@opengsd/gsd-core 1.9.0 → 1.10.0

package/.claude-plugin/marketplace.json

@@ -9,7 +9,7 @@
     {
       "name": "gsd-core",
       "description": "GSD Core is a meta-prompting, context engineering, and spec-driven development system for AI coding agents.",
-      "version": "1.9.0",
+      "version": "1.10.0",
       "source": "./",
       "author": {
         "name": "open-gsd",

package/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "gsd-core",
   "displayName": "GSD Core",
-  "version": "1.9.0",
+  "version": "1.10.0",
   "description": "GSD Core is a meta-prompting, context engineering, and spec-driven development system for AI coding agents.",
   "author": {
     "name": "open-gsd",
@@ -19,6 +19,5 @@
     "gsd"
   ],
   "commands": "./commands/gsd/",
-  "skills": "./skills/",
-  "hooks": "./hooks/hooks.json"
+  "skills": "./skills/"
 }

package/.opencode/plugins/gsd-core.js

@@ -563,7 +563,14 @@ const GsdCorePlugin = async ({ directory } = {}) => {
         handleHookResult(r, output);
       }
 
-      // 4. gsd-workflow-guard.js — workflow advisory + git-force-add block
+      // 4. gsd-write-guard.js — hard-block catastrophic shrink of curated
+      //    .planning/ artifacts (ROADMAP.md, milestones/*-ROADMAP.md, STATE.md)
+      if (claudeTool === "Write") {
+        const r = runHook("gsd-write-guard.js", prePayload());
+        handleHookResult(r, output);
+      }
+
+      // 5. gsd-workflow-guard.js — workflow advisory + git-force-add block
       //    (covers Write/Edit/MultiEdit AND Bash force-add detection)
       if (isWriteLike || claudeTool === "Bash") {
         const r = runHook("gsd-workflow-guard.js", prePayload());

package/agents/gsd-code-fixer.md

@@ -216,15 +216,53 @@ If a finding references multiple files (in Fix section or Issue section):
 
 This agent runs as a background process that makes commits. Operating on the main working tree would race the foreground session (shared index, HEAD, and on-disk files). Instead, every instance runs in its own isolated worktree.
 
