Skip to content

Make Codex and Claude Code subscriptions go further: a local model router that gives routine agent work to economical models and keeps your strongest model for the hard parts.

feat: feed issue-spec improvements back into HiRoute iteration (#131)

澄潭32f085de588a
diff --git a/.agents/README.md b/.agents/README.md
index 49855a83..a36a5d6c 100644
--- a/.agents/README.md
+++ b/.agents/README.md
@@ -33,6 +33,14 @@ and project behavior; a second preview must report zero changes. Conflicts requi
reconciliation, not deleting the manifest or force-overwriting local edits.
Commit the manifest, generated files and links together so worktrees stay pinned.
+The shared [workflow improvement skill](skills/hiroute-workflow-improvement/SKILL.md)
+owns feedback routing, deduplication, stable analysis labels and verification of
+adopted improvements when later work provides comparable context. Issues preserve
+the resumption context across sessions; feedback does not keep an iteration open. Its CLI and shared
+workflow suggestions go upstream; HiRoute policy suggestions stay here. It has no
+Codex host dependency and is exposed to Claude through its own relative link.
+Generated workflow files and their manifest remain owned by issue-spec.
+
## Codex-only skills
| Skill | Why it is not exposed to Claude |
diff --git a/.agents/skills/hiroute-workflow-improvement/SKILL.md b/.agents/skills/hiroute-workflow-improvement/SKILL.md
new file mode 100644
index 00000000..f4ab3101
--- /dev/null
+++ b/.agents/skills/hiroute-workflow-improvement/SKILL.md
@@ -0,0 +1,154 @@
+---
+name: hiroute-workflow-improvement
+description: Improve HiRoute iteration by capturing issue-spec CLI and workflow friction, routing labeled feedback to its owner, and assessing adopted improvements when a later task provides suitable context. Use during relevant project work or requested feedback reviews; not ordinary product bugs or automatic upgrades.
+---
+
+# Improve issue-spec through evidence
+
+Use HiRoute iteration as the source of concrete improvement evidence: observed
+friction becomes feedback, recurring feedback informs CLI/workflow corrections,
+and adopted corrections should improve subsequent HiRoute work. These steps can
+span weeks and unrelated sessions; no original agent or conversation owns a
+continuous follow-up obligation. Labels support
+periodic analysis; filing Issues is an intermediate result, not proof of improvement.
+
+Capture observations while doing the original task, such as repeated manual repair,
+ambiguous guidance, unnecessary steps or missing command capability. Do not launch
+a separate broad audit or require a feedback report for every task.
+Continue the original task wherever possible. Feedback is not a new planning,
+review or delivery gate, and creating an Issue does not authorize its implementation.
+
+HiRoute's repository policy authorizes filing and labeling evidence-backed feedback
+from its work. Honor a user's narrower scope, such as read-only or no publication.
+Do not infer this standing authorization when copying this skill to another project.
+Do not start agents, recurring jobs, workflow upgrades or automatic rule rewrites.
+
+## Establish the cause and destination
+
+Read [instruction ownership](../../README.md), the current project's
+`issue-spec/config.yaml` rules and shared guidance. Inspect the relevant installed
+command's exact `--help`, or the instruction and its owning source. Record the CLI
+revision from `issue-spec version --json`, the generated workflow source revision
+from `../issue-spec-workflow/release.json`, and the project commit when applicable.
+Different installed and generated revisions alone are not a defect.
+
+| Finding | Destination | Category label |
+| --- | --- | --- |
+| CLI behavior, command UX, unsupported capability, incorrect output or error | `higress-group/issue-spec` | `improvement/cli` |
+| Shared workflow or generated instruction gap whose correction remains useful after removing HiRoute names, paths and policy | `higress-group/issue-spec` | `improvement/workflow-generic` |
+| HiRoute policy, project supplement, local skill, validation or repository-specific convention | `higress-group/HiRoute` | `improvement/workflow-project` |
+
+Use the smallest source that actually owns the correction. A stale local recipe or
+an agent ignoring correct instructions is not automatically a CLI defect. Correct
+routine command use first. File only when a concrete usability or instruction gap
+remains; transient network/authentication errors alone do not establish one.
