@gobing-ai/spur 0.4.9 → 0.4.11

package/plugins/sp/skills/source-driven-development/SKILL.md

@@ -55,27 +55,31 @@ Do **not** use this skill for:
 
 - **Your own code's correctness** — that is `sp:code-verification` (requirements/AC) and `sp:code-review`.
 - **Stress-testing a design decision** — that is `sp:doubt-driven-development` (artifact vs contract).
-- **Well-known, version-stable stdlib** you can state with HIGH confidence — verification has a cost;
+- **Well-known, version-stable stdlib** you have already checked — verification has a cost;
   spend it where being wrong is likely and expensive.
 
 ## The process
 
-### Step 1 — Classify your confidence before you write
+### Step 1 — Know where each fact came from before you write
 
-| Level | Meaning | Action |
-|---|---|---|
-| **HIGH** | Verified against the pinned version's docs/source **this session** | Generate; cite the source inline |
-| **MEDIUM** | Recalled from a prior session; plausibly stale | Verify before relying on it |
-| **LOW** | Memory only, no source in hand | Stop — verify first; never present as fact |
+| Source in hand | Action |
+|---|---|
+| Checked against the pinned version's docs/source **this session** | Generate; cite the source inline |
+| Recalled from a prior session; plausibly stale | Verify before relying on it |
+| Memory only, no source in hand | Stop — verify first; never present as fact |
 
-If you cannot honestly claim HIGH for a version-specific behavior, you are at MEDIUM or LOW — verify.
+Every claim carries its citation **and an earned confidence level** — `HIGH|MEDIUM|LOW`: `HIGH`
+cites (`path:line`, a URL, or a path with a code/doc extension), `MEDIUM`/`LOW` cite or name what is
+unverified. That grade is evidence, not self-assessment, so it can only be as strong as what is cited
+beside it. ADR-138 still forbids a confidence label on a verdict or verify answer, where the citation
+alone is the evidence.
 
 ### Step 2 — Go to the primary source, in priority order
 
 1. The **type signature / source** in the installed, pinned dependency (the ground truth for *this* build).
 2. The **official docs for the pinned version** (not the latest — the version in the lockfile).
 3. Authoritative references when docs are thin.
-4. Memory — **LOW only**, and never as the final authority.
+4. Memory — never the final authority; verify before relying on it.
 
 State the **version** inline whenever behavior is version-specific.
 
@@ -88,43 +92,44 @@ State the **version** inline whenever behavior is version-specific.
 ### Step 4 — Cite, then generate
 
 Generate the code and **cite the source** (doc URL + date, or `pkg@version` + the file/symbol) at the
-point of use or in the task's notes. A claim about external behavior without a citation is
-unverified — flag it as such rather than presenting it as fact.
-
-### Step 5 — Close with a verification verdict
+point of use or in the task's notes, with the claim's earned `HIGH|MEDIUM|LOW` level beside it. A claim
+about external behavior without a citation is unverified — flag it as such rather than presenting it as
+fact.
 
-Before finishing, verify the citations for the API/library claims you emitted and close with one
-line: `Verification: HIGH|MEDIUM|LOW — <first failing check and deviation, or 'all checks passed'>`.
+### Step 5 — Check the citations before finishing
 
 - **Citation coverage** — every API/library claim in the output carries a source citation (doc URL + date, or `pkg@version` + file/symbol); no uncited claim is asserted as fact.
 - **Source authority** — each citation points at the pinned version's primary source (installed signature/source, or official docs for the lockfile version), not the latest docs or memory.
-- **Honest confidence** — the stated HIGH/MEDIUM/LOW matches the evidence: HIGH requires a check against the pinned source this session; MEDIUM/LOW items are labeled, and LOW is never presented as fact.
-- **HIGH** — all three checks pass. **MEDIUM** — coverage intact but some citations are off-version (latest docs for a pinned dependency) or secondary-source only. **LOW** — an API/library claim lacks any citation, or a LOW-confidence claim was asserted as fact.
+- **Claim confidence** — every API/library claim carries an earned level inside `HIGH|MEDIUM|LOW`: `HIGH` cites evidence, `MEDIUM`/`LOW` cite or name what is unverified. A level outside the enum, or one nothing cited earns, is a defect.
+
+Report the first failing check and its deviation, if any. This grade lives on the claim: do not append
+a confidence verdict or a `Confidence:` line to the answer (ADR-138).
 