+**#2825: honor `workflow.use_worktrees`.** This is the ONLY writer that hand-rolls a git worktree
+inside the agent prompt; every other writer path (`/gsd:execute-phase`, `/gsd:execute-plan`,
+`/gsd:quick`, `/gsd:diagnose-issues`) reads `workflow.use_worktrees` and skips isolation when it is
+`false`. Read the same flag here and, when it is `false`, edit and commit in the main checkout
+directly (set `wt="."`, no `reviewfix_branch`, no recovery sentinel, no `git worktree add`, and skip
+the cleanup tail — there is no worktree to remove). When the flag is not `false`, the transactional
+worktree path below runs unchanged. A user who explicitly opted out of worktrees must never have a
+worktree created; the hand-rolled worktree also cannot run the project's gates safely (no
+`node_modules`), so the opt-out is also the safe path.
+
 The cleanup tail (commit fixes -> remove worktree -> drop recovery sentinel) MUST be **transactional**: either all of (worktree, branch advance, sentinel) end in a clean state, or — if the process is interrupted (system restart, OOM kill) between the last commit and `git worktree remove` — a discoverable recovery sentinel is left behind so a future run, `/gsd:resume-work`, or `/gsd:progress` can complete the cleanup. The bug fixed by #2839 was that the cleanup tail was non-transactional and silently left orphan worktrees + unmerged branches with no resume marker.
 
 ```bash
+# #2825: honor workflow.use_worktrees — the documented opt-out. When false,
+# edit/commit in the main checkout (wt=".", no temp branch, no sentinel, no
+# cleanup tail). Read the flag the same way the four sibling writer workflows
+# do. NOTE: this read parses .planning/config.json directly via `node` rather
+# than the gsd-tools CLI, because setup_worktree runs BEFORE the canonical
+# launcher preamble is sourced — invoking the CLI here would be undefined at
+# runtime and violates the runtime-launcher-parity preamble-ordering rule.
+# Once the preamble is sourced (later steps), the CLI is available.
+USE_WORKTREES=$(node -e '
+  try {
+    const fs = require("fs");
+    const p = (process.env.GSD_PROJECT_DIR || process.cwd()) + "/.planning/config.json";
+    const cfg = JSON.parse(fs.readFileSync(p, "utf8"));
+    process.stdout.write(String((cfg.workflow && cfg.workflow.use_worktrees) ?? true));
+  } catch { process.stdout.write("true"); }
+')
+
 # Derive worktree path from padded_phase (parsed from config in next step,
 # but the shell snippet below is illustrative — adapt once config is parsed).
 # In practice: parse padded_phase from config first, then run:
 branch=$(git branch --show-current)
 test -n "$branch" || { echo "Detached HEAD is not supported for review-fix (#2686)"; exit 1; }
 
+# #2647 defense-in-depth: padded_phase is interpolated into a worktree PATH
+# and a git BRANCH NAME below. The orchestrator (code-review-fix.md) already
+# validates it as ^[0-9]+(\.[0-9]+)?$, but this agent prompt is a literal bash
+# contract any caller can spawn — validate at the SINK too, so a future caller
+# that forgets cannot turn ${padded_phase} into a path-traversal or branch-name
+# injection. Reject anything that is not digits + an optional single dotted
+# numeric suffix (e.g. '02' or '36.14'); reject '../', spaces, shell metachars.
+if ! [[ "$padded_phase" =~ ^[0-9]+(\.[0-9]+)?$ ]]; then
+  echo "Invalid padded_phase for review-fix: '$padded_phase' (expected e.g. '02' or '36.14')"; exit 1
+fi
+
 # Recovery-sentinel handling (#2839):
 # Path is ${phase_dir}/.review-fix-recovery-pending.json. If it already exists,
 # a previous run was interrupted between fix commits and `git worktree remove`.
@@ -264,50 +302,85 @@ if [ -f "$sentinel" ]; then
   rm -f "$sentinel"
 fi
 
-wt=$(mktemp -d "/tmp/sv-${padded_phase}-reviewfix-XXXXXX")
-
-# Create a temp branch from the current branch tip so the worktree
-# attaches to that NEW branch rather than the user's currently-checked-out
-# branch (#2990: git refuses to check out the same branch in two
-# worktrees by default; the original `git worktree add "$wt" "$branch"`
-# failed before the agent could do any work). The temp branch shares
-# history with $branch up to the moment of creation, so commits made
-# inside the worktree fast-forward $branch on cleanup.
-reviewfix_branch="gsd-reviewfix/${padded_phase}-$$"
-git worktree add -b "$reviewfix_branch" "$wt" "$branch"
-
-# Write the recovery sentinel ONLY AFTER `git worktree add` succeeds.
-# Writing it before would leave a sentinel pointing at a worktree that does
-# not exist if `git worktree add` itself failed.
-node -e '
-  const fs = require("fs");
-  const [sentinelPath, worktree_path, branch, reviewfix_branch, padded_phase] = process.argv.slice(1);
-  fs.writeFileSync(sentinelPath, JSON.stringify({
-    worktree_path,
-    branch,
-    reviewfix_branch,
-    padded_phase,
-    started_at: new Date().toISOString()
-  }, null, 2));
-' "$sentinel" "$wt" "$branch" "$reviewfix_branch" "$padded_phase"
-
-cd "$wt"
+# #2825: when the user opted out of worktrees, edit/commit in the main
+# checkout directly — no temp branch, no sentinel, no cleanup tail. This is
+# the safe path: the hand-rolled worktree has no node_modules, so it cannot
+# run the project's gates, and an improvised teardown can destroy the real
+# node_modules on Windows (a junction followed by rm -rf). wt="." means every
+# downstream read/edit/commit lands in the main working tree, and the cleanup
+# tail below is a no-op (nothing to fast-forward, no worktree to remove).
+if [ "$USE_WORKTREES" = "false" ]; then
+  wt="."
+  reviewfix_branch="$branch"
+  echo "workflow.use_worktrees=false — editing/committing in the main checkout (no worktree)."
+else
+  # #2647: create the worktree INSIDE the repo under the same `.claude/worktrees/`
+  # dir the harness-managed executor worktrees already use. An absolute `/tmp`
+  # path landed outside the project tree (outside the agent session's permission
+  # allowlist → every Read inside prompted; on Windows/Git Bash mktemp also
+  # produced an un-removable short `C:/mvwtNN` path to dodge MAX_PATH). A
+  # repo-relative path inherits the repository's existing permission scope, is
+  # valid and short on Windows as well as POSIX, and is covered by the single
+  # `.gitignore` rule for `.claude/` (`.gitignore:12`). Uniqueness across
+  # concurrent runs for the same phase comes from the PID (`$$`) + epoch suffix
+  # (replacing mktemp's XXXXXX). `$main_repo` is resolved the same way the
+  # cleanup tail below resolves it (`git worktree list --porcelain` first line).
+  main_repo="$(git worktree list --porcelain | awk '/^worktree / { sub(/^worktree /, ""); print; exit }')"
+  wt="$main_repo/.claude/worktrees/rf-${padded_phase}-$$-$(date +%s)"
+  mkdir -p "$wt"
+
+  # Create a temp branch from the current branch tip so the worktree
+  # attaches to that NEW branch rather than the user's currently-checked-out
+  # branch (#2990: git refuses to check out the same branch in two
+  # worktrees by default; the original `git worktree add "$wt" "$branch"`
+  # failed before the agent could do any work). The temp branch shares
+  # history with $branch up to the moment of creation, so commits made
+  # inside the worktree fast-forward $branch on cleanup.
+  reviewfix_branch="gsd-reviewfix/${padded_phase}-$$"
+  git worktree add -b "$reviewfix_branch" "$wt" "$branch"
+
+  # Write the recovery sentinel ONLY AFTER `git worktree add` succeeds.
+  # Writing it before would leave a sentinel pointing at a worktree that does
+  # not exist if `git worktree add` itself failed.
+  node -e '
+    const fs = require("fs");
+    const [sentinelPath, worktree_path, branch, reviewfix_branch, padded_phase] = process.argv.slice(1);
+    fs.writeFileSync(sentinelPath, JSON.stringify({
+      worktree_path,
+      branch,
+      reviewfix_branch,
+      padded_phase,
+      started_at: new Date().toISOString()
+    }, null, 2));
+  ' "$sentinel" "$wt" "$branch" "$reviewfix_branch" "$padded_phase"
+
+  cd "$wt"
+fi
 ```
 
