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/dudupii/smart-dispatch/smart-dispatch-reportgit clone --depth 1 https://github.com/dudupii/smart-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 | $0.00020 | $0.00173 |
| Opus 5 | $0.00010 | $0.00086 |
| Sonnet 5 | $0.00004 | $0.00035 |
| Haiku 4.5 | $0.00002 | $0.00017 |
Grade A, and why
smart-dispatch-report 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.
What it actually says
Show the user their smart-dispatch routing stats.
Read the routing log at $SMART_DISPATCH_LOG (default ~/.smart-dispatch/log.jsonl) and summarize it: total decisions, model distribution (haiku / sonnet / opus counts), estimated savings vs an all-opus baseline, and the fraction of Hard-tier tasks downgraded (budget mode).
The bundled report script scripts/report.mjs computes this — run it if you can locate this plugin's directory (try ~/.claude/plugins/), otherwise read the log file directly and compute the same summary with the Bash and Read tools. If the log doesn't exist yet, tell the user it appears once the skill routes its first sub-agent dispatch.
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 · 10 lines · 20 tokens per session scan A adc8b931dc24
smart-dispatch-report is a command published in the GitHub repository dudupii/smart-dispatch (2 stars, last pushed 6d ago), licensed MIT. It adds 20 tokens to every session and 173 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
boss:ship
只跑部署环节：DevOps 构建部署 + 上线前门禁 + 部署报告。对已通过测试的项目单独可用，产出 deploy-report.md，门禁不可绕过。.
tokenless-stats
Show Tokenless compression statistics.
profile
Save, apply, and share multi-agent configuration profiles.
audit-artifacts
List suspicious root agent process files and placement directories.
start
Initialize the productivity system and open the dashboard.
surgical
Enforce strict scope on a task — build only what was explicitly asked, nothing more.