Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/ai-sdlc-framework/ai-sdlc/execute-parallelgit clone --depth 1 https://github.com/ai-sdlc-framework/ai-sdlcWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00088 | $0.05525 |
| Opus 5 | $0.00044 | $0.02763 |
| Sonnet 5 | $0.00018 | $0.01105 |
| Haiku 4.5 | $0.00009 | $0.00553 |
Grade A, and why
execute-parallel scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 499 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spawn N concurrent /ai-sdlc execute sessions in tmux panes (AISDLC-462).
Hard rules
- Hard cap: maximum 5 concurrent sessions. Refuses when already at cap.
- Resource gate: refuses if available memory < 4GB OR 1-min load avg >= ncpu.
- Mutual-awareness: refuses to spawn a task already in
sessions/with status != done|failed. - Operator confirmation: always AskUserQuestion before spawning.
- Never merge PRs. Never force-push to main/master.
Path resolution
PLUGIN_SCRIPTS_DIR="${CLAUDE_PLUGIN_DIR:-${CLAUDE_PLUGIN_ROOT:-$(pwd)/ai-sdlc-plugin}}/scripts"
if [ -z "${PIPELINE_CLI_BIN:-}" ]; then
PIPELINE_CLI_BIN=$(bash "$PLUGIN_SCRIPTS_DIR/resolve-pipeline-cli.sh") || exit 1
fi
Step 1 — Parse arguments
ARG="${ARGUMENTS:-}"
REQUESTED_COUNT=4
EXPLICIT_TASKS=""
# ─── Task ID validation gate (SECURITY) ──────────────────────────────────────
# ALL task IDs from ALL input pathways (--tasks arg, frontier JSON, operator
# confirmation) MUST pass through this function before being interpolated into
# tmux commands, file paths, or branch names. Reject with a clear error if any
# ID fails — this is the primary defense against command injection.
validate_task_id() {
local id="$1"
if ! printf '%s' "$id" | grep -qE '^[A-Z][A-Z0-9]+-[0-9]+(\.[0-9]+)*$'; then
echo "ERROR: invalid task ID '$id' — must match ^[A-Z][A-Z0-9]+-[0-9]+(\.[0-9]+)*$" >&2
return 1
fi
return 0
}
# Parse --count N
if printf '%s' "$ARG" | grep -q '\-\-count'; then
REQUESTED_COUNT=$(printf '%s' "$ARG" | sed -E 's/.*--count[= ]([0-9]+).*/\1/')
fi
# Clamp to max 5
if [ "$REQUESTED_COUNT" -gt 5 ]; then
echo "WARNING: --count $REQUESTED_COUNT exceeds hard cap of 5. Clamping to 5." >&2
REQUESTED_COUNT=5
fi
# Parse --tasks AISDLC-N,...
if printf '%s' "$ARG" | grep -q '\-\-tasks'; then
EXPLICIT_TASKS=$(printf '%s' "$ARG" | sed -E 's/.*--tasks[= ]([A-Z0-9,-]+).*/\1/')
fi
Step 2 — Resource gate
RESOURCE_GATE_SCRIPT="$PLUGIN_SCRIPTS_DIR/check-resource-gate.sh"
if [ -f "$RESOURCE_GATE_SCRIPT" ]; then
bash "$RESOURCE_GATE_SCRIPT" || {
echo "ERROR: resource gate refused — see stderr above." >&2
echo "Set AI_SDLC_EXECUTE_PARALLEL_SKIP_RESOURCE_GATE=1 to override." >&2
exit 1
}
else
echo "WARNING: check-resource-gate.sh not found at $RESOURCE_GATE_SCRIPT; skipping resource check." >&2
fi
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 499 lines · 88 tokens per session scan A b96c695f47a7
execute-parallel is a command published in the GitHub repository ai-sdlc-framework/ai-sdlc (92 stars, last pushed 9d ago), licensed Apache-2.0. It adds 88 tokens to every session and 5,525 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
loop
Design and run a bounded engineering loop with durable state, human approval, and independent verification.
evolve
Run an optional AHE iteration to evaluate or improve this OpenCode harness with evidence and attribution.
loop-status
Consulta el estado durable de una misión sin adquirir locks ni escribir archivos.
app-init
Execute the canonical workflow: .agent/workflows/app-init.md.
ask-openrouter
Execute the canonical workflow: .agent/workflows/ask-openrouter.md.
init
Install the dxkit agent DX layer in a repository: AGENTS.md + CLAUDE.md shim + .claude/skills/dxkit-/ (the lifecycle skills).