 Concrete steps:
 1. Parse `padded_phase` and `phase_dir` from the `<config>` block (needed for the path and for the sentinel location).
 2. Resolve the current branch: `branch=$(git branch --show-current)`. If empty (detached HEAD), print an error and exit — detached-HEAD state is not supported; commits made in a detached-HEAD worktree would not advance the branch.
 3. **Recovery check (#2839, #2990):** If `${phase_dir}/.review-fix-recovery-pending.json` already exists, a prior run was interrupted. Parse the JSON, attempt to remove the orphan worktree it points at (best-effort, with `--force`), and delete the stale `reviewfix_branch` (best-effort, with `git branch -D`), then delete the stale sentinel before continuing. This makes a re-run of `/gsd:code-review --fix` self-healing.
-4. Create a unique worktree path: `wt=$(mktemp -d "/tmp/sv-${padded_phase}-reviewfix-XXXXXX")`. The `mktemp` suffix ensures concurrent runs for the same phase do not collide.
+4. Create a unique worktree path **inside the repo**: `main_repo="$(git worktree list --porcelain | awk '/^worktree / { sub(/^worktree /, ""); print; exit }')"` then `wt="$main_repo/.claude/worktrees/rf-${padded_phase}-$$-$(date +%s)"` + `mkdir -p "$wt"`. The path lives under the same `.claude/worktrees/` dir the harness-managed executor worktrees use (already gitignored via `.claude/`, already in the session's permission scope), and the `$$`-PID + epoch suffix ensures concurrent runs for the same phase do not collide (#2647 — an absolute `/tmp` path landed outside the project tree and prompted on every read).
 5. Run `git worktree add -b "$reviewfix_branch" "$wt" "$branch"` — this creates a NEW branch (`gsd-reviewfix/${padded_phase}-$$`) starting from the current branch tip and attaches the worktree to that new branch. Attaching to a new branch (rather than `$branch` directly) is what allows the worktree to coexist with the user's checkout — git refuses to check out the same branch in two worktrees by default (#2990). Commits made inside the worktree advance `$reviewfix_branch`; the cleanup tail fast-forwards `$branch` to `$reviewfix_branch` so the user's branch ends up with the agent's commits.
 6. **Write the recovery sentinel** at `${phase_dir}/.review-fix-recovery-pending.json` containing `{worktree_path, branch, reviewfix_branch, padded_phase, started_at}`. Doing this AFTER `git worktree add` ensures the sentinel only ever points at a real worktree. The sentinel includes `reviewfix_branch` so recovery can clean both the orphan worktree AND its temp branch.
 7. All subsequent file reads, edits, and commits happen inside `$wt` (which is on `$reviewfix_branch`, not `$branch`).
 
 **If `git worktree add` fails**, surface the error and exit — do not force-remove the path, as another concurrent run may be holding it. Do not write the sentinel (the worktree does not exist). Do not delete `$reviewfix_branch` either; if `-b` failed, no temp branch was created.
 
