Repository navigation
Description
Problem
Slice 07 of #327 connects the preflight and writer reports after the commands and shared installation contract exist. Originals are packages/agents/source/skills/fix-prose/shared/scripts/preflight.sh:24 and packages/agents/source/skills/write-prose-fix/shared/scripts/context.sh:12.
Acceptance criteria
- AC1: Both generated report entries preserve the caller's arguments and working-directory contract.
- AC2: The switched preflight reproduces the executed original summary contract.
- AC3: The switched writer context reproduces the executed original detailed-report contract.
- AC4: An absent or outdated binary produces the shared one-line nonzero launch failure without automatic fallback.
- AC5: One byte-identical original of each report remains directly usable through the compatibility note.
- AC6: The writer still runs context as its explicit permitted step.
- AC7: Non-functional: forwarding contains no new shell decision logic.
- AC8: Non-functional: canonical generation reproduces every committed deployment change.
- AC9: Guidance matches the minimum binary version, warning releases and supported Bash executor.
- AC10: Non-functional: no owner-tier path changes occur.
Scope and non-goals
This child's existing explicit retention arrangement authorizes retaining one original per report while preserving public entry paths. Non-goal: a resolver, broader permissions, configuration edits, scanner exceptions, new report behavior, hook changes or removing frozen originals. No new shell logic. Canonical sources generate the packages and deployments; generated copies are never edited by hand. No edits to shared libraries, guard scripts, merge scripts, ownership rules, workflow files or harness configuration.
Approach
Use constant forwarding invocations through #321; do not duplicate its resolver. Preserve packages/agents/source/skills/write-prose-fix/SKILL.claude.md:13 and its explicit context step at packages/agents/source/skills/write-prose-fix/SKILL.claude.md:25. Consume #889/#890's Bash-start failure outcome and distinguish it from ordinary nonzero lint status.
Replay the executed summary records (BLOCKED/0 for missing inputs, empty probe and probe error; absent-Vale failing lint PROCEED/0) and context records (evidence mismatch BLOCKED/0, partial failing-lint output, notes precedence and unavailable notices). Add complete probe/count coverage before rollout rather than infer its result. No real writer invocation is needed.
Dependencies
Blocked on: #889
Blocked on: #890
Blocked on: #891
Blocked on: #321
Blocked on: #333
Blocked on: #544
Blocked on: #753
These block rollout merge for shared-launcher, verified-binary, installation and enforcement-protection evidence. #328 completion is unnecessary because hooks remain unchanged.
Size
S. Measured report-body replacements plus their explicitly authorized frozen copies: 2 × (72 + 101) = 346 code lines before forwarding and integration changes. Counts use scc 4.1.0; generated package/deployment output and token metadata are excluded, while source, tests, fixtures and frozen copies count. One PR with fewer than 800 changed code lines and at most 2,000 prose lines. No unbuilt Go size is claimed: measure the actual staged diff before publication and split again if the cap is exceeded.
Verify plan
- AC1, AC2, AC3, AC4, AC5, AC7:
go test ./internal/agentrepo -run '^TestProseEntry' -count=1 -vruns both generated report entries against the original fixture records; include spaces, non-ASCII arguments, --, old/missing binaries and direct originals. - AC6:
mise run test-hooks tests/skills/writersretains existing permission/explicit-step assertions without requiring authenticated probes. - AC8:
mise run check-generated-skillsandapm audit --cifollow canonical generation/deployment and metadata refresh. - AC9:
go test ./internal/agentrepo -run '^TestProse(Preflight|Context|Entry)' -count=1 -vexecutes native macOS/Linux/Windows fixtures with supported Bash and absent Bash; compare guidance withgit log -- docs/agent-skills-migration.mdand verified release evidence. - AC10:
git diff --name-status origin/main...HEADchecks all path kinds against .agents/agent-skills.conf:4 and .agents/agent-skills.conf:9.
At the merged head, record each AC command and result, native platform execution and any skips. Required checks must pass without weakening gates. Obtain independent review of the exact head and record findings dispositions; use signed commits with Assisted-by trailers and the provenance:agent-assisted label. Match documentation to behavior, scan issue/PR text before any later publication, and record the final merge commit and closing reference. This draft authorizes no publication.
Risks
A changed invocation can block context loading or expose detailed findings to the caller. Undo: revert this rollout and regenerate both original entry bodies; keep active workflow evidence.
Operator authority
None
Metadata
Metadata
Assignees
Labels
Type
Fields
Priority
Work type
Projects
- StatusShow more project fieldsBacklog
Activity
tbhb-agent commentedon Oct 27, 2026
Refinement: READY — Route prose report entry points through the shared launcher
Model: gpt-6-astra
Child 07 Route prose report entry points through the shared launcher
Verdict: READY
Checked: Both round 1 gaps are closed. AC4 and AC5 specify the same settled compatibility contract as 06. AC9 consumes 04/05’s executor behavior and verifies the guidance through generated entry points on all three platforms. Existing permission and explicit context invocation remain preserved at
packages/agents/source/skills/write-prose-fix/SKILL.claude.md:13andpackages/agents/source/skills/write-prose-fix/SKILL.claude.md:25. The 346-line relocation baseline and 540-code-line estimate are correct.Gaps: None.
Split: None required.
Definition of done
The definition of done for this issue (Feature). Tick each item and give its evidence.
check-leaks.shwith the repository's private-strings list, and the leak review of each post.docs/, CHANGELOG or help text), or the Verification section says "No doc impact" and why.provenance:agent-assistedlabel.Status:comment names the merge commit.mise run checkis green, and so are the coverage floorsmise run cover-go-checkandmise run cover-py-check, whichcheckdoesn't run.packages/agents/source/commits whatmise run generate-skills, thenmise run skill-tokens, thenapm installrewrite, in that order, andcheck-generated-skills(part oflint) passes.docs/agent-skills-migration.mdor the adoption docs, or the PR's Verification says "No consumer impact" and why.Round: 2 of 3
tbhb-agent commentedon Nov 1, 2026
Refinement: READY — Gather the prose writer’s context in Go
Checked
originidentifiestbhb-dev/devtools. The draft’s early refusals, notes fallback, numbered report, lint output, Vale probes and replacement counting align withpackages/agents/source/skills/write-prose-fix/shared/scripts/context.sh:25,:48,:72,:84,:90,:109and:134.agentrepo, reuse Print prose preflight verdicts from Go #889’s probe/executor helper, and add no shell logic..github/CODEOWNERSor.agents/agent-skills.conf. Operator authority “None” fits the stated scope.Gaps
None.
Split
None required.
Definition of done
Planning coverage only; these items describe future evidence, not completed work.
Assisted-bytrailers and theprovenance:agent-assistedlabel — stated in the plan.Round: 1 of 3