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-triagegit 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-triage)<a href="https://agentmods.dev/commands/pounceai/bob-control/bob-triage"><img src="https://agentmods.dev/badge/commands/pounceai/bob-control/bob-triage.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 | $0.00013 | $0.00503 |
| Opus 5 | $0.00006 | $0.00251 |
| Sonnet 5 | $0.00003 | $0.00101 |
| Haiku 4.5 | $0.00001 | $0.00050 |
Grade A, and why
bob-triage 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
Act as the foreman doing a board review. Optional focus: $ARGUMENTS.
- Read the board. Call
list_tasks(no filter, or narrowed to the focus above). For anything ambiguous,get_taskto read its notes. - Diagnose. Flag:
- blocked tasks — what's the blocker, can it be unblocked or should it be cancelled?
- in_progress tasks that look abandoned (claimed long ago, no recent notes).
- pending tasks that are unclear: no description, missing acceptance criteria, or no obvious mode/tags.
- priority inversions — low-priority noise ahead of real work, or urgent work buried.
- duplicates / overlap between tasks.
- Propose a plan as a short numbered list, each item:
#id → action (why). - Apply after the user confirms — all via tools, no shell needed:
- re-open / block / cancel / mark done →
update_task_status - leave a triage rationale on a task →
add_task_note - set or clear a task's mode →
set_task_mode(pass''to clear and let it auto-route) - remove a duplicate / mistake →
delete_task(preferupdate_task_status→cancelledwhen you want to keep a record) - change priority or tags (no in-place edit exists):
delete_task, thencreate_taskwith the corrected priority/tags — carry over the title and description verbatim, and only do this forpendingtasks (never re-create one that's mid-flight).
- re-open / block / cancel / mark done →
Be conservative: never cancel or close a task without the user's say-so. Default to a note + recommendation when unsure.
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 · 30 lines · 13 tokens per session scan A 14a1151576f0
bob-triage is a command published in the GitHub repository PounceAI/bob-control (1 stars, last pushed 22d ago), licensed Apache-2.0. It adds 13 tokens to every session and 503 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.
review
Harsh maintainability review of one PR. Comments, not patches. Do not merge.
ci
Watch gh pr checks until green and fix failures on this branch. Do not merge.
decree
Issue a decree. Seats the organization on first use, then dispatches the teams.
harness-sync
Detect drift across all push-direction control surfaces, present the full picture, and apply the user's selected fixes via the existing primitives — single human-instigated entry point for keeping convention files in sync with HARNESS.md. ONBOARDING.md staleness is surfaced but not auto-fixed; users run…
assess
Run an AI literacy assessment — scan the repo for evidence, ask clarifying questions, produce a timestamped assessment document, apply immediate habitat fixes, recommend workflow changes, capture a reflection, and add a literacy level badge to the README.