-**Cleanup tail (transactional, ALWAYS — even on failure):** After writing REVIEW-FIX.md and before returning to the orchestrator, run the cleanup in this exact order:
+**Cleanup tail (transactional, ALWAYS — even on failure — when a worktree was created):** After writing REVIEW-FIX.md and before returning to the orchestrator, run the cleanup in this exact order. (When `workflow.use_worktrees` is `false`, no worktree was created — the cleanup is a no-op and the bash below early-exits.)
 
 ```bash
+# #2825: when worktrees were disabled, there is nothing to clean up — the
+# agent edited/committed on $branch directly in the main checkout (wt=".",
+# reviewfix_branch==$branch, no sentinel, no temp worktree). Skip the whole
+# tail; the four steps below are all no-ops or harmful (e.g. `git worktree
+# remove "."` ) in that mode.
+if [ "$USE_WORKTREES" = "false" ]; then
+  exit 0
+fi
+
 # Step 1 (#2990): fast-forward $branch to capture the commits the agent
 # made on $reviewfix_branch. Run from the main repo (not $wt) — the user's
 # checkout owns $branch. --ff-only ensures we never silently drop or
@@ -354,7 +427,7 @@ fi
 rm -f "$sentinel"
 ```
 
-This cleanup is unconditional — register it mentally as a finally-block obligation. If the agent exits early (config error, no findings, etc.), still run the cleanup tail in order (fast-forward → worktree remove → temp branch delete → sentinel rm) before exit. The sentinel must NEVER be removed before `git worktree remove` succeeds. The temp branch must NEVER be deleted while the fast-forward is in a diverged state.
+This cleanup is unconditional when a worktree was created — register it mentally as a finally-block obligation. If the agent exits early (config error, no findings, etc.), still run the cleanup tail in order (fast-forward → worktree remove → temp branch delete → sentinel rm) before exit. (When `workflow.use_worktrees` is `false`, no worktree exists and the bash above early-exits before these steps.) The sentinel must NEVER be removed before `git worktree remove` succeeds. The temp branch must NEVER be deleted while the fast-forward is in a diverged state.
 </step>
 
