sdd-workspace: owns() cannot distinguish 'unusable' from 'foreign-owned' — infinite slug loop; marker claim is check-then-create
#2618
Six test-discipline gaps from heavy real-world use: mutation-survival diagnosis, escape-proof literals, cached editor diagnostics, e2e mock reloads, verdict-shaped output, seed-path invariants
1
#2612
subagent-driven-development: 15-task port of a ~2,000-line R script hit 5 session limits; coordinator context grew to 830k tokens (Claude Code)
#2611
task-brief: a task that isn't found leaves an empty task-N-brief.md behind (exit 3)
#2599
Parallel plan-and-build path: contract registry, owned packages, convergence critic, DAG build with merge train (build brief)
2
#2587
writing-plans / subagent-driven-development: plans fix the type model task by task, so structural problems surface only at the broad review (Claude Code)
#2583
OpenCode: bootstrap instructs `superpowers:<skill>`, but the plugin registers bare ids - every session opens with failed skill calls
#2576
brainstorming: a bug report gets a restate-and-confirm turn instead of an investigation, and questions never use AskUserQuestion (still on dev after #2560)
3
#2575
Add support for DeepSeek harness
#2568
subagent-driven-development: a finding the reviewer can't verify because it depends on the production environment gets graded Minor and deferred "to check at deploy"
#2567
brainstorming: the Builder check has a fallback for "no subagent tool" but not for a harness that only allows spawning when the user asks
test-driven-development: two blind spots where the test is born from the threat the author already imagined (a stub that pins the predicate; a lock that guards one entry)
1
#2556
using-git-worktrees: the native tool targets the session's repo, and the baseline run assumes exclusive ports
#2553
brainstorming / writing-plans: the spec's claims about today's code are never checked against the code, and the self-review passes clean
#2549
executing-plans: no honest way to ledger a task whose verification runs outside the shell
#2546
test-driven-development / executing-plans: "batch the test and the code to save a turn" is missing from the rationalization table, and fix-pass ledger lines don't require RED output
#2544
Consider submitting superpowers to the Hermes plugin catalog
#2539
subagent-driven-development / writing-plans: acceptance tests written by a different agent from the implementer, oracle rules, and a per-task size cap
#2536
Hermes: using-superpowers bootstrap is injected into delegate_task subagents (Hermes counterpart of #2160)
2
#2530
v7's brainstorm questions are rather annoying
24
#2529
scripts/lint-shell.sh --help output is cut off mid-sentence (usage sed range stops one line early)