-Deterministic backstop: the `cited-version-strings`, `cited-api-claims`,
-`cited-api-claims-confidence` and `cited-high-confidence` rules
+Deterministic backstop: the `cited-version-strings` and `cited-api-claims` rules
 (`.spur/rules/docs/sourced-api-claims.yaml`) flag markdown lines that assert a version string or a
-time-anchored API claim with no citation anchor on the same line, claim lines that carry no
-HIGH/MEDIUM/LOW level, and claim lines that claim HIGH with no anchor — the one level that asserts
-"verified this session", so its source must be on the line; MEDIUM (recalled) and LOW (memory only)
-need no anchor by contract and are not flagged. They are an info-severity advisory backstop for
-this contract and are deliberately NOT wired into `recommended-pre-check` — run them ad hoc with
-`spur rule run --file .spur/rules/docs/sourced-api-claims.yaml`. The checks above and the SECUA
-checklist remain the enforcement points.
+time- or version-anchored API claim (`deprecated since`, `removed in 0.9`, `fixers (since 0.3.4)`)
+with no citation anchor on the same line. Where a project runs the claim-table companion
+(`structure/api-library-claim-citation`), the rows of an `API/library claim sources and confidence`
+block are checked the same way — citation present, level earned. They are an info-severity advisory
+backstop for this contract and are deliberately NOT wired into `recommended-pre-check` — run them ad
+hoc with `spur rule run --file .spur/rules/docs/sourced-api-claims.yaml`. Dated working records
+(`docs/report*`, `docs/dogfood`, `docs/plans`, `docs/analysis`) are excluded, as are the task
+archives: a version measured by a past run is not an authorable claim. The checks above and the
+SECUA checklist remain the enforcement points.
 
 ## Common Rationalizations
 
 | Rationalization | Reality |
 |---|---|
-| "I've used this API a hundred times — I know the signature." | APIs change across versions and your memory is a silent cache. Verify against the *pinned* version; recall is MEDIUM at best. |
+| "I've used this API a hundred times — I know the signature." | APIs change across versions and your memory is a silent cache. Verify against the *pinned* version; recall is not a source. |
 | "It compiled, so I used it right." | Compiling proves existence and types, not contract. Ordering, preconditions, and error modes are not checked by the compiler. |
 | "The latest docs say so." | You ship against the *pinned* version, not latest. Read the docs for the version in the lockfile. |
 | "Close enough — I'll fix it if it breaks." | Guessing at an external contract moves the cost to runtime/production. Verify before generating; it is cheaper here. |
-| "Verifying every call is too slow." | Verify what you are *not sure of*, at the confidence level you honestly hold. HIGH needs no re-check; LOW always does. |
+| "Verifying every call is too slow." | Verify what you have no source for. A fact checked this session needs no re-check; memory always does. |
 
 ## Red Flags
 
-- Generating version-specific code you would rate MEDIUM or LOW confidence, without opening a source.
+- Generating version-specific code from memory, without opening a source.
 - Presenting an API claim as fact with no citation (doc + date, or `pkg@version` + symbol).
 - Treating "it exists" as proof it is used correctly (the two questions collapsed into one).
 - Reading the *latest* docs for a dependency pinned to an older version.
@@ -136,8 +141,7 @@ checklist remain the enforcement points.
 - [ ] Every version-specific external behavior relied on was checked against the pinned version's source/docs **this session**.
 - [ ] Both questions answered — the API exists **and** is called within its contract.
 - [ ] Claims about external behavior carry a citation (source + date, or `pkg@version` + symbol); unverifiable ones are flagged, not asserted.
-- [ ] Confidence is stated honestly (HIGH/MEDIUM/LOW); nothing at LOW was presented as fact.
-- [ ] Run closes with the Step 5 verdict line: `Verification: HIGH|MEDIUM|LOW — <first failing check and deviation, or 'all checks passed'>`.
+- [ ] Nothing recalled from memory alone was presented as fact.
 