 <step name="load_context">
@@ -587,9 +660,33 @@ _Iteration: {N}_
 
 <critical_rules>
 
-**ALWAYS run inside the isolated worktree** — set up via `branch=$(git branch --show-current)` + `wt=$(mktemp -d "/tmp/sv-${padded_phase}-reviewfix-XXXXXX")` + `git worktree add -b "$reviewfix_branch" "$wt" "$branch"` at the very start (see `setup_worktree` step). Using `mktemp` ensures concurrent runs do not collide. Attaching to a NEW branch `$reviewfix_branch` (not `$branch` directly) is required because git refuses to check out the same branch in two worktrees by default — `$branch` is already checked out in the user's main repo (#2990). Commits advance `$reviewfix_branch`; the cleanup tail fast-forwards `$branch` to `$reviewfix_branch` so the user's branch ends up with the agent's commits. Every file read, edit, and commit must happen inside `$wt`. Run the four-step cleanup tail unconditionally when done (treat it as a finally block). If `git worktree add` fails, exit with an error rather than force-removing a path another run may hold. This prevents racing the foreground session on the shared main working tree (#2686).
-
-**ALWAYS run the transactional cleanup tail in order** (#2839, #2990): the cleanup is four steps with strict ordering. (1) `git -C "$main_repo" merge --ff-only "$reviewfix_branch"` — fast-forward the user's branch to capture the agent's commits; on divergence, fail loudly and preserve the temp branch. (2) `git worktree remove "$wt" --force`. (3) `git -C "$main_repo" branch -D "$reviewfix_branch"` ONLY if the fast-forward succeeded; otherwise leave the temp branch for manual merge. (4) `rm -f "$sentinel"` (the recovery sentinel at `${phase_dir}/.review-fix-recovery-pending.json`). The sentinel is written AFTER `git worktree add` succeeds and removed only AFTER `git worktree remove` returns successfully. The temp branch is deleted only when the fast-forward succeeded. This ordering is what makes the cleanup tail transactional — an interruption between commits and `git worktree remove` leaves the sentinel behind (with `reviewfix_branch` recorded) so a future run, `/gsd:resume-work`, or `/gsd:progress` can detect and complete the recovery. Reversing the order recreates the orphan-worktree bug.
+**ALWAYS run inside the isolated worktree** — set up via `branch=$(git branch --show-current)` + `main_repo="$(git worktree list --porcelain | awk '/^worktree / { sub(/^worktree /, ""); print; exit }')"` + `wt="$main_repo/.claude/worktrees/rf-${padded_phase}-$$-$(date +%s)"` + `mkdir -p "$wt"` + `git worktree add -b "$reviewfix_branch" "$wt" "$branch"` at the very start (see `setup_worktree` step). The worktree path is repo-relative under `.claude/worktrees/` (the same dir the harness-managed executor worktrees use — gitignored via `.claude/`, inside the session's permission scope); the `$$`-PID + epoch suffix ensures concurrent runs do not collide (#2647 — a hardcoded `/tmp` path landed outside the project tree and prompted on every read). Attaching to a NEW branch `$reviewfix_branch` (not `$branch` directly) is required because git refuses to check out the same branch in two worktrees by default — `$branch` is already checked out in the user's main repo (#2990). Commits advance `$reviewfix_branch`; the cleanup tail fast-forwards `$branch` to `$reviewfix_branch` so the user's branch ends up with the agent's commits. Every file read, edit, and commit must happen inside `$wt`. Run the four-step cleanup tail when done (treat it as a finally block) — but only when a worktree was actually created; when `workflow.use_worktrees` is `false` the cleanup early-exits (no worktree to remove). If `git worktree add` fails, exit with an error rather than force-removing a path another run may hold. This prevents racing the foreground session on the shared main working tree (#2686).
+
+**#2825 — honor `workflow.use_worktrees`.** Before creating a worktree, read the
+`workflow.use_worktrees` config flag (the documented opt-out — same key the four sibling writer
+workflows honor). `setup_worktree` reads it via `node` directly from `.planning/config.json`
+(because that step runs BEFORE the canonical gsd_run launcher preamble is sourced; later steps may
+use `gsd_run query config-get workflow.use_worktrees`). When it is `false`, do NOT create a worktree
+— edit and commit in the main checkout directly (`wt="."`, no temp branch, no sentinel, no cleanup
+tail). A user who opted out of worktrees must
+never have one created. See the `setup_worktree` step for the gated bash.
+
+**NEVER `rm -rf` a possible reparse point** (#2825). On Windows, `node_modules` inside the worktree
+may be a junction/reparse point whose target is the REAL `node_modules` in the main checkout — and
+`rm -rf` follows the link and deletes the target's contents (silent, misdiagnosable data loss). Do
+NOT improvise a `node_modules` teardown. The worktree has no `node_modules` by design; if you need
+the project's gates, run them in the main checkout after the fast-forward, OR leave the worktree's
+dependency handling to `git worktree remove` (which does not recurse into a separately-managed
+link). Never use `rm -rf` (or `2>/dev/null || rm -rf || true`) as a fallback for removing a path
+that might be a reparse point — on failure, STOP and surface the error rather than falling through
+to a destructive remove.
+
+**Record where verification ran** (#2825). The REVIEW-FIX.md verification section must state whether
+the gates ran in the main checkout or the isolated worktree, so a reader can tell whether the numbers
+are reproducible from the tree they are looking at (a worktree-env run is not reproducible from the
+main checkout after teardown).
+
+**ALWAYS run the transactional cleanup tail in order when a worktree was created** (#2839, #2990; skipped — bash early-exits — when `workflow.use_worktrees` is `false`): the cleanup is four steps with strict ordering. (1) `git -C "$main_repo" merge --ff-only "$reviewfix_branch"` — fast-forward the user's branch to capture the agent's commits; on divergence, fail loudly and preserve the temp branch. (2) `git worktree remove "$wt" --force`. (3) `git -C "$main_repo" branch -D "$reviewfix_branch"` ONLY if the fast-forward succeeded; otherwise leave the temp branch for manual merge. (4) `rm -f "$sentinel"` (the recovery sentinel at `${phase_dir}/.review-fix-recovery-pending.json`). The sentinel is written AFTER `git worktree add` succeeds and removed only AFTER `git worktree remove` returns successfully. The temp branch is deleted only when the fast-forward succeeded. This ordering is what makes the cleanup tail transactional — an interruption between commits and `git worktree remove` leaves the sentinel behind (with `reviewfix_branch` recorded) so a future run, `/gsd:resume-work`, or `/gsd:progress` can detect and complete the recovery. Reversing the order recreates the orphan-worktree bug.
 
 **ALWAYS use the Write tool to create files** — never use `Bash(cat << 'EOF')` or heredoc commands for file creation.
 

package/agents/gsd-debugger.md

@@ -168,73 +168,20 @@ try {
 
 <investigation_techniques>
 
-## Binary Search / Divide and Conquer
+## Technique Catalog
 
-**When:** Large codebase, long execution path, many possible failure points.
+Full step-by-step bodies for every technique below: @gsd-core/references/debugger-techniques.md
 
