Skip to content

cskwork/supergoal-skill / skills/supergoal

supergoal

Unverified

Route objective-driven development, verification, planning, "teach/explain", codebase learning, and skill evaluation through the Supergoal workflow. Use when Supergoal is requested or an autonomous delivery workflow is needed.

FileKindSize
SKILL.mdskill md12.8 KB
agents/analyst.mdmarkdown1.5 KB
agents/architect.mdmarkdown1.7 KB
agents/code-reviewer.mdmarkdown2.5 KB
agents/db-reader.mdmarkdown2.0 KB
agents/debugger.mdmarkdown2.0 KB
agents/designer.mdmarkdown6.3 KB
agents/executor.mdmarkdown2.8 KB
agents/explore.mdmarkdown2.0 KB
agents/qa-auditor.mdmarkdown4.3 KB
agents/qa-tester.mdmarkdown3.2 KB
agents/security-reviewer.mdmarkdown1.2 KB
agents/skill-forger.mdmarkdown1.6 KB
agents/skill-miner.mdmarkdown1.6 KB
reference/agent-browser.mdmarkdown2.8 KB
reference/arch.mdmarkdown5.1 KB
reference/archify.mdmarkdown3.6 KB
reference/db-access.mdmarkdown2.9 KB
reference/debugging.mdmarkdown6.5 KB
reference/delivery-gate.mdmarkdown6.6 KB
reference/domain-context.mdmarkdown7.8 KB
reference/domain-rules.mdmarkdown1.6 KB
reference/engagement.mdmarkdown3.8 KB
reference/functional-ui.mdmarkdown6.4 KB
reference/harness-eval.mdmarkdown28.7 KB
reference/interview.mdmarkdown7.7 KB
reference/learn-domain.mdmarkdown12.7 KB
reference/market-research.mdmarkdown1.7 KB
reference/observability.mdmarkdown5.0 KB
reference/plan-grounding.mdmarkdown4.3 KB
reference/playwright-cli.mdmarkdown2.6 KB
reference/prototype.mdmarkdown4.5 KB
reference/qa-only.mdmarkdown12.7 KB
reference/qa.mdmarkdown7.9 KB
reference/reporting.mdmarkdown1.5 KB
reference/research.mdmarkdown2.7 KB
reference/review-only.mdmarkdown2.4 KB
reference/role-loop.mdmarkdown26.7 KB
reference/rules.mdmarkdown982 B
reference/skill-mine.mdmarkdown7.6 KB
reference/taste-aesthetics.mdmarkdown7.5 KB
reference/taste-skill-v2.mdmarkdown18.8 KB
reference/taste-sources.mdmarkdown3.0 KB
reference/teach.mdmarkdown28.0 KB
reference/ui-ux.mdmarkdown4.0 KB
reference/vercel-host.mdmarkdown3.6 KB
reference/wayfinder.mdmarkdown7.2 KB
templates/GOAL.mdmarkdown1.3 KB
templates/PLAN.mdmarkdown1.4 KB
templates/QA.mdmarkdown1.2 KB
templates/R-LOOP.mdmarkdown569 B
templates/Z-DONE.mdmarkdown301 B
templates/arch-report.htmlother8.1 KB
templates/commit-gate.shexecutablescript11.6 KB
templates/contrast-gate.mjsexecutablescript4.3 KB
templates/db-access/.env.exampleother451 B
templates/db-access/check-connection.shexecutablescript134 B
templates/db-access/db-access.cmdscript39 B
templates/db-access/db-access.mjsexecutablescript5.2 KB
templates/db-access/read-only-query.shexecutablescript138 B
templates/db-access/schema-summary.shexecutablescript132 B
templates/domain-agent/code-map.mdmarkdown744 B
templates/domain-agent/config.jsonconfig291 B
templates/domain-agent/decisions/README.mdmarkdown270 B
templates/domain-agent/flows/README.mdmarkdown800 B
templates/domain-agent/freshness.mdmarkdown1.2 KB
templates/domain-agent/glossary.mdmarkdown781 B
templates/domain-agent/index.mdmarkdown1.3 KB
templates/domain-agent/invariants.mdmarkdown504 B
templates/domain-agent/qa/README.mdmarkdown879 B
templates/domain-agent/qa/nav-map.mdmarkdown1.2 KB
templates/domain-agent/test-map.mdmarkdown432 B
templates/domain-agent/tickets/README.mdmarkdown204 B
templates/domain-onboarding.htmlother9.2 KB
templates/harness-eval-case.yamlconfig4.4 KB
templates/harness-eval-cases/authored/authored-underspec-001-deepmerge.yamlconfig2.2 KB
templates/harness-eval-cases/authored/authored-underspec-002-csvline.yamlconfig2.0 KB
templates/harness-eval-cases/authored/authored-underspec-003-authz-cache.yamlconfig1.6 KB
templates/harness-eval-cases/fixtures/README.mdmarkdown2.8 KB
templates/harness-eval-cases/fixtures/revfactory-case-002-async-race/package.jsonmanifest124 B
templates/harness-eval-cases/fixtures/revfactory-case-002-async-race/src/cache.mjsscript494 B
templates/harness-eval-cases/fixtures/revfactory-case-002-async-race/test/cache.hidden.test.mjsscript2.2 KB
templates/harness-eval-cases/fixtures/revfactory-case-002-async-race/test/cache.visible.test.mjsscript950 B
templates/harness-eval-cases/fixtures/revfactory-case-003-refactoring/package.jsonmanifest125 B
templates/harness-eval-cases/fixtures/revfactory-case-003-refactoring/src/order.mjsscript1.3 KB