 ## See also
 

package/plugins/sp/skills/spur-cli/SKILL.md

@@ -44,7 +44,7 @@ Pick the noun, read its reference. Each Tier A and Tier B reference owns that no
 | **Tier A** | **feature** | Feature tree: author with hierarchical IDs (DD-14), acceptance criteria (Gherkin), status lifecycle, move subtrees, `check --json` | [references/features.md](references/features.md) |
 | **Tier A** | **rule** | Constraint quality gate: run presets, author rules, fine-tune, validate rule files/presets, extend engine | [references/rules.md](references/rules.md) |
 | **Tier A** | **workflow** | Dual-mode workflow runtime: author state-machine / transition-flow workflows, validate, run, read traces | [references/workflows.md](references/workflows.md) |
-| **Tier A** | **builder** | Release/PR plumbing: `bump-ver` (including read-only `--check`), `drop-tags`, `publish`, and `pr` review operations | [references/builder.md](references/builder.md) |
+| **Tier A** | **builder** | Release/PR plumbing: `bump-ver` (including read-only `--check`), `drop-tags`, `publish`, the four flat PR verbs (`pr-status`, `pr-check`, `pr-open`, `pr-review`), and the read-only `show-branches` topology report | [references/builder.md](references/builder.md) |
 | **Tier B** | **agent** | Coding-agent execution surface: run prompts via detected/named agents, list agent specs (incl. `agent.fleet` members), start/stop supervised processes, fleet `report`/`join`/`leave`/`wait`/`trace`, readiness check | [references/agent.md](references/agent.md) |
 | **Tier B** | **message** | Durable inter-agent messaging: send, inbox, reply, watch | [references/message.md](references/message.md) |
 | **Tier B** | **self** | Self-management verbs: scaffold (`init`), database maintenance (`maintain`), schema migrations (`migrate`), local web server (`serve`), status overview (`status`); `self init` runs post-scaffold validation probes & layout classification | [references/self.md](references/self.md) |

