipline:**
 1. **Verify before asserting** — check Context7 or official docs before stating capabilities
@@ -96,7 +96,7 @@ Always include current year. Use multiple query variations. Mark WebSearch-only
 Check `brave_search` from orchestrator context. If `true`, use Brave Search for higher quality results:
 
 ```bash
-node ~/.claude/get-shit-done/bin/gsd-tools.cjs websearch "your query" --limit 10
+node ~/.codex/get-shit-done/bin/gsd-tools.cjs websearch "your query" --limit 10
 ```
 
 **Options:**

package/agents/gsd-research-synthesizer.md

@@ -119,7 +119,7 @@ Identify gaps that couldn't be resolved and need attention during planning.
 
 ## Step 6: Write SUMMARY.md
 
-Use template: ~/.claude/get-shit-done/templates/research-project/SUMMARY.md
+Use template: ~/.codex/get-shit-done/templates/research-project/SUMMARY.md
 
 Write to `.planning/research/SUMMARY.md`
 
@@ -128,7 +128,7 @@ Write to `.planning/research/SUMMARY.md`
 The 4 parallel researcher agents write files but do NOT commit. You commit everything together.
 
 ```bash
-node ~/.claude/get-shit-done/bin/gsd-tools.cjs commit "docs: complete project research" --files .planning/research/
+node ~/.codex/get-shit-done/bin/gsd-tools.cjs commit "docs: complete project research" --files .planning/research/
 ```
 
 ## Step 8: Return Summary
@@ -139,7 +139,7 @@ Return brief confirmation with key points for the orchestrator.
 
 <output_format>
 
-Use template: ~/.claude/get-shit-done/templates/research-project/SUMMARY.md
+Use template: ~/.codex/get-shit-done/templates/research-project/SUMMARY.md
 
 Key sections:
 - Executive Summary (2-3 paragraphs)

package/agents/gsd-roadmapper.md

@@ -38,12 +38,12 @@ Your ROADMAP.md is consumed by `/gsd:plan-phase` which uses it to:
 
 <philosophy>
 
-## Solo Developer + Claude Workflow
+## Solo Developer + Codex Workflow
 
-You are roadmapping for ONE person (the user) and ONE implementer (Claude).
+You are roadmapping for ONE person (the user) and ONE implementer (Codex).
 - No teams, stakeholders, sprints, resource allocation
 - User is the visionary/product owner
-- Claude is the builder
+- Codex is the builder
 - Phases are buckets of work, not project management artifacts
 
 ## Anti-Enterprise
@@ -325,11 +325,11 @@ After roadmap creation, REQUIREMENTS.md gets updated with phase mappings:
 | 2. Name | 0/2 | Not started | - |
 ```
 
-Reference full template: `~/.claude/get-shit-done/templates/roadmap.md`
+Reference full template: `~/.codex/get-shit-done/templates/roadmap.md`
 
 ## STATE.md Structure
 
-Use template from `~/.claude/get-shit-done/templates/state.md`.
+Use template from `~/.codex/get-shit-done/templates/state.md`.
 
 Key sections:
 - Project Reference (core value, current focus)

package/agents/gsd-verifier.md

@@ -10,7 +10,7 @@ You are a GSD phase verifier. You verify that a phase achieved its GOAL, not jus
 
 Your job: Goal-backward verification. Start from what the phase SHOULD deliver, verify it actually exists and works in the codebase.
 
-**Critical mindset:** Do NOT trust SUMMARY.md claims. SUMMARYs document what Claude SAID it did. You verify what ACTUALLY exists in the code. These often differ.
+**Critical mindset:** Do NOT trust SUMMARY.md claims. SUMMARYs document what Codex SAID it did. You verify what ACTUALLY exists in the code. These often differ.
 </role>
 
 <core_principle>
@@ -54,7 +54,7 @@ Set `is_re_verification = false`, proceed with Step 1.
 ```bash
 ls "$PHASE_DIR"/*-PLAN.md 2>/dev/null
 ls "$PHASE_DIR"/*-SUMMARY.md 2>/dev/null
-node ~/.claude/get-shit-done/bin/gsd-tools.cjs roadmap get-phase "$PHASE_NUM"
+node ~/.codex/get-shit-done/bin/gsd-tools.cjs roadmap get-phase "$PHASE_NUM"
 grep -E "^| $PHASE_NUM" .planning/REQUIREMENTS.md 2>/dev/null
 ```
 
@@ -91,7 +91,7 @@ must_haves:
 If no must_haves in frontmatter, check for Success Criteria:
 
 ```bash
-PHASE_DATA=$(node ~/.claude/get-shit-done/bin/gsd-tools.cjs roadmap get-phase "$PHASE_NUM" --raw)
+PHASE_DATA=$(node ~/.codex/get-shit-done/bin/gsd-tools.cjs roadmap get-phase "$PHASE_NUM" --raw)
 ```
 
 Parse the `success_criteria` array from the JSON output. If non-empty:
@@ -134,7 +134,7 @@ For each truth:
 Use gsd-tools for artifact verification against must_haves in PLAN frontmatter:
 
 ```bash
-ARTIFACT_RESULT=$(node ~/.claude/get-shit-done/bin/gsd-tools.cjs verify artifacts "$PLAN_PATH")
+ARTIFACT_RESULT=$(node ~/.codex/get-shit-done/bin/gsd-tools.cjs verify artifacts "$PLAN_PATH")
 ```
 
 Parse JSON result: `{ all_passed, passed, total, artifacts: [{path, exists, issues, passed}] }`
@@ -183,7 +183,7 @@ Key links are critical connections. If broken, the goal fails even with all arti
 Use gsd-tools for key link verification against must_haves in PLAN frontmatter:
 
 ```bash
-LINKS_RESULT=$(node ~/.claude/get-shit-done/bin/gsd-tools.cjs verify key-links "$PLAN_PATH")
+LINKS_RESULT=$(node ~/.codex/get-shit-done/bin/gsd-tools.cjs verify key-links "$PLAN_PATH")
 ```
 
 Parse JSON result: `{ all_verified, verified, total, links: [{from, to, via, verified, detail}] }`
@@ -251,12 +251,12 @@ Identify files modified in this phase from SUMMARY.md key-files section, or extr
 
 ```bash
 # Option 1: Extract from SUMMARY frontmatter
-SUMMARY_FILES=$(node ~/.claude/get-shit-done/bin/gsd-tools.cjs summary-extract "$PHASE_DIR"/*-SUMMARY.md --fields key-files)
+SUMMARY_FILES=$(node ~/.codex/get-shit-done/bin/gsd-tools.cjs summary-extract "$PHASE_DIR"/*-SUMMARY.md --fields key-files)
 
 # Option 2: Verify commits exist (if commit hashes documented)
 COMMIT_HASHES=$(grep -oE "[a-f0-9]{7,40}" "$PHASE_DIR"/*-SUMMARY.md | head -10)
 if [ -n "$COMMIT_HASHES" ]; then
-  COMMITS_VALID=$(node ~/.claude/get-shit-done/bin/gsd-tools.cjs verify commits $COMMIT_HASHES)
+  COMMITS_VALID=$(node ~/.codex/get-shit-done/bin/gsd-tools.cjs verify commits $COMMIT_HASHES)
 fi
 
 # Fallback: grep for files
@@ -415,7 +415,7 @@ human_verification: # Only if status: human_needed
 ---
 
 _Verified: {timestamp}_
-_Verifier: Claude (gsd-verifier)_
+_Verifier: Codex (gsd-verifier)_
 ```
 
 ## Return to Orchestrator