-**How:** Cut problem space in half repeatedly until you isolate the issue.
-
-1. Identify boundaries (where works, where fails)
-2. Add logging/testing at midpoint
-3. Determine which half contains the bug
-4. Repeat until you find exact line
-
-**Example:** API returns wrong data
-- Test: Data leaves database correctly? YES
-- Test: Data reaches frontend correctly? NO
-- Test: Data leaves API route correctly? YES
-- Test: Data survives serialization? NO
-- **Found:** Bug in serialization layer (4 tests eliminated 90% of code)
-
-## Rubber Duck Debugging
-
-**When:** Stuck, confused, mental model doesn't match reality.
-
-**How:** Explain the problem out loud in complete detail.
-
-Write or say:
-1. "The system should do X"
-2. "Instead it does Y"
-3. "I think this is because Z"
-4. "The code path is: A -> B -> C -> D"
-5. "I've verified that..." (list what you tested)
-6. "I'm assuming that..." (list assumptions)
-
-Often you'll spot the bug mid-explanation: "Wait, I never verified that B returns what I think it does."
-
-## Delta Debugging
-
-**When:** Large change set is suspected (many commits, a big refactor, or a complex feature that broke something). Also when "comment out everything" is too slow.
-
-**How:** Binary search over the change space — not just the code, but the commits, configs, and inputs.
-
-**Over commits (use git bisect):**
-Already covered under Git Bisect. But delta debugging extends it: after finding the breaking commit, delta-debug the commit itself — identify which of its N changed files/lines actually causes the failure.
-
-**Over code (systematic elimination):**
-1. Identify the boundary: a known-good state (commit, config, input) vs the broken state
-2. List all differences between good and bad states
-3. Split the differences in half. Apply only half to the good state.
-4. If broken: bug is in the applied half. If not: bug is in the other half.
-5. Repeat until you have the minimal change set that causes the failure.
-
-**Over inputs:**
-1. Find a minimal input that triggers the bug (strip out unrelated data fields)
-2. The minimal input reveals which code path is exercised
-
-**When to use:**
-- "This worked yesterday, something changed" → delta debug commits
-- "Works with small data, fails with real data" → delta debug inputs
-- "Works without this config change, fails with it" → delta debug config diff
-
-**Example:** 40-file commit introduces bug
-```
-Split into two 20-file halves.
-Apply first 20: still works → bug in second half.
-Split second half into 10+10.
-Apply first 10: broken → bug in first 10.
-... 6 splits later: single file isolated.
-```
+- **Binary Search / Divide and Conquer** — halve the search space until the fault localizes.
+- **Rubber Duck Debugging** — reconstruct the mental model aloud; the gap is the bug.
+- **Delta Debugging** — shrink a failing input to its minimal failing core.
+- **Minimal Reproduction** — strip everything not required to reproduce.
+- **Working Backwards** — start at the symptom and walk causality in reverse.
+- **Differential Debugging** — compare a working case against a failing one.
+- **Observability First** — add instrumentation before forming further hypotheses.
+- **Comment Out Everything** — reduce to nothing, restore until the fault returns.
+- **Git Bisect** — binary-search history for the introducing commit.
+- **Follow the Indirection** — trace each hop when the fault hides behind a layer.
 
 ## Structured Reasoning Checkpoint
 
@@ -268,187 +215,6 @@ reasoning_checkpoint:
 
 If you cannot fill all seven fields with specific, concrete answers — you do not have a confirmed root cause yet. Return to investigation_loop.
 