package/plugins/sp/skills/spur-cli/references/agent.md

@@ -341,9 +341,12 @@ spur agent usage --dry-run  # print would-be changes; write nothing
 spur agent usage --json
 ```
 
-Runs `codexbar usage --format json --provider all` once, writes the snapshot to
+Runs `codexbar usage --format json` once — the operator-enabled provider set, deliberately not an
+all-provider sweep (`--provider all` covers every provider configured in CodexBar, most of them
+uncredentialed, and its wall time is the slowest of all of them) — writes the snapshot to
 `~/.config/spur/agent-usage.json` (`captured_at`, `source`, `providers[]`, `raw`), maps providers
-to executors via `agent.executors[].agent` (or the model's `<provider>/` prefix), and records
+to executors via `agent.executors[].agent` (with the `antigravity-cli` → `antigravity` alias) or the
+model's `<provider>/` prefix, and records
 `owner: quota` availability observations that the standard drain applies — the single availability
 write path. A provider is exhausted when any `primary|secondary|tertiary` window reports
 `usedPercent >= 100`; the window name and `resetsAt` go into the observation reason. Per-provider

package/plugins/sp/skills/spur-cli/references/builder.md

@@ -1,22 +1,27 @@
 ---
 name: spur-cli-builder
-description: "spur-cli noun reference: operate `spur builder` as the release plumbing surface - bump a workspace package (or the `workspace:`-pinned release set) with `bump-ver`, delete release tags with `drop-tags`, with commit + annotated tag + optional push; publish a package to npm with `publish` (and guard version drift with `bump-ver --check`); run the `/sp:dev-pr-review` spine ops with `pr`. Promoted from spur-dev (task 0617, ADR-051); frozen at exactly these four verbs."
+description: "spur-cli noun reference: operate `spur builder` as the release plumbing surface - bump a workspace package (or the `workspace:`-pinned release set) with `bump-ver`, delete release tags with `drop-tags`, with commit + annotated tag + optional push; publish a package to npm with `publish` (and guard version drift with `bump-ver --check`); run the `/sp:dev-pr-review` PR loop with the four flat verbs `pr-status` (read-only status), `pr-check` (submission gate), `pr-open` (push + ensure PR) and `pr-review` (Codex request + wait + collect); report base-relative branch topology with `show-branches`. Promoted from spur-dev (task 0617, ADR-051); frozen at exactly these eight verbs."
 see_also:
   - spur-cli
 ---
 
 # spur builder - release plumbing
 
-`spur builder` is the CLI for **version bumps and release tags**. It wraps the internal
-`release-ops` implementation behind a public four-verb surface. The repo-local forwarder
+`spur builder` is the CLI for **version bumps and release tags**, plus the PR-review loop and the
+read-only branch report. It wraps the internal
+`release-ops` implementation behind a public eight-verb surface. The repo-local forwarder
 (`scripts/commands/release.ts`) and its `spur-dev` dispatcher cases were retired in task 1173; the
 root `bun run bump-ver` / `bun run drop-tags` names route to `spur builder` directly. Package ids are
 the unscoped short names (`@gobing-ai/spur` → `spur`); the released set and the aggregate tag are
 discovered from the repo's own workspace manifests, so the same code serves any git+semver
 monorepo.
 
-This noun is **frozen at exactly four verbs** (`bump-ver`, `drop-tags`, plus `pr` and `publish` from the 2026-10-15 script-absorption entries) by operator consent (`docs/design/harness-surface-governance.md`
-§3) — do not invent additional `builder` subcommands.
+This noun is **frozen at exactly eight verbs** (`bump-ver`, `drop-tags`, `publish` from the 2026-10-15
+script-absorption entries; `show-branches` and the four flat PR verbs `pr-status`, `pr-check`,
+`pr-open`, `pr-review` from the 2026-10-16 feature-L1 entries) by operator consent
+(`docs/design/harness-surface-governance.md` §3) — do not invent additional `builder` subcommands.
+The former `pr <op>` pass-through stays registered as a **hidden, deprecated alias** for one release
+(it prints one stderr deprecation line naming the replacement verb), so it is not listed here.
 
 ## Verb map
 
@@ -25,7 +30,11 @@ This noun is **frozen at exactly four verbs** (`bump-ver`, `drop-tags`, plus `pr
 | `bump-ver [package-id] [version]` | Bump one package (manifest + in-source `binaryVersion` + consumer `workspace:` pins), commit, tag, optionally push; `--check [package-id]` only verifies marketplace/plugin versions (exit 1 on drift) | `--all` `--push` `--check` `--json` |
 | `drop-tags [package-id] <version>` | Delete a package's release tag (local only by default) | `--all` `--remote` `--json` |
 | `publish <dir>` | CI npm publish: resolve `workspace:`/`catalog:` ranges, `build:bundle`, `npm publish --access public`, restore the manifest | `--otp` |
-| `pr <op>` | PR-review spine ops for `/sp:dev-pr-review`: `preflight` `push` `ensure` `hygiene` `request` `wait` `collect` `status` | `--base` `--since` `--head` `--json` `--status-file` |
+| `pr-check [--base <branch>] [--scan-only]` | Submission gate for `/sp:dev-pr-review`: preflight then the `base...HEAD` hygiene scan; a preflight failure stops before hygiene (`PASS`/`WARN`/`BLOCK`/`FAIL`) | `--base` `--scan-only` `--json` `--status-file` |
+| `pr-open [--base <branch>]` | Publish the branch (never force) and reuse or create its PR (`FOUND`/`CREATED`/`FAIL`) | `--base` `--json` `--status-file` |
+| `pr-review [--force] [--focus <text>] [--no-wait]` | Post the `@codex review` request, wait, then collect (`CLEAN`/`FINDINGS`/`PENDING`/`FAIL`; exit 3 = pending) | `--force` `--focus` `--no-wait` `--timeout` `--interval` `--json` `--status-file` |
+| `pr-status [--since <iso>] [--head <sha>]` | Read-only PR/CI/Codex status with the current-HEAD review as `review` (no verdict) | `--since` `--head` `--json` `--status-file` |
+| `show-branches` | Read-only branch topology report against a base (default `markdown` with a condensed mermaid `gitGraph`) | `--format` `--json` `--base` `--local` `--remote` `--pr` `--limit` `--max-commits` `--hide-contained` `--theme` |
 
 A bare `bump-ver <version>` (single positional that parses as semver) or explicit `--all` bumps
 every package pinned via `workspace:` by another workspace package, then adds per-package trace
@@ -58,14 +67,78 @@ spur builder drop-tags spur 0.1.4           # delete the local tag @gobing-ai/sp
 spur builder drop-tags --all 0.1.4 --remote # delete per-package + aggregate tags, locally and on origin
 ```
 