+
+For workflow findings, explain whether the fix survives removal of project policy.
+If ownership remains uncertain, gather a bounded additional read; keep a local draft
+and state the uncertainty instead of guessing the destination. Split genuinely
+independent CLI and workflow causes into linked reports, not copies of one symptom.
+Never edit generated `issue-spec-*` files to implement upstream suggestions.
+
+## Deduplicate and write
+
+Use the [report and analysis guide](references/feedback.md) for the body fields,
+label definitions, provider commands and time-window queries.
+
+1. Verify the destination repository and active backend with read-only CLI/auth
+ inspection; use explicit `--repo` on each command. HiRoute and the upstream above
+ are GitHub repositories. Do not change profiles or credentials to bypass failure.
+ If an explicitly selected backend differs, resolve it before writing.
+2. Search both open and closed discussions in the destination with one to three
+ specific command, symptom or instruction terms using `issue-spec search issues`.
+ Read plausible matches with `issue-spec read issue --comments`. Do not rely only
+ on titles, labels, the first page of a broad query, or a search snippet. Follow
+ relevant remaining pages or narrow the query; disclose bounded search coverage.
+3. Reuse an existing Issue for the same cause and expected correction. Add only new
+ evidence or a distinct recurrence through `issue-spec comment create`; do not
+ repeat an unchanged report. Respect closed/wontfix decisions. A demonstrated
+ regression after a fix may warrant a new Issue linked to the old one; do not
+ reopen it automatically. Split unrelated causes even if their symptoms match.
+4. Prepare a self-contained English body with sanitized reproduction, expected and
+ observed behavior, impact, owning layer, suggested correction and acceptance.
+ Include the minimal scenario and prerequisites needed by a future session; a
+ conversation link or temporary worktree alone cannot carry required context.
+ Distinguish measured facts from hypotheses. A design gap can use an observed
+ task sequence rather than a failing command. Do not manufacture a bug to fill
+ a category or attach private logs, credentials or local absolute paths.
+5. On GitHub, provision missing labels first, then create the ordinary suggestion
+ with `gh issue create --body-file ... --label ...` so creation includes its
+ classification. This is HiRoute's explicit feedback-publication policy. Use
+ issue-spec for selected workflow artifacts and ordinary recurrence comments;
+ non-GitHub Issue creation follows its configured issue-spec backend. Use installed
+ command help rather than invented flags. No Proposal, typed QUESTION/TASK or
+ PROCESS is needed just to collect feedback.
+6. Apply `improvement/feedback` and exactly one category label from the table to
+ every report, including a reused matching Issue. Preserve unrelated labels.
+ Provision missing labels without overwriting existing definitions. For a reused
+ Issue with conflicting category labels, resolve ownership before changing them;
+ do not silently remove others' classification.
+7. Read back the Issue URL, body/comment and labels. If a create returns an uncertain
+ result, search/read before retrying. If labeling fails after creation, retain the
+ URL and report the missing labels; retry only that step after resolving the
+ failure. Never create a replacement Issue just to retry labels, switch providers
+ after a denial, or claim the labeled feedback is complete when it is partial.
+
+Report the Issue URL, category, create/reuse result and any incomplete labeling.
+If nothing actionable was found, say so without filing placeholder Issues.
+
+## Review an interval
+
+When asked, collect the umbrella label from both repositories for the requested
+interval, including closed Issues. Use creation time for new reports and dated
+occurrence comments for recurrences; updated time is only a discovery aid. Group
+by underlying cause and layer, link representative evidence, distinguish unique
+Issues from occurrences, and prioritize by observed impact and recurrence.
+Propose common fixes upstream and project-specific fixes locally. Summarizing
+feedback does not authorize implementation, closure, relabeling history or a schedule.