templates/harness-eval-cases/fixtures/revfactory-case-003-refactoring/test/order.hidden.test.mjsscript2.2 KB
templates/harness-eval-cases/fixtures/revfactory-case-003-refactoring/test/order.visible.test.mjsscript1.2 KB
templates/harness-eval-cases/fixtures/underspec-001-deepmerge/package.jsonmanifest124 B
templates/harness-eval-cases/fixtures/underspec-001-deepmerge/src/merge.mjsscript84 B
templates/harness-eval-cases/fixtures/underspec-001-deepmerge/test/merge.hidden.test.mjsscript1013 B
templates/harness-eval-cases/fixtures/underspec-001-deepmerge/test/merge.visible.test.mjsscript276 B
templates/harness-eval-cases/fixtures/underspec-002-csvline/package.jsonmanifest122 B
templates/harness-eval-cases/fixtures/underspec-002-csvline/src/csv.mjsscript77 B
templates/harness-eval-cases/fixtures/underspec-002-csvline/test/csv.hidden.test.mjsscript804 B
templates/harness-eval-cases/fixtures/underspec-002-csvline/test/csv.visible.test.mjsscript240 B
templates/harness-eval-cases/fixtures/underspec-003-authz-cache/package.jsonmanifest126 B
templates/harness-eval-cases/fixtures/underspec-003-authz-cache/src/authorizer.mjsscript601 B
templates/harness-eval-cases/fixtures/underspec-003-authz-cache/test/authorizer.hidden.test.mjsscript3.8 KB
templates/harness-eval-cases/fixtures/underspec-003-authz-cache/test/authorizer.visible.test.mjsscript1.2 KB
templates/harness-eval-cases/revfactory-case-001-rest-api.yamlconfig2.1 KB
templates/harness-eval-cases/revfactory-case-002-bug-fix.yamlconfig2.4 KB
templates/harness-eval-cases/revfactory-case-003-refactoring.yamlconfig2.4 KB
templates/harness-eval-cases/revfactory-case-004-documentation.yamlconfig2.1 KB
templates/harness-eval-cases/revfactory-case-005-complex.yamlconfig2.0 KB
templates/harness-eval-cases/revfactory-case-006-research.yamlconfig2.1 KB
templates/harness-eval-cases/revfactory-case-007-interpreter.yamlconfig2.1 KB
templates/harness-eval-cases/revfactory-case-008-microservice.yamlconfig2.1 KB
templates/harness-eval-cases/revfactory-case-009-sql-engine.yamlconfig2.0 KB
templates/harness-eval-cases/revfactory-case-010-crdt.yamlconfig2.0 KB
templates/harness-eval-cases/revfactory-case-011-raft-kv.yamlconfig2.1 KB
templates/harness-eval-cases/revfactory-case-012-spreadsheet.yamlconfig2.1 KB
templates/harness-eval-cases/revfactory-case-013-bytecode-vm.yamlconfig2.1 KB
templates/harness-eval-cases/revfactory-case-014-event-sourcing.yamlconfig2.1 KB
templates/harness-eval-cases/revfactory-case-015-lsp.yamlconfig2.3 KB
templates/harness-eval-cases/run-local-eval.mjsscript43.3 KB
templates/harness-eval-cases/run-underspec-n3.mjsscript41.1 KB
templates/harness-eval-external/deepswe/README.mdmarkdown9.9 KB
templates/harness-eval-external/deepswe/prepare-supergoal-arm.mjsscript4.4 KB
templates/harness-eval-external/deepswe/run-default-suite.mjsscript6.1 KB
templates/harness-eval-external/deepswe/run-full-cycle.mjsscript25.3 KB
templates/harness-eval-external/deepswe/task-set.yamlconfig12.2 KB
templates/harness-eval-external/featadd/README.mdmarkdown3.9 KB
templates/harness-eval-external/featadd/features.tsvother1.6 KB
templates/harness-eval-external/featadd/gen.shscript4.0 KB
templates/harness-eval-external/featadd/package.pyscript6.2 KB
templates/harness-eval-gate.mjsscript24.9 KB
templates/harness-eval-report.mdmarkdown5.8 KB
templates/harness-eval-result.jsonconfig11.9 KB
templates/harness-eval-runner.mjsscript19.9 KB
templates/harness-eval-stats.mjsscript1.8 KB
templates/learn-grounding-gate.mjsscript6.1 KB
templates/observability/heartbeat.schema.jsonconfig2.5 KB
templates/observability/sg-emit.shexecutablescript5.4 KB
templates/qa-gate.shexecutablescript6.9 KB
templates/qa-only-gate.shexecutablescript5.1 KB
templates/qa-report.mdmarkdown2.8 KB
templates/rules.mdmarkdown301 B
templates/run-state-gate.mjsscript2.2 KB
templates/run-state.jsonconfig474 B
templates/skill-frontmatter-gate.mjsscript3.7 KB
templates/skill-install-audit.mjsexecutablescript3.7 KB
templates/skill-mine/mine.mjsscript7.8 KB
templates/skill.md.templateother568 B
templates/teach-lesson-gate.mjsscript5.4 KB
templates/teach/README.mdmarkdown4.1 KB
templates/teach/assets/lesson-book.jsscript5.8 KB
templates/teach/assets/lesson-template.htmlother6.1 KB
templates/teach/assets/lesson.cssother11.8 KB
templates/teach/assets/quiz.jsscript3.2 KB

