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/pounceai/bob-control/bob-routegit clone --depth 1 https://github.com/PounceAI/bob-controlWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/pounceai/bob-control/bob-route)<a href="https://agentmods.dev/commands/pounceai/bob-control/bob-route"><img src="https://agentmods.dev/badge/commands/pounceai/bob-control/bob-route.svg" alt="Measured on agentmods" height="20"></a>What 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 | $0.00014 | $0.00276 |
| Opus 5 | $0.00007 | $0.00138 |
| Sonnet 5 | $0.00003 | $0.00055 |
| Haiku 4.5 | $0.00001 | $0.00028 |
Grade A, and why
bob-route 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 4d 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
Predict the dispatch mode for: $ARGUMENTS
Call predict_mode — it routes via the connector's own router (modes.ts), so this never re-encodes
the keyword table and can't drift from it:
- If the argument is a number, pass it as
id(routes the real task: its explicitmode› a tag naming a mode › the keyword auto-router ›code). - Otherwise pass the text as
text(routes it as a hypothetical task title/description).
It returns {mode, source, risk}. Report:
- the chosen mode and the source (
explicit/tag/auto-router/default); - the risk (
safe/standard/elevated). The worker auto-dispatches only at/below its--max-risk(defaultstandard), so anadvanced(elevated) task waits for manual dispatch.
If it routed somewhere the user probably didn't intend, suggest clearer wording or an explicit mode
to pin it.
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.
- 4d ago First seen · 24 lines · 14 tokens per session scan A 5508c5aa1fa0
bob-route is a command published in the GitHub repository PounceAI/bob-control (1 stars, last pushed 21d ago), licensed Apache-2.0. It adds 14 tokens to every session and 276 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
bug
Reproduce then TDD-fix a ready-for-agent bug ticket in this checkout. Web bugs get a browser repro first.
app-init
Start a new mobile app project — runs requirements intake, then CEO vision, then PRD + architecture in parallel.
app-learn
Mine a shipped app's conventions into the living House Knowledge Base — adds net-new learnings to knowledge/.md, harvests its failures into knowledge/failure-corpus.md, and flags conflicts for human decision.
app-status
Show the current state of the project — vision, sprint goal, board, blockers, daily report.
ci
Watch gh pr checks until green and fix failures on this branch. Do not merge.
review
Harsh maintainability review of one PR. Comments, not patches. Do not merge.