-## `pr` - PR-review spine ops
+## `pr-status`, `pr-check`, `pr-open`, `pr-review` - the PR-review loop
 
 ```bash
-spur builder pr preflight --json            # repo/gh checks
-spur builder pr ensure --base main --json   # reuse or create the branch PR
-spur builder pr wait --since "$t" --head "$sha" --json   # exit 3 = still pending
-spur builder pr status --json               # read-only composite status
+spur builder pr-status --json                          # read-only composite status + .review
+spur builder pr-check --base main --json               # preflight + hygiene submission gate
+spur builder pr-check --scan-only --json               # hygiene alone (local review on a dirty tree)
+spur builder pr-open --base main --json                # push, then reuse or create the PR
+spur builder pr-review --focus "migration safety" --json   # request → wait → collect
+spur builder pr-review --no-wait --json                # post the request, return PENDING
+spur builder pr-review --force --json                  # force a fresh review of the current HEAD
 ```
 
-Absorbed from `plugins/sp/scripts/pr-reviewing.ts` (script-absorption PR-7); driven by
-the `pr-review` workflow. Exit codes: `0` ok, `1` usage, `2` hard failure, `3` wait timeout.
+Four flat verbs over the ops absorbed from `plugins/sp/scripts/pr-reviewing.ts` (script-absorption
+PR-7); driven by the `pr-review` workflow. Each composes existing ops and embeds their records in
+one JSON object per verb: `pr-status` → the status object plus `review` (collect, or `null` with no
+PR); `pr-check` → `{ ok, verdict, preflight, hygiene }`; `pr-open` → `{ ok, verdict, push, pr }`;
+`pr-review` → `{ ok, verdict, request, findings }`.
+
+- **`--status-file`** holds the verb's one-word verdict: `PASS`/`WARN`/`BLOCK`/`FAIL` (`pr-check`),
+  `FOUND`/`CREATED`/`FAIL` (`pr-open`), `CLEAN`/`FINDINGS`/`PENDING`/`FAIL` (`pr-review`).
+  `pr-status` is read-only and writes none.
+- **Exit codes:** `0` ok, `1` usage, `2` hard failure, `3` wait timeout — exit 3 is `PENDING`
+  (pending, never failure; collect later with `pr-status`).
+- **`--head`:** `pr-status` pins the reviewed commit; it defaults to the current local HEAD, and an
+  explicit pin that no longer matches the PR head fails loud instead of reporting a moved commit.
+- **Deduping:** `pr-review` collects without a new request when the exact HEAD is already reviewed,
+  and returns `PENDING` when a marked request is still in flight; `--force` requests a fresh review
+  (`mode=rerun`). Never force-pushes.
+
+```bash
+# deprecated alias, one release: maps the old op names to the verbs above
+spur builder pr preflight --json     # -> spur builder pr-check
+spur builder pr status --json        # -> spur builder pr-status
+```
+
+## `show-branches` - read-only branch topology report
+
+```bash
+spur builder show-branches                      # markdown: summary table + condensed mermaid gitGraph
+spur builder show-branches --base origin/main   # measure every branch against another base
+spur builder show-branches --format json        # raw { base, generatedAt, branches[], omitted, warnings[] }
+spur builder show-branches --pr --limit 50      # add open pull-request state, keep up to 50 rows
+```
+
+One row per branch — local, remote-only, or the detached HEAD by short sha — with the fork point,
