Repository navigation
feat(planning): chart a data-sharing item for a selected service that receives user data - #16551
kyle-sexton wants to merge 2 commits into
Conversation
… receives user data /planning:wayfind work step 6 now charts one interview item when a resolution selects an outside service that will receive user data: which fields cross, under what agreement, and, in a regulated repository, what must be in place before build (for example a business associate agreement). One item per service; none when no user data crosses. Its resolution feeds the PRD. Chart step 4 applies the same rule to a settled answer that already selects such a service. A prototype item that proves an outside vendor does something routes to /prototype:pressure-test in its vendor-fit mode. Eval case 28 and its plugin-eval mirror assert that route by skill and intent, not an exact flag; new case 33 pairs a service that receives user data with one that receives none. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01MWmASNT5Knyq99gphnV6B2
Codex Review Summary: ✅ CompletedThis comment shows the latest Codex review activity on this pull request.
ℹ️ About Codex in GitHubYour team has set up Codex to review pull requests in this repo. Reviews are triggered when you
Codex reacts with 👀 while any review is running, comments if it has suggestions, and reacts with 👍 once all reviews finish with no findings. |
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: a6b7137782
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
Lane run report
Failed GitHub API calls
|
|
claude-review needs no new review of Code review: PR #16551I read all 6 changed files in What changes
Consistency checks
Finding (inline): the new routing names a pressure-test vendor-fit mode that doesn't exist on this base. The pressure-test skill offers only I ran none of the PR's listed verification commands myself. The skill-check, schema validation and changelog checks are the author's claims and are unverified. Verifier dropped 0 of 1 candidates. |
|
claude-security-review needs no new review of No security issues found. I read every hunk of all 6 changed files. The change only adds instructions to
Instruction-surface lens. The diff deletes, narrows or softens no standing instruction:
Nothing else here is security-relevant:
Spend: the new eval case (id 33) and the new grader slightly increase prepaid eval-run usage when the suite runs. critical-findings: 0 |
No related issue: owner decision this session; no tracker item covers it.
Summary
/planning:wayfindgains one rule: when a decision selects an outside service that will receiveuser data, the map charts one
interviewitem for that service covering which fields cross, underwhat agreement, and, in a regulated repository, what must be in place before build (for example
whether a business associate agreement is needed). Its resolution feeds the PRD. A service that
receives no user data gets no item. Before this change nothing in the skill raised that question
(grep for
user data,business associateandregulatedacrossplugins/planningfound nosuch rule).
A
wayfind: prototypeitem that proves an outside vendor does something now routes to/prototype:pressure-testin its vendor-fit mode.Fix
plugins/planning/skills/wayfind/SKILL.md: work step 6 holds the data-sharing item rule; chartstep 4 applies it to a settled answer that already selects such a service; the work-step-5
routing table names the vendor-fit mode of
pressure-test.plugins/planning/skills/wayfind/evals/evals.json: case 28 adds an expectation that the vendorcheck runs through
/prototype:pressure-testin a vendor-fit mode, asserted on the skill and thevendor-fit intent, so a slightly different final mode name still passes. New case 33 pairs a
service that receives patient data (one data-sharing item expected) with one that receives none
(no item expected).
plugins/planning/evals/wayfind-prototype-files-on-dossier-folder-and-safe-push/: theplugin-eval mirror of case 28 gets the same expected outcome plus a
vendor-fit-routegrader andits pass/fail samples.
.changes/planning/: aminorfragment.session: AI Hero
Verification
scripts/check-changed-skills.sh origin/main:CHECK-SKILL wayfind: PASS — 0 errors, 6 warning(s)(five pre-existing; one notes the body grew by 8 lines).check-jsonschema --schemafile plugins/skill-quality/reference/evals.schema.json plugins/planning/skills/wayfind/evals/evals.json:ok -- validation done.validate-cases.py plugins/planning/evals: no FAIL; the changed case shows only thejudge-calibration warnings every case in the suite carries.
scripts/check-changelog-fragments.sh --checkand--check-required origin/main: pass.claude plugin eval, run locally on head0542551fafter the branch tookmain:evals.jsonin a scratch copy, 3 runs per arm:VALID. With the plugin 15 of 15 grader checks passed; without it 14 of 15. One case is too few
for the noise report to call a gain, the baseline is near the ceiling, and these graders are
uncalibrated, so no gain is claimed.
wayfind-prototype-files-on-dossier-folder-and-safe-push): the newvendor-fit-routejudge grader calibrated at 12 of 12 against its samples. The case itselfreturned INVALID on two runs (
2 permission denials in the traces): the without-plugin armtries to Read the plugin's
SKILL.mdand is denied. The case's prompt onmainalready asksthe agent to read skill files at their exact path, so this is not caused by this change. No
grader counts are quoted for an invalid run; the case has no valid result yet.
Related
/prototype:pressure-testlanded in feat(prototype): add pressure-test vendor-fit mode and sandbox-only writes #16554, which merged before thischange; this branch was updated from
mainafter it.https://claude.ai/code/session_01MWmASNT5Knyq99gphnV6B2
🤖 Generated with Claude Code