templates/commit-gate.sh

View on GitHub
#!/usr/bin/env bash
# /supergoal commit gate — the literal precondition for commit/merge in a GREENFIELD/DEBUG/LEGACY run
# (reference/delivery-gate.md "Commit gate"). Run it and see PASS before committing/merging into the
# target/integration branch. It blocks the commit while the run vault is not green:
#   1) GOAL.md exists and its ## Success Criteria is seeded (>=1 checkbox row),
#   2) no decision gate is still open (ask-user/unresolved => block; resolve or ask the user, do not commit),
#   3) every Success Criterion and QA Case is checked — an unchecked '- [ ]' (including a surfaced
#      criterion or a leftover placeholder row) blocks commit,
#   4) PLAN.md ## Approval is approved-by-user or auto-approved (a pending plan blocks),
#   5) QA.md Backward-trace is exactly 'clean' (no orphan scope),
#   6) non-exact Reproduction Fidelity records residual risk and post-deploy confirmation (QA.md),
#   7) QA.md ## Results has >=1 checked row and no unchecked row,
#   8) QA.md has exactly one canonical '- Verdict: PASS'; for an app run, browser/CLI QA evidence passes,
#   9) at least one trusted command (frozen_repo/evaluator_owned) backs QA.md,
#  10) final run-state.json proves verified refs, Finalize phase, and no blockers,
#  11) exactly one Z-<date>.md completion marker exists with Branch: and Completed: lines.
# NEVER edit this script to make a non-green run commit — resolve the gap or ask the user instead.
#
# Usage: commit-gate.sh <vault-dir> [browser|cli|none]
#   <vault-dir>      the run's changelog folder, e.g. docs/changelog/2026-06/30-commit-gate
#   browser|cli|none app exercised: a browser app, a CLI/library, or none (no app QA to delegate)