+
+## Bring improvements back into HiRoute
+
+Resume this loop only when a later related task, an authorized adoption, or a
+requested periodic review makes a feedback item relevant. Do not keep the current
+task open, wait for an upstream release, poll, or scan the entire backlog on every
+iteration. A future session can recover the scenario from its Issue and linked
+durable evidence using the [resumption guide](references/feedback.md#resume-after-a-gap).
+
+When a relevant feedback item has a proposed or released fix, assess its current
+applicability before planning adoption. Read its actual resolution,
+linked implementation and available revision; an Issue closure alone is not proof
+that a fix exists, is installed or addresses HiRoute's scenario. Batch related
+candidates for the user's periodic review instead of repeatedly interrupting work.
+
+- **CLI correction:** identify the tested fix/release and the currently installed
+ revision. Propose adoption when needed. Install or change a global CLI only within
+ the user's authorized scope; a feedback-filing policy does not authorize upgrades.
+- **Shared workflow correction:** use the reviewed CLI revision and the workflow
+ preview/apply procedure in [instruction ownership](../../README.md). Review the
+ generated diff and project supplements together; preserve the manifest and links.
+ Do not hand-patch generated instructions or update them merely to clear a warning.
+- **Project correction:** change the owning HiRoute supplement, skill or validation
+ path through the normal authorized change and PR process. Avoid copying generic
+ upstream rules into local policy when the shared source now supplies them.
+
+Adoption is separate implementation work: propose it when not yet authorized, and
+proceed without asking again when the current task already includes it. Keep
+feedback Issues linked to the corresponding fix and adoption PR/revision.
+
+When a comparable scenario is available within the current scope, validate an
+adopted improvement against the recorded symptom and applicable project checks.
+Recheck current requirements and environment first; historical evidence explains
+the report but does not override today's contract. Record actual results and source
+versions on the feedback Issue or adoption PR.
+
+If the original context is missing, too costly to reconstruct, obsolete or no longer
+relevant, record that limitation and leave the benefit unverified or the scenario
+no longer applicable. State a useful future trigger only when known, such as the
+next task using the affected command. Do not invent a deadline, assign the original
+session ongoing ownership, or reconstruct an old environment solely to finish the
+feedback loop. This does not waive checks required by an actual adoption change.
+
+Do not claim time savings without measurements, count an upstream release as local
+adoption, infer success from silence, or automatically close the report. New relevant
+evidence can resume the same thread later; a remaining cause returns there without
+requiring continuity of agent, conversation or worktree.
diff --git a/.agents/skills/hiroute-workflow-improvement/agents/openai.yaml b/.agents/skills/hiroute-workflow-improvement/agents/openai.yaml
new file mode 100644
index 00000000..61261fe1
--- /dev/null
+++ b/.agents/skills/hiroute-workflow-improvement/agents/openai.yaml
@@ -0,0 +1,6 @@
+interface:
+ display_name: "HiRoute Workflow Improvement"
+ short_description: "Turn iteration friction into verified workflow gains"
+ default_prompt: "Use $hiroute-workflow-improvement to capture issue-spec friction from HiRoute work, route labeled feedback, and preserve context so later relevant work can assess adopted fixes."
+policy:
+ allow_implicit_invocation: true
diff --git a/.agents/skills/hiroute-workflow-improvement/references/feedback.md b/.agents/skills/hiroute-workflow-improvement/references/feedback.md
new file mode 100644
index 00000000..0325e8e5
--- /dev/null
+++ b/.agents/skills/hiroute-workflow-improvement/references/feedback.md
@@ -0,0 +1,129 @@
+# Feedback records and labels
+
+## Stable taxonomy
+
+Every feedback Issue carries `improvement/feedback` and exactly one category:
+
+| Label | Description | Suggested color |
+| --- | --- | --- |
+| `improvement/feedback` | Evidence-backed CLI or workflow feedback for periodic analysis | `5319e7` |
+| `improvement/cli` | issue-spec CLI behavior, capability or command usability | `0052cc` |
+| `improvement/workflow-generic` | Reusable issue-spec workflow or generated instruction improvement | `1d76db` |
+| `improvement/workflow-project` | Project-specific workflow, policy or skill improvement | `0e8a16` |
+
+Keep these names stable across repositories and dates. Use the umbrella for the
+whole feedback set and the category for grouping; do not add per-session, per-agent
+or per-week labels. GitHub timestamps and the dated observations below support
+interval analysis. Existing unrelated labels remain intact.