-## Minimal Reproduction
-
-**When:** Complex system, many moving parts, unclear which part fails.
-
-**How:** Strip away everything until smallest possible code reproduces the bug.
-
-1. Copy failing code to new file
-2. Remove one piece (dependency, function, feature)
-3. Test: Does it still reproduce? YES = keep removed. NO = put back.
-4. Repeat until bare minimum
-5. Bug is now obvious in stripped-down code
-6. **Shrinking (input-space bugs)** — when the bug triggers on a class of inputs, wrap it in a property (fast-check for JS/TS, Hypothesis for Python) and let the shrinker auto-minimize the counterexample; store the **minimized** input as the regression seed. See `gsd-core/references/debugger-repro-hardening.md`.
-
-**Example:**
-```jsx
-// Start: 500-line React component with 15 props, 8 hooks, 3 contexts
-// End after stripping:
-function MinimalRepro() {
-  const [count, setCount] = useState(0);
-
-  useEffect(() => {
-    setCount(count + 1); // Bug: infinite loop, missing dependency array
-  });
-
-  return <div>{count}</div>;
-}
-// The bug was hidden in complexity. Minimal reproduction made it obvious.
-```
-
-## Working Backwards
-
-**When:** You know correct output, don't know why you're not getting it.
-
-**How:** Start from desired end state, trace backwards.
-
-1. Define desired output precisely
-2. What function produces this output?
-3. Test that function with expected input - does it produce correct output?
-   - YES: Bug is earlier (wrong input)
-   - NO: Bug is here
-4. Repeat backwards through call stack
-5. Find divergence point (where expected vs actual first differ)
-
-**Example:** UI shows "User not found" when user exists
-```
-Trace backwards:
-1. UI displays: user.error → Is this the right value to display? YES
-2. Component receives: user.error = "User not found" → Correct? NO, should be null
-3. API returns: { error: "User not found" } → Why?
-4. Database query: SELECT * FROM users WHERE id = 'undefined' → AH!
-5. FOUND: User ID is 'undefined' (string) instead of a number
-```
-
-## Differential Debugging
-
-**When:** Something used to work and now doesn't. Works in one environment but not another.
-
-**Time-based (worked, now doesn't):**
-- What changed in code since it worked?
-- What changed in environment? (Node version, OS, dependencies)
-- What changed in data?
-- What changed in configuration?
-
-**Environment-based (works in dev, fails in prod):**
-- Configuration values
-- Environment variables
-- Network conditions (latency, reliability)
-- Data volume
-- Third-party service behavior
-
-**Process:** List differences, test each in isolation, find the difference that causes failure.
-
-**Example:** Works locally, fails in CI
-```
-Differences:
-- Node version: Same ✓
-- Environment variables: Same ✓
-- Timezone: Different! ✗
-
-Test: Set local timezone to UTC (like CI)
-Result: Now fails locally too
-FOUND: Date comparison logic assumes local timezone
-```
-
-## Observability First
-
-**When:** Always. Before making any fix.
-
-**Add visibility before changing behavior:**
-
-```javascript
-// Strategic logging (useful):
-console.log('[handleSubmit] Input:', { email, password: '***' });
-console.log('[handleSubmit] Validation result:', validationResult);
-console.log('[handleSubmit] API response:', response);
-
-// Assertion checks:
-console.assert(user !== null, 'User is null!');
-console.assert(user.id !== undefined, 'User ID is undefined!');
-
-// Timing measurements:
-console.time('Database query');
-const result = await db.query(sql);
-console.timeEnd('Database query');
-
-// Stack traces at key points:
-console.log('[updateUser] Called from:', new Error().stack);
-```
-
-**Workflow:** Add logging -> Run code -> Observe output -> Form hypothesis -> Then make changes.
-
-## Comment Out Everything
-
-**When:** Many possible interactions, unclear which code causes issue.
-
-**How:**
-1. Comment out everything in function/file
-2. Verify bug is gone
-3. Uncomment one piece at a time
-4. After each uncomment, test
-5. When bug returns, you found the culprit
-
-**Example:** Some middleware breaks requests, but you have 8 middleware functions
-```javascript
-app.use(helmet()); // Uncomment, test → works
-app.use(cors()); // Uncomment, test → works
-app.use(compression()); // Uncomment, test → works
-app.use(bodyParser.json({ limit: '50mb' })); // Uncomment, test → BREAKS
-// FOUND: Body size limit too high causes memory issues
-```
-
-## Git Bisect
-
-**When:** Feature worked in past, broke at unknown commit.
-
-**How:** Binary search through git history.
-
-```bash
-git bisect start
-git bisect bad              # Current commit is broken
-git bisect good abc123      # This commit worked
-# Git checks out middle commit
-git bisect bad              # or good, based on testing
-# Repeat until culprit found
-```
-
-100 commits between working and broken: ~7 tests to find exact breaking commit.
-
-## Follow the Indirection
-
-**When:** Code constructs paths, URLs, keys, or references from variables — and the constructed value might not point where you expect.
-
-**The trap:** You read code that builds a path like `path.join(configDir, 'hooks')` and assume it's correct because it looks reasonable. But you never verified that the constructed path matches where another part of the system actually writes/reads.
-
-**How:**
-1. Find the code that **produces** the value (writer/installer/creator)
-2. Find the code that **consumes** the value (reader/checker/validator)
-3. Trace the actual resolved value in both — do they agree?
-4. Check every variable in the path construction — where does each come from? What's its actual value at runtime?
-
-**Common indirection bugs:**
-- Path A writes to `dir/sub/hooks/` but Path B checks `dir/hooks/` (directory mismatch)
-- Config value comes from cache/template that wasn't updated
-- Variable is derived differently in two places (e.g., one adds a subdirectory, the other doesn't)
-- Template placeholder (`{{VERSION}}`) not substituted in all code paths
-
-**Example:** Stale hook warning persists after update
-```
-Check code says:  hooksDir = path.join(configDir, 'hooks')
-                  configDir = ~/.claude
-                  → checks ~/.claude/hooks/
-
-Installer says:   hooksDest = path.join(targetDir, 'hooks')
-                  targetDir = ~/.claude/gsd-core
-                  → writes to ~/.claude/gsd-core/hooks/
-
-MISMATCH: Checker looks in wrong directory → hooks "not found" → reported as stale
-```
-
-**The discipline:** Never assume a constructed path is correct. Resolve it to its actual value and verify the other side agrees. When two systems share a resource (file, directory, key), trace the full path in both.
-
 ## Technique Selection (routed by bug class)
 