+commits ahead/behind the base, the contained flag (`ahead == 0`, i.e. everything in it is already in
+the base), the last commit, and the worktree path that has it checked out. Base resolution is
+`--base <ref>`, else the `origin/HEAD` target, else `main`. `--local` / `--remote` filter the ref
+namespace (mutually exclusive), `--limit <n>` (default 30) caps rows by most recent commit and
+reports the omitted count, and `--pr` adds the open pull-request number/state/review decision from a
+single `gh pr list` call (a missing or unauthenticated `gh` degrades to null PR fields plus one
+warning, never a failure).
+
+| Flag | Description |
+| ---- | ----------- |
+| `--format <markdown\|json\|text>` | Output format; `markdown` is the default |
+| `--json` | Alias of `--format json` |
+| `--base <ref>` | Base ref (default: the `origin/HEAD` target, else `main`) |
+| `--local` / `--remote` | Restrict to local or remote branches |
+| `--pr` | Enrich rows with open pull-request state (one `gh pr list` call) |
+| `--limit <n>` | Maximum branch rows (default 30) |
+| `--max-commits <n>` | Maximum commit nodes per branch line in the graph (default 3) |
+| `--hide-contained` | Drop contained branches from the graph instead of drawing their join |
+| `--theme <name>` | Mermaid theme for the graph init directive |
+
+The graph draws the base line, one `branch` per open branch, a `+N earlier` summary node for the
+commits a cap hides, `HIGHLIGHT` tips, `REVERSE` reverts and the tag names of the commits it shows.
+Read-only: it never creates, moves or deletes a ref, config entry, index entry or worktree.
+
+The graph rules are `mermaid@11.15.0` HIGH, pinned at `apps/web/package.json:28` and asserted by
+`apps/web/tests/branch-topology-graph.heavy.test.ts:155`. The `--pr` vocabulary is `gh@2.102.0` HIGH at
+`https://cli.github.com/manual/gh_pr_list` (read 2026-10-16), measured against this repo's own PRs.
+
+**Exit codes:** `0` ok, `1` usage (unknown `--format`, non-positive `--limit`/`--max-commits`,
+unknown base ref, `--local` with `--remote`), `2` git failure (not a repository, `git` missing).

package/plugins/sp/skills/spur-cli/references/features.md

@@ -30,7 +30,7 @@ what* or *how to write a scenario*, this skill.
 | `refresh` | Rebuild INDEX + each feature `## Tasks` table from task edges (**docs only**; no status change) | `--feature <id>` `--all` `--folder` `--json` |
 | `check [id]` | Validate one feature / the tree; the 4-layer gate; `--fix` repairs structural findings in place | `--strict` `--fix` `--as <status>` `--folder` `--json` |
 | `sync [id]` | Align feature **lifecycle status** with linked task states (real transitions + guards) | `--all` `--dry-run` `--force` `--folder` `--json` |
-| `verify [id]` | The `feature-verification` pass: run the check set once and record the bound PASS/FAIL receipt — workflow-internal (`feature-lifecycle` runs it) | `--run-id <id>` `--cmd <command>` `--confidence <level>` `--ack-low-confidence` |
+| `verify [id]` | The `feature-verification` pass: run the check set once and record the bound PASS/FAIL receipt — workflow-internal (`feature-lifecycle` runs it) | `--run-id <id>` `--cmd <command>` |
 | `handoff [id]` | The `idea-pipeline` finalization: task ordering, roster refresh, handoff report — workflow-internal | `--run-id <id>` `--spur-bin <cmd>` |
 