set -euo pipefail

usage() { echo "usage: commit-gate.sh <vault-dir> [browser|cli|none]" >&2; exit 2; }
[ $# -ge 1 ] || usage
VAULT="$1"; APPTYPE="${2:-none}"
GOAL="$VAULT/GOAL.md"
PLAN="$VAULT/PLAN.md"
QAMD="$VAULT/QA.md"
RUNSTATE="$VAULT/run-state.json"
fail() { echo "COMMIT-GATE FAIL: $*" >&2; exit 1; }

case "$APPTYPE" in browser|cli|none) ;; *) usage ;; esac

echo "== /supergoal commit gate =="
echo "vault: $VAULT  app-type: $APPTYPE"

# 1) Goal present and seeded: GOAL.md exists and ## Success Criteria has at least one checkbox row.
[ -s "$GOAL" ] || fail "GOAL.md missing/empty — no success criteria to commit against"
criteria_rows="$(awk '
  /^[[:space:]]*##[[:space:]]+Success Criteria/ { ing=1; next }
  /^[[:space:]]*##[[:space:]]/ { ing=0 }
  ing && /^[[:space:]]*-[[:space:]]*\[[ xX]\]/ { rows++ }
  END { print rows+0 }
' "$GOAL")"
[ "$criteria_rows" -ge 1 ] || fail "GOAL.md ## Success Criteria has no checkbox row — seed the criteria at Frame before commit"
echo "  ok: success criteria seeded ($criteria_rows)"

# 2) Decision gates resolved: in the '## Decision Gates' table, no Status cell (col 3) still reads 'open'.
#    Catches unresolved ask-user gates AND an un-filled placeholder row ('open / resolved').
open_gate="$(awk -F'|' '
  /^[[:space:]]*##[[:space:]]+Decision Gates/ { ing=1; next }
  /^[[:space:]]*##[[:space:]]/ { ing=0 }
  ing && /^[[:space:]]*\|/ {
    s=$4; gsub(/^[[:space:]]+|[[:space:]]+$/,"",s); l=tolower(s)
    if (l ~ /(^|[^a-z])open([^a-z]|$)/) { print "OPEN"; exit }
  }
' "$GOAL")"
[ -z "$open_gate" ] || fail "an open decision gate remains in GOAL.md — resolve it or ask the user about the requirement; do not commit on an unresolved/ask-user gate"
echo "  ok: no open decision gate"

# 3) Every criterion checked: no unchecked '- [ ]' row under ## Success Criteria or ## QA Cases.
#    A surfaced criterion the verifier has not ticked, or a leftover placeholder row, blocks here —
#    remove placeholder rows that do not apply instead of ticking them.
unchecked="$(awk '
  /^[[:space:]]*##[[:space:]]+(Success Criteria|QA Cases)/ { ing=1; next }
  /^[[:space:]]*##[[:space:]]/ { ing=0 }
  ing && /^[[:space:]]*-[[:space:]]*\[[[:space:]]\]/ { n++ }
  END { print n+0 }
' "$GOAL")"
[ "$unchecked" -eq 0 ] || fail "GOAL.md has $unchecked unchecked success criterion/QA case — the verifier must tick every box (or the requirement must be resolved with the user) before commit"
echo "  ok: every success criterion and QA case checked"

# 4) Plan approved: PLAN.md ## Approval Status is approved-by-user or auto-approved. A pending status,
#    a placeholder, or a missing PLAN.md blocks — implementation without an approved plan cannot commit.
[ -s "$PLAN" ] || fail "PLAN.md missing/empty — no approved plan to commit against"
approval_line="$(awk '
  /^[[:space:]]*##[[:space:]]+Approval/ { ing=1; next }
  /^[[:space:]]*##[[:space:]]/ { ing=0 }
  ing && tolower($0) ~ /^[[:space:]]*-?[[:space:]]*status:/ { print; exit }
' "$PLAN")"
[ -n "$approval_line" ] || fail "PLAN.md ## Approval has no Status line — record the approval (user OK or auto-approved) before commit"
approval_l="$(printf '%s' "$approval_line" | tr '[:upper:]' '[:lower:]')"
if printf '%s' "$approval_l" | grep -q 'pending'; then
  fail "PLAN.md approval is pending (or the placeholder is unfilled) — get the user's explicit OK, or record the autonomous auto-approval, before commit"
fi
printf '%s' "$approval_l" | grep -qE 'approved-by-user|auto-approved' \
  || fail "PLAN.md approval status is neither approved-by-user nor auto-approved — a plan without approval cannot commit"
echo "  ok: plan approved"