 Classify the failure first (Phase 1.75), then route by class — not by ad-hoc

package/agents/gsd-executor.md

@@ -26,10 +26,12 @@ When you need library or framework documentation, check in this order:
 
 1. If Context7 MCP tools (`mcp__context7__*, mcp__plugin_context7_context7__*`) are available in your environment, use them:
    - Resolve library ID: `mcp__context7__resolve-library-id` with `libraryName`
-   - Fetch docs: `mcp__context7__get-library-docs` with `context7CompatibleLibraryId` and `topic`
+   - Fetch docs: `mcp__context7__query-docs` with `libraryId` (the ID from step 1) and `query`
 
-2. If Context7 MCP is not available (upstream bug anthropics/claude-code#13898 strips MCP
-   tools from agents with a `tools:` frontmatter restriction), use the CLI fallback via Bash:
+2. If Context7 MCP is not available (custom subagents cannot see project-scoped
+   `.mcp.json` servers — they only inherit user-scoped `~/.claude/mcp.json`, so a
+   context7 server configured at the project scope is invisible to spawned
+   agents), use the CLI fallback via Bash:
 
    Step 1 — Resolve library ID:
    ```bash
@@ -498,8 +500,8 @@ if [ -f .git ]; then  # worktree
   # Positive allow-list: HEAD must be on a per-agent branch (`agent-<id>` or
   # legacy `worktree-agent-<id>`). This catches feature/* and any other
   # arbitrary branch that the deny-list would silently allow (#2924, #1995).
-  if ! echo "$ACTUAL_BRANCH" | grep -Eq '^(worktree-)?agent-[A-Za-z0-9._/-]+$'; then
-    echo "FATAL: refusing to commit — worktree HEAD '$ACTUAL_BRANCH' is not in the agent-* / worktree-agent-* namespace." >&2
+  if ! echo "$ACTUAL_BRANCH" | grep -Eq '^((worktree-)?agent-|worktree-wf_)[A-Za-z0-9._/-]+$'; then
+    echo "FATAL: refusing to commit — worktree HEAD '$ACTUAL_BRANCH' is not in the agent-* / worktree-agent-* / worktree-wf_* namespace." >&2
     echo "Agent commits must live on per-agent branches; surface as blocker (#2924)." >&2
     exit 1
   fi

package/agents/gsd-integration-checker.md

@@ -94,6 +94,9 @@ For each phase, extract what it provides and what it should consume.
 **From SUMMARYs, extract:**
 
 ```bash
+# #2962: zsh aborts the block on an unmatched for-list glob (nomatch); bash passes it through. nullglob both.
+shopt -s nullglob 2>/dev/null; setopt NULL_GLOB 2>/dev/null
+
 # Key exports from each phase
 for summary in .planning/phases/*/*-SUMMARY.md; do
   echo "=== $summary ==="

package/agents/gsd-plan-checker.md

@@ -714,6 +714,9 @@ Extract from init JSON: `phase_dir`, `phase_number`, `has_plans`, `plan_count`.
 Orchestrator provides CONTEXT.md content in the verification prompt. If provided, parse for locked decisions, discretion areas, deferred ideas.
 
 ```bash
+# #2962: zsh aborts the block on an unmatched for-list glob (nomatch); bash passes it through. nullglob both.
+shopt -s nullglob 2>/dev/null; setopt NULL_GLOB 2>/dev/null
+
 gsd_run query phase.list-plans "$phase_number"
 # Research / brief artifacts (deterministic listing)
 gsd_run query phase.list-artifacts "$phase_number" --type research
@@ -735,6 +738,9 @@ done
 Use `gsd-tools query` to validate plan structure:
 
 ```bash
+# #2962: zsh aborts the block on an unmatched for-list glob (nomatch); bash passes it through. nullglob both.
+shopt -s nullglob 2>/dev/null; setopt NULL_GLOB 2>/dev/null
+
 for plan in "$PHASE_DIR"/*-PLAN.md; do
   echo "=== $plan ==="
   PLAN_STRUCTURE=$(gsd_run query verify.plan-structure "$plan")
@@ -820,6 +826,9 @@ Inspect `tasks` in the JSON; open the PLAN in the editor for prose-level review.
 ## Step 6: Verify Dependency Graph
 
 ```bash
+# #2962: zsh aborts the block on an unmatched for-list glob (nomatch); bash passes it through. nullglob both.
+shopt -s nullglob 2>/dev/null; setopt NULL_GLOB 2>/dev/null
+
 for plan in "$PHASE_DIR"/*-PLAN.md; do
   grep "depends_on:" "$plan"
 done