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-nextgit 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-next)<a href="https://agentmods.dev/commands/pounceai/bob-control/bob-next"><img src="https://agentmods.dev/badge/commands/pounceai/bob-control/bob-next.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 5.1 | $0.00015 | $0.00366 |
| Opus 5 | $0.00008 | $0.00183 |
| Sonnet 5 | $0.00003 | $0.00073 |
| Haiku 4.5 | $0.00002 | $0.00037 |
Grade A, and why
bob-next scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Show what Bob will pull next — without claiming it (you are the foreman, not the
worker; do not set claim).
Call get_next_task with claim: false (and tag: "$ARGUMENTS" only if a tag was
given above). If it returns null, say the queue is empty — or, if it reports
board: "disarmed", that dispatch is paused (arm the board to pull) — and stop.
Otherwise call predict_mode { id: <that task's id> } (it routes via the connector's own router
in modes.ts, so this never re-encodes the keyword table) and report:
- the task:
#id· priority · title, plus its description and tags; - the mode it will dispatch in and the source (
explicit/tag/auto-router/default); - the risk of that mode (
safe/standard/elevated). The worker auto-dispatches only at/below its--max-risk(defaultstandard), so anadvanced(elevated) task waits for manual dispatch.
State the mode, the source, and a one-line "why" (for an explicit/tag source, name the mode or tag
that pinned it; for auto-router, the wording that matched). Do not change the task.
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.
- 5d ago First seen · 24 lines · 15 tokens per session scan A 9acc35db4e88
bob-next is a command published in the GitHub repository PounceAI/bob-control (1 stars, last pushed 21d ago), licensed Apache-2.0. It adds 15 tokens to every session and 366 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
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.
app-recover
Recover an interrupted run — reconcile the ledger, the board, the worktrees and the wave, then restart from a known state.
bug
Reproduce then TDD-fix a ready-for-agent bug ticket in this checkout. Web bugs get a browser repro first.
ci
Watch gh pr checks until green and fix failures on this branch. Do not merge.