+
+## Body fields
+
+Use these fields in ordinary Markdown; they are analysis conventions, not typed
+issue-spec artifacts. Omit unavailable revisions with an explicit reason.
+
+- **Category:** `cli`, `workflow-generic`, or `workflow-project`.
+- **Observed on:** ISO date with timezone; distinguish observation from filing time.
+- **Source:** originating project, public Issue/PR or repository-relative instruction
+ path, and applicable project commit, CLI version/revision and workflow source revision.
+- **Owning layer and routing reason:** why the correction belongs in this repository;
+ for workflow reports, explain the project-independent or project-specific boundary.
+- **Observation:** minimal sanitized command/task sequence, expected versus actual
+ behavior, and concrete impact. Mark hypotheses explicitly.
+- **Recurrence:** observed count and distinct task contexts, or `unknown`; never infer
+ frequency from repeated tool retries or count one report per label as occurrences.
+- **Suggested improvement:** smallest useful correction and any known workaround.
+- **Acceptance and resumption:** observable outcome, minimal sanitized scenario,
+ necessary prerequisites and stable evidence references for a future session.
+ Record known missing context; do not require a complete environment archive.
+- **Related:** matching prior discussions and linked reports for independent causes.
+
+For new evidence on an existing Issue, append the observation date, source revision,
+new reproduction/impact and what differs. Do not overwrite its original evidence.
+Record a recurrence only for a distinct observed occurrence, not another search or
+retry of the same event.
+
+When a correction becomes available, append its public fix/release link and revision.
+When HiRoute adopts it, append the adoption PR/commit, installed CLI or generated
+workflow revision and, when feasible, the comparable scenario and observed result.
+Otherwise record why benefit remains unverified or the scenario no longer applies. Keep
+these distinct from occurrence counts. A useful review separates reported findings,
+upstream fixes available, adopted fixes, verified benefit and remaining friction;
+Issue open/closed state alone cannot represent that progression.
+
+## Resume after a gap
+
+The Issue is the durable handoff, not the original chat, agent or temporary checkout.
+Keep the problem, expected outcome and minimal scenario understandable from its body
+and dated comments; use public commit permalinks for historical paths that may move.
+Summarize essential evidence in sanitized text. Raw logs can stay in ignored local
+artifacts, but future understanding must not depend on those artifacts surviving.
+
+On a later relevant task or requested review, read the selected Issue and linked
+fix/adoption records, then check today's commands, versions and project requirements.
+Distinguish an upstream fix being available, a local adoption, verified benefit,
+unverified benefit, and a scenario that no longer applies. These are plain-language
+observations in dated comments, not a new typed workflow, label set or mandatory
+state machine. Write only when new evidence or a material context change exists.
+
+If context is sufficient, use the smallest comparable current scenario and explain
+any differences from the original. If prerequisites or baseline evidence are missing,
+record what cannot be concluded and stop that validation attempt. If requirements
+have changed, explain why the old scenario no longer applies instead of forcing a
+reproduction. Missing baseline measurements cannot establish a quantitative gain.
+A known future trigger can be recorded without creating a reminder or recurring job.
