Skip to content

ericrisco/rsc-harness / skills/implement

implement

Verified

Use when an approved plan and task list exist and it is time to turn them into working, reviewed code — ASDD stage 4, the per-task loop after `analyze`: TDD build and self-check, `rsc risk` on the diff, review scaled by tier (0/1/3 reviewers), mandatory controls (tests, build, security, traceability), at most 3 fix rounds, then fix-and-record or park in the decision queue. Progress ledger survives compaction; disjoint tasks fan out via `parallel`. NOT spec writing (that is `specify`), NOT planning (that is `plan`), NOT the closing whole-branch gate (stage 5: `verify` + `review`).

FileKindSize
SKILL.mdskill md24.4 KB
evals/README.mdmarkdown3.1 KB
evals/cases.yamlconfig5.1 KB
references/per-task-review.mdmarkdown4.3 KB
scripts/review-packageexecutablescript1.6 KB
scripts/sdd-workspaceexecutablescript1.3 KB
scripts/task-briefexecutablescript3.4 KB

scripts/task-brief

View on GitHub
#!/bin/sh
# task-brief PLAN_FILE N
# Extracts task N from a plan/tasks markdown file into a brief file in the sdd-workspace dir, and
# prints its path. N may be written 2, 002 or T002: ids compare as numbers.
#
# Two task shapes are read, because `tasks` prescribes a table and older plans used headings:
#   - a table row `| T002 | ... |` → the table's header, its separator and that row;
#   - a heading `### T2 …` / `## T002 …` → the block up to the next ## / ### heading;
#   - a bold block `**T002 — Interfaces**` → that line and what follows up to a blank line.
# Both are printed when both exist (the row is the contract, the heading its detail).
# If task N is not found, exits nonzero with a clear message.

# Resolve the directory of this script portably.
_SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"

usage() {
  printf 'Usage: task-brief <PLAN_FILE> <N>\n' >&2
  printf '  PLAN_FILE  path to the tasks markdown file\n' >&2
  printf '  N          task id to extract: 2, 002 or T002\n' >&2
  exit 1
}

if [ $# -lt 2 ]; then
  printf 'error: task-brief requires PLAN_FILE and N arguments\n' >&2
  usage
fi

PLAN_FILE="$1"
N="${2#T}"
N="${N#t}"

if [ ! -f "$PLAN_FILE" ]; then
  printf 'error: plan file not found: %s\n' "$PLAN_FILE" >&2
  exit 1
fi

case "$N" in
  ''|*[!0-9]*)
    printf 'error: N must be a task number (2, 002 or T002), got: %s\n' "$2" >&2
    exit 1
    ;;
esac

CONTENT="$(awk -v n="$N" '
  function idnum(s) { sub(/^[Tt]/, "", s); return s + 0 }
  BEGIN { n = n + 0; printing = 0; bold = 0; found = 0; head = ""; sep = "" }
  # Table rows: remember the latest header + separator, print the matching row.
  /^\|/ {
    split($0, cell, "|"); id = cell[2]; gsub(/[[:space:]]/, "", id)
    if (id ~ /^[Tt][0-9]+$/) {
      if (idnum(id) == n) { if (!printing) { if (head != "") print head; if (sep != "") print sep }; print; found = 1; next }
    } else if ($0 ~ /^\|[-:| ]+\|[[:space:]]*$/) { sep = $0 }
    else { head = $0; sep = "" }
    if (!printing) next
  }
  # A bold block `**T004 — Interfaces**` (what `tasks` writes under the table): the line and every
  # line after it up to the first blank one. It is the task-local contract an isolated worker needs.
  bold && /^[[:space:]]*$/ { bold = 0 }
  bold { print; next }
  /^\*\*[Tt][0-9]+/ {
    t = $0; sub(/^\*\*/, "", t); sub(/[^Tt0-9].*$/, "", t)
    if (idnum(t) == n) { bold = 1; found = 1; print ""; print; next }
  }
  # `###?` rather than a brace interval: mawk (the default awk on Debian) does not read intervals.
  /^###?[[:space:]]/ {
    if (printing) { printing = 0 }
    if (match($0, /^###?[[:space:]]+[Tt][0-9]+([[:space:](]|-|$)/)) {
      t = $0; sub(/^###?[[:space:]]+/, "", t); sub(/[^Tt0-9].*$/, "", t)
      if (idnum(t) == n) { printing = 1; found = 1; print ""; print; next }
    }
  }
  { if (printing) print }
  END { if (!found) exit 1 }
' "$PLAN_FILE")" || {
  printf 'error: task T%s not found in %s (looked for a "| T%s |" table row and a "### T%s" heading)\n' "$N" "$PLAN_FILE" "$N" "$N" >&2
  exit 1
}

if [ -z "$CONTENT" ]; then
  printf 'error: task T%s not found in %s\n' "$N" "$PLAN_FILE" >&2
  exit 1
fi

# Get the scratch workspace dir.
SCRATCH="$(sh "$_SCRIPT_DIR/sdd-workspace")"

# Derive a readable unique name from the plan file basename and task number.
PLAN_BASENAME="$(basename "$PLAN_FILE" .md)"
NUM="$(printf %s "$N" | sed "s/^0*//")"
OUT="$SCRATCH/brief-${PLAN_BASENAME}-T${NUM:-0}.txt"

printf '%s\n' "$CONTENT" > "$OUT"
printf '%s\n' "$OUT"
rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit.Stars: 468kUpdated Claude CodeCodexVerifiedInstall
rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure.Stars: 468kUpdated Claude CodeCodexVerifiedInstall
rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics.Stars: 468kUpdated Claude CodeCodexVerifiedInstall
ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first.Stars: 194kUpdated Claude CodeCodexVerifiedInstall