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-parallel-cleanupgit 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 | $0.00053 | $0.01982 |
| Opus 5 | $0.00026 | $0.00991 |
| Sonnet 5 | $0.00011 | $0.00396 |
| Haiku 4.5 | $0.00005 | $0.00198 |
Grade A, and why
execute-parallel-cleanup scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
const { execFileSync } = require('child_process'); How it starts
The opening of the file, as written. The whole thing — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Kill in-flight /ai-sdlc execute-parallel panes and archive their session files (AISDLC-462).
Hard rules
- AskUserQuestion before kill. Always list what will be killed and ask for confirmation.
- Never merge PRs. Never close PRs or issues.
- If a session is already done/failed, archive it without killing (no tmux window to kill).
Arguments
- No arguments: list and clean up ALL sessions (done, failed, and optionally in-progress).
--all: same as no arguments.AISDLC-N,AISDLC-M,...: target specific task IDs only.
ARG="${ARGUMENTS:-}"
BOARD_DIR=".ai-sdlc/dispatch"
SESSIONS_DIR="$BOARD_DIR/sessions"
ARCHIVE_DIR="$SESSIONS_DIR/archived"
TMUX_SESSION="ai-sdlc-parallel"
# Parse target tasks
EXPLICIT_TASKS=""
if [ -n "$ARG" ] && [ "$ARG" != "--all" ]; then
EXPLICIT_TASKS=$(printf '%s' "$ARG" | tr -d ' ')
fi
if [ ! -d "$SESSIONS_DIR" ]; then
echo "No sessions directory at $SESSIONS_DIR. Nothing to clean up."
exit 0
fi
mkdir -p "$ARCHIVE_DIR"
Step 1 — List sessions to clean up
# Collect candidate session files
CANDIDATES_JSON=$(node -e "
const fs = require('fs');
const path = require('path');
const sessionsDir = process.argv[1];
const explicitTasks = process.argv[2] ? process.argv[2].split(',').map(t => t.trim().toUpperCase()) : [];
const sessions = [];
try {
const files = fs.readdirSync(sessionsDir).filter(f => f.endsWith('.session.json'));
for (const f of files) {
try {
const s = JSON.parse(fs.readFileSync(path.join(sessionsDir, f), 'utf8'));
if (explicitTasks.length === 0 || explicitTasks.includes((s.taskId || '').toUpperCase())) {
sessions.push(s);
}
} catch {}
}
} catch {}
process.stdout.write(JSON.stringify(sessions));
" "$SESSIONS_DIR" "$EXPLICIT_TASKS" 2>/dev/null || echo '[]')
Step 2 — Present the list and ask for confirmation (AskUserQuestion)
List all candidate sessions with their status and ask the operator to confirm before killing any in-progress sessions.
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.
- 3d ago First seen · 202 lines · 53 tokens per session scan A 12f9cfbb66ac
execute-parallel-cleanup 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 53 tokens to every session and 1,982 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
help
Execute the canonical workflow: .agent/workflows/help.md.
session
Complete reference for all session-related commands — start, end, list, and compact.
README
Command "README" from s977043/PlanGate, covering カスタムスラッシュコマンド一覧, コマンド, 使い方, 作業コンテキストの新規作成・読み込み and 作業コンテキストの保存(セッション終了時).
session-memory
Maintain context and learnings across Claude Code sessions for continuous improvement.
smart-agents
Automatically spawn the right agents at the right time without manual intervention.
ovd-log
ovd-log — lightweight save (default) or full handoff at session end.