 **`refresh` vs `sync` (do not conflate):**

package/plugins/sp/skills/spur-cli/references/workflows/authoring-workflows.md

@@ -138,7 +138,7 @@ Spur's host additionally registers (`registerSpurBuiltins`, `packages/app/src/wo
 
 | Kind | Capability |
 | ---- | ---------- |
-| Action | `agent.run` (model call via `spur agent run`; `executor: 'fleet'` dispatches into the agent fleet), `decide` (inline `id`/`method`/`question`/`choices`/`default`/`evidence` → outcome written to `resultFile`; catalog-id references are pending task 1094 — use `spur decision run` for catalog decisions), `command.gate`, `rule.check`, `doctor.probe`, `response.validate`, `proof.fingerprint`, `run.artifact`, `file.exists`, `file.read`, `file.read.into-var`, `http.request`, `hitl.confirm`, `hitl.select`, `hitl.input`, `shell` (streaming) |
+| Action | `agent.run` (model call via `spur agent run`; `executor: 'fleet'` dispatches into the agent fleet), `decide` (inline `id`/`method`/`question`/`choices`/`default`/`evidence` → outcome written to `resultFile`; catalog-id references are pending task 1094 — use `spur decision run` for catalog decisions), `command.gate`, `rule.check`, `doctor.probe`, `proof.fingerprint`, `run.artifact`, `file.exists`, `file.read`, `file.read.into-var`, `http.request`, `hitl.confirm`, `hitl.select`, `hitl.input`, `shell` (streaming) |
 | Guard | `shell` (env-aware), `contract-violation` |
 
 Order matters for both guards and conditions: **the first that passes wins.** Put the discriminating

package/plugins/sp/skills/spur-dev/references/dev-operations.md

@@ -590,12 +590,11 @@ host instructions does not add one. An opt-in gate is explicit: `gitmsg --check
      - `keepachangelog` (default): `## [<version>] - <date>` header, then category headings per the keepachangelog convention — `### Added` / `### Fixed` / `### Changed` / `### Removed` / `### Other` — mapped from conventional-commit types.
      - `simple`: flat bulleted list grouped by type heading (`### feat`, `### fix`, …).
   6. Emit: with `<file>`, insert the section into that file above its newest `## [` release heading (or after its title when none exists) and touch nothing else in the file; without `<file>`, print it to stdout.
-  7. **Verify claims before emitting — two checks, both required, on every claim bullet.** Classify first: an *API/library claim* is a bullet asserting what code, an API, a library, a dependency or a version does — skip merge/bookkeeping bullets that assert no such fact (a status move, a filing, a doc relocation). Then run both checks and append one HTML comment line directly under the bullet carrying both results: `<!-- src: <citation> · <HIGH|MEDIUM|LOW> -->`.
-     - **(a) Source citation — the anchor.** Internal claims (what a commit or the code does): confirm against the commit diff (`git show --stat <hash>`, reading hunks when the summary asserts behavior) or the artifact's presence in the tree; cite `path[:line]` — bare path for whole-file claims, `path:line` for a specific behavior or symbol. External claims (framework/library/version behavior): confirm against official docs for the installed version; cite the URL. An anchor you cannot produce fails the check — reword the bullet or drop the claim; a citation is not a citation until it names something a reader can open.
-     - **(b) Confidence level — exactly one in-rubric token.** HIGH = the diff/artifact confirms the summary as written; MEDIUM = the evidence is real but narrower than the summary; LOW = cannot be confirmed from available sources (append the reason in one clause). A missing level, an off-rubric token, or two levels on one bullet fails the check.
-     - **Defect precision decides what must be fixed.** Both checks are precise once a bullet is classified as a claim: an annotation missing its anchor or its level is unambiguously wrong and blocks emitting. Which bullets *are* claims is the heuristic half — resolve it by this step's rule, and for a genuinely borderline bullet say so in the bullet's body rather than annotating or skipping it silently.
-  8. Self-check before emitting: every short hash in `<since>..<until>` appears exactly once, and every claim bullet carries exactly one `<!-- src: … -->` comment holding exactly one anchor and exactly one of `HIGH`, `MEDIUM`, `LOW` — no unannotated claim bullets, no duplicate annotations, no doubled or off-rubric levels. Fix any miss, duplicate, or bad level; do not report a verdict.
-  9. Reply in at most three lines: the range, bullet counts per category plus verified-claim counts (`x HIGH / y MEDIUM / z LOW`), and the output target.
+  7. **Verify claims before emitting — one required check on every claim bullet.** Classify first: an *API/library claim* is a bullet asserting what code, an API, a library, a dependency or a version does — skip merge/bookkeeping bullets that assert no such fact (a status move, a filing, a doc relocation). Then run the check and append one HTML comment line directly under the bullet carrying its anchor: `<!-- src: <citation> -->`. No confidence level is recorded (ADR-138): the anchor is the evidence.
+     - **Source citation — the anchor.** Internal claims (what a commit or the code does): confirm against the commit diff (`git show --stat <hash>`, reading hunks when the summary asserts behavior) or the artifact's presence in the tree; cite `path[:line]` — bare path for whole-file claims, `path:line` for a specific behavior or symbol. External claims (framework/library/version behavior): confirm against official docs for the installed version; cite the URL. An anchor you cannot produce fails the check — reword the bullet or drop the claim; a citation is not a citation until it names something a reader can open.
+     - **Defect precision decides what must be fixed.** The check is precise once a bullet is classified as a claim: an annotation missing its anchor is unambiguously wrong and blocks emitting. A summary broader than its evidence is reworded to what the anchor shows. Which bullets *are* claims is the heuristic half — resolve it by this step's rule, and for a genuinely borderline bullet say so in the bullet's body rather than annotating or skipping it silently.
+  8. Self-check before emitting: every short hash in `<since>..<until>` appears exactly once, and every claim bullet carries exactly one `<!-- src: … -->` comment holding exactly one anchor — no unannotated claim bullets, no duplicate annotations. Fix any miss or duplicate; do not report a verdict.
+  9. Reply in at most three lines: the range, bullet counts per category plus the verified-claim count, and the output target.
 - **Invariants:** Bullets are derived from `git log` only; the claim-verification pass (step 7) adds evidence from commit diffs, the working tree, and official docs. No quality gates — no `bun run gate`/lint/typecheck/test/`spur-check`/rule runs, and no edits beyond the one inserted section (its verification comments included). The file is left uncommitted.
 