+
+## Commands and partial failures
+
+Read exact command help before unfamiliar options. Search/read and recurrence
+comments can use the configured issue-spec discussion commands:
+
+```sh
+issue-spec search issues --repo OWNER/REPO --query 'specific symptom' --scope discussion --state all --limit 10 --page 1 --json
+issue-spec read issue --repo OWNER/REPO --issue NUMBER --comments
+issue-spec comment create --repo OWNER/REPO --issue NUMBER --body-file occurrence.md --json
+```
+
+For ordinary GitHub feedback Issues, HiRoute explicitly selects
+[the GitHub skill](../../issue-spec-github/SKILL.md) and `gh issue create` with
+labels. Native issue-spec label support is not a prerequisite, and its absence
+alone does not warrant a CLI improvement Issue when gh meets the task's needs.
+Prepare the body, ensure the umbrella and chosen category exist, then create:
+
+```sh
+gh label list --repo OWNER/REPO --limit 100 --json name,description,color
+gh label create 'improvement/feedback' --repo OWNER/REPO --color 5319e7 --description 'Evidence-backed CLI or workflow feedback for periodic analysis'
+gh label create 'improvement/cli' --repo OWNER/REPO --color 0052cc --description 'issue-spec CLI behavior, capability or command usability'
+gh issue create --repo OWNER/REPO --title 'Concrete improvement' --body-file report.md --label 'improvement/feedback' --label 'improvement/cli'
+gh issue view NUMBER --repo OWNER/REPO --json url,body,labels
+```
+
+The CLI category above is an example; use the category actually selected by the
+routing table. Create only missing labels and do not use `--force`. Paginate a
+larger label inventory before concluding a label is absent. For a reused matching
+Issue, attach missing labels with `gh issue edit --add-label`, preserving unrelated
+labels. Inspect the Issue before retrying an uncertain create; if it exists, repair
+only missing labels rather than submitting again.
+
+This provider choice covers ordinary feedback, not issue-spec planning artifacts.
+For a non-GitHub target use its supported issue-spec Issue/label operations. If
+labeling is unavailable, keep the feedback draft or report an already-created Issue
+as incompletely labeled. Do not switch to GitHub or raw APIs after a backend denial.
+
+## Interval analysis
+
+For GitHub, query each verified repository with the umbrella label, `--state all`
+and an explicit date range. For example, replace the dates with the requested window:
+
+```sh
+gh issue list --repo OWNER/REPO --label 'improvement/feedback' --state all --search 'created:2026-10-01..2026-10-31' --limit 100 --json number,title,url,labels,createdAt,updatedAt,state
+```
+
+This selects new Issues, not all occurrences. Also discover older Issues updated in
+the interval (`updated:START..END`), then read their discussions through issue-spec
+and count only explicitly dated observations in the interval. An update can be a
+label edit or closure and is not evidence of recurrence. Page through results when
+limits are reached, or split the date range and deduplicate by repository + number;
+state incomplete coverage if it cannot be exhausted. Use the user's timezone and
+explicit inclusive start/end dates in the summary. Include relevant fix/adoption
+updates from that window and distinguish verified benefits from untested upgrades
+and scenarios that no longer apply. Do not treat absence of a recorded occurrence as evidence that the workflow never encountered the problem.
diff --git a/.claude/skills/hiroute-workflow-improvement b/.claude/skills/hiroute-workflow-improvement
new file mode 120000
index 00000000..50b71b16
--- /dev/null
+++ b/.claude/skills/hiroute-workflow-improvement
@@ -0,0 +1 @@
+../../.agents/skills/hiroute-workflow-improvement
\ No newline at end of file
diff --git a/AGENTS.md b/AGENTS.md
index ce04db8c..f4397b65 100644
--- a/AGENTS.md
+++ b/AGENTS.md
@@ -9,3 +9,4 @@
- Keep each checkout's default `target/`; share compiler objects only through sccache. Never use external Cargo targets or `cargo clean`, and never clean active runs. Preserve source worktrees and unique evidence during owner-led cleanup.
- For persisted data, configuration, recovery, published CLI/Gateway behavior, OS filesystem/process boundaries or release handoff, use [compatibility maintenance](.agents/skills/hiroute-compatibility/SKILL.md). Keep one current contract per boundary; register intentional legacy support in [the compatibility register](contracts/compatibility-support.v1.json).
