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/rbinar/cli-dispatch/resumegit clone --depth 1 https://github.com/rbinar/cli-dispatchWhat 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 | $0.00019 | $0.00721 |
| Opus 5 | $0.00010 | $0.00360 |
| Sonnet 5 | $0.00004 | $0.00144 |
| Haiku 4.5 | $0.00002 | $0.00072 |
Grade A, and why
resume scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Resume cli-dispatch session
Usage: /cli-dispatch:resume <session-id> <follow-up prompt>
Auto-detects backend (DeepSeek / Antigravity / Codex / OpenCode / Copilot) from the session's status.json.
ARGS="$ARGUMENTS"
SID="${ARGS%% *}"
PROMPT="${ARGS#* }"
if [ -z "$SID" ] || [ "$SID" = "$ARGS" ] || [ -z "$PROMPT" ]; then
echo "usage: /cli-dispatch:resume <session-id> <follow-up prompt>"
echo "tip: /cli-dispatch:sessions to list session ids"
exit 1
fi
ROOT="${CLI_DISPATCH_SESSIONS_DIR:-${CLAUDE_DS_SESSIONS_DIR:-}}"
[ -n "$ROOT" ] || { _c="${XDG_CACHE_HOME:-$HOME/.cache}"; ROOT="$_c/cli-dispatch/sessions"; [ -d "$ROOT" ] || [ ! -d "$_c/claude-ds/sessions" ] || ROOT="$_c/claude-ds/sessions"; }
DIR="$ROOT/$SID"
if [ ! -d "$DIR" ]; then
echo "no such session: $SID (use /cli-dispatch:sessions to list)"
exit 1
fi
BACKEND=$(CLI_DISPATCH_SESSION_DIR="$DIR" node -e "
const fs=require('fs');
const d=process.env.CLI_DISPATCH_SESSION_DIR;
const read=p=>{try{return JSON.parse(fs.readFileSync(p,'utf8'))}catch{return{}}};
const s=read(d+'/status.json'), m=read(d+'/meta.json');
const b=s.backend||m.backend;
if(!b){process.stderr.write('warning: no backend field in session metadata, assuming deepseek\n');}
process.stdout.write(b||'deepseek');
" 2>/dev/null)
echo "session: $SID backend: $BACKEND"
echo "prompt: $PROMPT"
echo ""
case "$BACKEND" in
deepseek|claude-ds|"")
claude-ds-stream --resume "$SID" -p "$PROMPT"
;;
antigravity|agy)
ag-agent --resume "$SID" "$PROMPT"
;;
codex|cx)
cx-agent --resume "$SID" "$PROMPT"
;;
opencode|oc)
oc-agent --resume "$SID" "$PROMPT"
;;
copilot|cp)
cp-agent --resume "$SID" "$PROMPT"
;;
*)
echo "unknown backend '$BACKEND' — run manually:"
echo " deepseek: claude-ds-stream --resume $SID -p \"$PROMPT\""
echo " antigravity: ag-agent --resume $SID \"$PROMPT\""
echo " codex: cx-agent --resume $SID \"$PROMPT\""
echo " opencode: oc-agent --resume $SID \"$PROMPT\""
echo " copilot: cp-agent --resume $SID \"$PROMPT\""
exit 1
;;
esac
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.
- yesterday First seen · 73 lines · 19 tokens per session scan A fb87f92f9c17
resume is a command published in the GitHub repository rbinar/cli-dispatch (5 stars, last pushed 14d ago), licensed MIT. It adds 19 tokens to every session and 721 once invoked, about $0.0001 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 2026-08-31.
Other commands, from other repositories
strict
Enable strict RIPER protocol enforcement.
research
Enter RESEARCH mode for information gathering.
status
Show the current status of the Claude Code Router server.
brainstorm
多模型并行对同一问题各给独立意见(发散式 brainstorming),主 Claude 综合分歧、共识、独到见解。各模型彼此看不到对方答案,避免回声室效应。.
language
Toggle the HUD label language between English and 中文 (edits /.claude/plugins/balance-hud/config.json).
benchmark
Run the Permafrost cache benchmark (offline emulator, no API key).