 ### 9. gitmsg

package/plugins/sp/skills/spur-dev/references/execution-worktree-landing.md

@@ -425,7 +425,7 @@ git checkout <base-ref> && git merge --no-ff -m "<prepared message>" <branch>
 #     git checkout <base-ref> && git merge --no-commit <branch>
 # 2. resolve source conflicts by hand; generated files are then regenerated with the project's
 #    generator, never hand-merged
-#    (this repo: bun run build:plugin-lib && bun run --filter @gobing-ai/spur build:bundle)
+#    (this repo: bun run --filter @gobing-ai/spur build:bundle)
 # 3. stage every resolved path and regenerated bundle through the guard — an unmerged or
 #    unstaged path makes step 5 abort, and a conflict-marked path exits 3 (resolve, then retry):
 #      spur workflow commit-guard stage --run "$RUN_ID" -- <resolved paths and regenerated bundles>

package/plugins/sp/skills/spur-dev/references/flag-glossary.md

@@ -209,8 +209,9 @@ wraps the one resolved ticket inside the worktree before the merge, and is skipp
 **Anchor:** `#flag-force`.
 
 Bypass a specific named guard that would otherwise stop the command (e.g. a shippable check on
-`dev-verify`/`dev-verifyall`). Named, not global: the command documentation states which guard is
-forced. Never bypasses lifecycle status transitions or irreversible HITL gates.
+`dev-verify`/`dev-verifyall`, or the per-HEAD review dedupe on `dev-pr-review`). Named, not global:
+the command documentation states which guard is forced. Never bypasses lifecycle status transitions
+or irreversible HITL gates.
 
 ### `--feature <id>` — scope the operation to a feature