# 5) Backward trace clean: QA.md attests the diff maps back to GOAL.md criteria with no orphan scope.
[ -s "$QAMD" ] || fail "QA.md missing/empty — no verification evidence to commit against"
backward_line="$(grep -m1 -E '^[[:space:]]*Backward-trace:' "$QAMD" || true)"
[ -n "$backward_line" ] || fail "QA.md missing Backward-trace line — reverse trace scope before commit"
backward_norm="$(printf '%s' "$backward_line" | tr '[:upper:]' '[:lower:]' | sed -E 's/^[[:space:]]+|[[:space:]]+$//g; s/[[:space:]]+/ /g')"
[ "$backward_norm" = "backward-trace: clean" ] \
  || fail "Backward-trace is not clean — remove orphan scope or get explicit user acceptance before commit"
echo "  ok: backward trace clean"

# 6) Reproduction Fidelity: exact runs are minimal. Non-exact prod/proxy runs must record the data gap's
#    residual risk and a post-deploy confirmation plan; a synthetic green alone is not conclusive proof.
proof_field() {
  local label="$1"
  awk -v label="$label" '
    /^[[:space:]]*##[[:space:]]+Reproduction Fidelity/ { ing=1; next }
    /^[[:space:]]*##[[:space:]]/ { ing=0 }
    ing {
      line=$0
      sub(/^[[:space:]]*-[[:space:]]*/, "", line)
      low=tolower(line); want=tolower(label) ":"
      if (index(low, want) == 1) {
        sub(/^[^:]*:[[:space:]]*/, "", line)
        gsub(/^[[:space:]]+|[[:space:]]+$/, "", line)
        print line
        exit
      }
    }
  ' "$QAMD"
}
fidelity="$(proof_field "Fidelity level")"
[ -n "$fidelity" ] || fail "QA.md missing Reproduction Fidelity fidelity level"
fidelity_l="$(printf '%s' "$fidelity" | tr '[:upper:]' '[:lower:]' | sed -E 's/^[[:space:]]+|[[:space:]]+$//g')"
case "$fidelity_l" in
  exact)
    echo "  ok: reproduction fidelity exact"
    ;;
  prod-snapshot|synthetic-representative|synthetic-minimal|not-reproduced)
    residual="$(proof_field "Residual risk from data gap")"
    confirm="$(proof_field "Post-deploy confirmation plan")"
    if ! printf '%s' "$residual" | grep -qE '[[:alnum:]]' || printf '%s' "$residual" | grep -qiE '^(todo|tbd|none|n/a|<.*>|\(.*\))$'; then
      fail "non-exact Reproduction Fidelity missing residual risk from data gap"
    fi
    if ! printf '%s' "$confirm" | grep -qE '[[:alnum:]]' || printf '%s' "$confirm" | grep -qiE '^(todo|tbd|none|n/a|<.*>|\(.*\))$'; then
      fail "non-exact Reproduction Fidelity missing post-deploy confirmation plan"
    fi
    echo "  ok: non-exact reproduction fidelity records residual risk and post-deploy plan"
    ;;
  *)
    fail "unknown or placeholder Reproduction Fidelity level '$fidelity' — use exact, prod-snapshot, synthetic-representative, synthetic-minimal, or not-reproduced"
    ;;
esac

