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/watchgit 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 | $0.00029 | $0.00462 |
| Opus 5 | $0.00015 | $0.00231 |
| Sonnet 5 | $0.00006 | $0.00092 |
| Haiku 4.5 | $0.00003 | $0.00046 |
Grade A, and why
watch 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
Watch cli-dispatch session: $ARGUMENTS
Show the compact status of the given session. Cost-conscious rule: only the small
status.json (+ the last ~15 lines of progress.log) is read — the raw transcript.jsonl
is NEVER read, and it is not tailed repeatedly in a tight loop. When monitoring a background
run, call this ONCE per orchestration step.
SID="$ARGUMENTS"
if [ -z "$SID" ]; then
echo "usage: /cli-dispatch:watch <session-id>"
echo "tip: /cli-dispatch:sessions to list session ids"
exit 1
fi
ROOT="${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: $SID (use /cli-dispatch:sessions to list them)"
else
echo "=== status.json ==="
cat "$DIR/status.json"
echo ""
echo "=== progress.log (last 15 lines) ==="
tail -n 15 "$DIR/progress.log" 2>/dev/null || echo "(no progress)"
fi
state: runningmeans the task is ongoing → check again later (not continuously).state: done→ look atfinalResultPreview; the full output is intranscript.jsonl(if needed).- Continue the session:
/cli-dispatch:resume <id> <follow-up>(auto-detects backend).
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 · 37 lines · 29 tokens per session scan A 90b8f8b10095
watch is a command published in the GitHub repository rbinar/cli-dispatch (5 stars, last pushed 14d ago), licensed MIT. It adds 29 tokens to every session and 462 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
rebase
Rebase current branch onto trunk (origin/master or origin/main), predict and resolve conflicts.
execute
Enter EXECUTE mode to implement approved plan.
innovate
Enter INNOVATE mode for brainstorming approaches.
research
Enter RESEARCH mode for information gathering.
verify
Adversarial spec-vs-implementation verification for a completed task. Dispatches the spec-mentor subagent with fresh context (no anchoring bias), parses its verdict (PASS / DRIFT / NEEDS-MARTY), and updates the verification queue. The v7.4.0 architectural replacement for a dedicated "mentor session.".
criar-skill
Use when creating new skills, automations, or specialized knowledge packages. Keywords: criar skill, nova skill, automatizar, conhecimento, TDD skill.