- For Desktop layout, text wrapping, visual hierarchy or interactive form-state changes, use [Desktop UI quality](.agents/skills/hiroute-ui-quality/SKILL.md), with affected production states and actual screenshots.
+- For concrete issue-spec CLI or workflow friction encountered during work, use [workflow improvement](.agents/skills/hiroute-workflow-improvement/SKILL.md). File deduplicated, labeled suggestions in the owning repository for later analysis, and assess adopted improvements when a later relevant task has sufficient context; this authorizes feedback collection, not automatic implementation or workflow rewrites. Honor narrower user instructions.
diff --git a/docs/code-map/README.md b/docs/code-map/README.md
index e5aa47e8..2b6b23fd 100644
--- a/docs/code-map/README.md
+++ b/docs/code-map/README.md
@@ -30,7 +30,7 @@ results in the relevant run record.
| Manage the service through CLI or Desktop | [client-core](../../crates/client-core/src), [CLI](../../crates/cli/src), [Desktop host](../../apps/desktop/src-tauri/src), [daemon control](../../crates/daemon/src/control) | [Real control process](../../tools/product-e2e/tests/control_shell.rs), [Desktop test map](../../apps/desktop/tests/README.md) |
| Install and operate native Windows headless, including background service | [Windows operating guide](../standalone-windows.md), [native kernel owners](../../crates/platform/README.md), [Windows installer](../../scripts/install-standalone-windows.py) | [Actual installed Control/Gateway/restart](../../crates/daemon/tests/windows_headless.rs); Task and SCM have different session and administrator boundaries |
| Upgrade Desktop and recover a failed installation | [Updater](../../apps/desktop/src-tauri/src/updates.rs), [installer handshake](../../apps/desktop/src-tauri/src/updates/installer.rs), [resident restart](../../apps/desktop/src-tauri/src/bootstrap.rs) | Preflight → orderly stop → explicit commit; [macOS installation and recovery](../macos-installation.md) |
-| Maintain agent instructions, shared skills and issue-native planning | [Instruction ownership](../../.agents/README.md), [project workflow](../../issue-spec/project/workflow.md) | Pinned generated manifest, individual Claude links and current GitHub artifacts |
+| Maintain agent instructions, shared skills and issue-native planning | [Instruction ownership](../../.agents/README.md), [project workflow](../../issue-spec/project/workflow.md), [feedback routing](../../.agents/skills/hiroute-workflow-improvement/SKILL.md) | Pinned generated manifest, individual Claude links and current GitHub artifacts |
| Select, execute or diagnose a build/test run | [Validation workflow](../../.agents/skills/hiroute-validation/SKILL.md), [test map](testing.md) | [Selection](../../scripts/test-plan.py), [configured runner](../../scripts/validation.py) and revision-bound reports |
| Build macOS Desktop or Linux / Windows headless release candidates | [Release candidate entry](../../scripts/build-release.py), [build and publication guide](../release-builds.md), [independent Unix/Windows candidate jobs](../../.github/workflows/build-release.yml) | [Package-to-publication contract](../../scripts/test-build-release.py), [Linux ABI gate](../../scripts/linux-release-baseline.json), [Windows package/transaction checks](../../scripts/test-standalone-windows.py); final publishing remains in [release.yml](../../.github/workflows/release.yml) |
diff --git a/issue-spec/project/workflow.md b/issue-spec/project/workflow.md
index 6fdba5e8..ec182b64 100644
--- a/issue-spec/project/workflow.md
+++ b/issue-spec/project/workflow.md
@@ -11,3 +11,4 @@ Read with the generated issue-spec skills. Shared artifact rules, bounded reads
- Follow `AGENTS.md` for repository boundaries and task routing; use [HiRoute validation](../../.agents/skills/hiroute-validation/SKILL.md) for checks, execution, failure repair and evidence. Follow config rules for public content and record placement. Public records use English.
- HTML projections remain disabled by `html_review.enabled: false`; load their recipes only when enabled.
- Ordinary GitHub user discussions can use `issue-spec-github`. Selected issue-spec planning and typed artifacts use issue-spec's discussion commands. The repository marker explicitly selects GitHub; an authentication failure must not silently select another backend.
+- Capture concrete CLI/workflow friction with [workflow improvement](../../.agents/skills/hiroute-workflow-improvement/SKILL.md): route by the owning layer, deduplicate and label suggestion Issues for periodic analysis, then assess authorized fixes during later relevant work using durable Issue context; missing or obsolete context can leave benefits unverified without blocking iteration. Continue the original task; feedback does not add a phase or authorize automatic implementation.
diff --git a/scripts/test-plan.py b/scripts/test-plan.py
index 915c6b3d..a2c65494 100644
--- a/scripts/test-plan.py
+++ b/scripts/test-plan.py
@@ -49,8 +49,8 @@ INTEGRATION_SKILL = ".agents/skills/hiroute-integrate/SKILL.md"
PROJECT_AGENT_SKILLS = {
"hiroute-compatibility", "hiroute-cu", "hiroute-design-author", "hiroute-implementation-writer",
"hiroute-integrate", "hiroute-macos-launch", "hiroute-process-coordinator",
- "hiroute-public-pr", "hiroute-ui-quality", "hiroute-validation", "issue-spec-apply", "issue-spec-github",
- "issue-spec-propose", "issue-spec-workflow", "model-metadata-maintainer",
+ "hiroute-public-pr", "hiroute-ui-quality", "hiroute-validation", "hiroute-workflow-improvement",
+ "issue-spec-apply", "issue-spec-github", "issue-spec-propose", "issue-spec-workflow", "model-metadata-maintainer",
}
AGENT_TOOL_COMMANDS = {
"hiroute-cu": [["node", "--test", ".agents/skills/hiroute-cu/tests/" + name]
diff --git a/scripts/test-test-plan.py b/scripts/test-test-plan.py
index a7a4d7b7..fa81f7e5 100644
--- a/scripts/test-test-plan.py
+++ b/scripts/test-test-plan.py
@@ -748,7 +748,11 @@ class IntegrationPreflightTests(unittest.TestCase):
'issue-spec/project/workflow.md', '.claude/skills/issue-spec-apply',
'.agents/skills/hiroute-implementation-writer/SKILL.md',
'.agents/skills/hiroute-validation/SKILL.md', '.claude/skills/hiroute-validation',
- '.agents/skills/issue-spec-workflow/release.json']
+ '.agents/skills/issue-spec-workflow/release.json',
+ '.agents/skills/hiroute-workflow-improvement/SKILL.md',
+ '.agents/skills/hiroute-workflow-improvement/references/feedback.md',
+ '.agents/skills/hiroute-workflow-improvement/agents/openai.yaml',
+ '.claude/skills/hiroute-workflow-improvement']
result = plan.select(paths)
self.assertEqual(result['mode'], 'affected')
self.assertFalse(result['rust'])
@@ -771,7 +775,9 @@ class IntegrationPreflightTests(unittest.TestCase):
for command in plan.AGENT_TOOL_COMMANDS[name]:
self.assertIn(command, result['commands'])
for path in ['.agents/skills/unknown/SKILL.md', '.claude/skills/unknown',
- 'assets/skills/hiroute-cu/SKILL.md', 'assets/skills/hiroute-validation/SKILL.md']:
+ 'assets/skills/hiroute-cu/SKILL.md', 'assets/skills/hiroute-validation/SKILL.md',
+ '.agents/skills/hiroute-workflow-improvement/scripts/unknown.py',
+ 'assets/skills/hiroute-workflow-improvement/SKILL.md']:
self.assertEqual(plan.select([path])['mode'], 'full')
def test_only_the_known_operator_skill_is_tooling(self):