# 7) Results evidenced AND green: QA.md ## Results has >=1 checked row and no unchecked row. The checkbox
#    is the status — an unchecked result is not green, and zero rows is an unevidenced after target.
results_state="$(awk '
  /^[[:space:]]*##[[:space:]]+Results/ { ing=1; next }
  /^[[:space:]]*##[[:space:]]/ { ing=0 }
  ing && /^[[:space:]]*-[[:space:]]*\[[xX]\]/ { checked++ }
  ing && /^[[:space:]]*-[[:space:]]*\[[[:space:]]\]/ { unchecked++ }
  END {
    if (unchecked>0) print "RED";
    else if (checked>0) print "OK";
    else print "EMPTY";
  }
' "$QAMD")"
case "$results_state" in
  OK)    echo "  ok: results evidenced (green)" ;;
  RED)   fail "QA.md ## Results has an unchecked row — the after target is not green; fix it before commit" ;;
  *)     fail "QA.md ## Results has no checked row — the after target is not evidenced; finish verification before commit" ;;
esac

# 8) QA verdict: QA.md is the canonical verification record. It must contain exactly one verdict marker,
#    and that marker must be the literal template token '- Verdict: PASS'. Unknown values, placeholders,
#    missing markers, and duplicate markers are incomplete proof. Other vault files are not verdict sources.
verdict_state="$(awk '
  {
    line=$0; sub(/\r$/, "", line)
    low=tolower(line)
    if (low ~ /^[[:space:]]*-?[[:space:]]*verdict[[:space:]]*:/) total++
    if (line == "- Verdict: PASS") pass++
  }
  END { printf "%d %d", total+0, pass+0 }
' "$QAMD")"
set -- $verdict_state
[ "$1" -eq 1 ] && [ "$2" -eq 1 ] \
  || fail "QA.md must contain exactly one canonical '- Verdict: PASS' line — missing, duplicate, placeholder, FAIL/PARTIAL, or unknown verdicts block commit"
if [ "$APPTYPE" != none ]; then
  QAGATE="$(dirname "$0")/qa-gate.sh"
  [ -f "$QAGATE" ] || fail "qa-gate.sh not found next to commit-gate.sh — cannot verify $APPTYPE QA evidence"
  bash "$QAGATE" "$VAULT" "$APPTYPE" || fail "QA evidence gate failed (see qa-gate output above)"
fi
echo "  ok: QA verdict clean"

# 9) A trusted command backs the proof (agent-detected commands cannot be the whole proof).
grep -qE 'frozen_repo|evaluator_owned' "$QAMD" \
  || fail "no trusted command (frozen_repo/evaluator_owned) in QA.md — agent-detected alone cannot prove done"
echo "  ok: trusted command present"

# 10) Final run state: the mutable checkpoint must parse and prove ref safety, final phase, and no open
#     blockers/gates. PLAN.md and QA.md remain canonical for approval and proof commands.
RUNSTATE_GATE="$(dirname "$0")/run-state-gate.mjs"
[ -f "$RUNSTATE_GATE" ] || fail "run-state-gate.mjs not found next to commit-gate.sh — cannot verify final run state"
node "$RUNSTATE_GATE" "$RUNSTATE" || fail "final run-state gate failed (see run-state output above)"
echo "  ok: final run state is safe"

# 11) Completion marker: exactly one Z-<date>.md, created only after every criterion was checked (checks
#     1-3 above prove that), carrying the run branch and the completion timestamp.
z_count=0; z_file=""
for z in "$VAULT"/Z-*.md; do
  [ -e "$z" ] || continue
  z_count=$((z_count+1)); z_file="$z"
done
[ "$z_count" -ge 1 ] || fail "no Z-<date>.md completion marker — it is written only when every GOAL.md criterion is checked; finish the run before commit"
[ "$z_count" -eq 1 ] || fail "multiple Z-*.md completion markers in the vault — a run completes once; remove the stray marker"
[ -s "$z_file" ] || fail "$(basename "$z_file") is empty — record the branch and completion timestamp"
grep -qE '^[[:space:]]*-[[:space:]]*Branch:' "$z_file" \
  || fail "$(basename "$z_file") missing 'Branch:' line — record where the work was done"
grep -qE '^[[:space:]]*-[[:space:]]*Completed:' "$z_file" \
  || fail "$(basename "$z_file") missing 'Completed:' line — record the completion timestamp"
echo "  ok: completion marker $(basename "$z_file") present"

echo "== COMMIT GATE PASS =="
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall