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.
git clone --depth 1 https://github.com/itlackey/akmWrote 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/itlackey/akm/start-topic-swarm-deep-research)<a href="https://agentmods.dev/commands/itlackey/akm/start-topic-swarm-deep-research"><img src="https://agentmods.dev/badge/commands/itlackey/akm/start-topic-swarm-deep-research/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/itlackey/akm/start-topic-swarm-deep-research"><img src="https://agentmods.dev/badge/commands/itlackey/akm/start-topic-swarm-deep-research.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00020 | $0.00401 |
| Opus 5 | $0.00010 | $0.00200 |
| Sonnet 5 | $0.00004 | $0.00080 |
| Haiku 4.5 | $0.00002 | $0.00040 |
Grade A, and why
start-topic-swarm-deep-research 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 9d 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
Start Topic Swarm Deep Research
Start the combined swarm-plus-deep-research workflow for this goal:
$ARGUMENTS
Use this procedure:
- Ensure the workflow asset exists in the stash. If
workflows/research/topic-swarm-select-and-deep-researchdoes not exist yet, create it fromscripts/akm-eval/example-stash/workflows/topic-swarm-select-and-deep-research.md:
akm workflow create research/topic-swarm-select-and-deep-research --from scripts/akm-eval/example-stash/workflows/topic-swarm-select-and-deep-research.md
- Run the workflow with exact declared parameter flags. Fill in unknowns conservatively instead of inventing specifics:
akm workflow run workflows/research/topic-swarm-select-and-deep-research \
--goal "$ARGUMENTS" \
--audience "Specify the intended reader and decision-maker" \
--scope "Specify boundaries, exclusions, geography, time horizon, and quality bar" \
--workspace_dir ".akm-run/topic-swarm-deep-research" \
--deliverable_path ".akm-run/topic-swarm-deep-research/report.md" \
--wiki_name research \
--max_swarm_topics 12 \
--max_topic_depth 3 \
--max_topic_branches 5 \
--max_iterations 8 \
--min_primary_sources 5 \
--trusted_domains '[]' \
--seed_urls '[]'
- Record the returned run id and terminal result. If the goal is already
narrow and topic selection is unnecessary, prefer the standalone workflow in
scripts/akm-eval/example-stash/workflows/deep-research-auto-research.mdinstead.
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.
- 9d ago First seen · 42 lines · 20 tokens per session scan A e364e52d8b00
start-topic-swarm-deep-research is a command published in the GitHub repository itlackey/akm (58 stars, last pushed 4d ago), licensed MPL-2.0. It adds 20 tokens to every session and 401 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 2026-08-30.
Other commands, from other repositories
ai-do
You are a routing assistant for DSPy AI skills. Understand the user's problem, pick the best skill, and generate a ready-to-run prompt.
cohort
Command "cohort" from Dragoon0x/product-skills, covering /cohort, usage and related skills.
align
Align cross-functional stakeholders.
brief
Write a design or engineering brief.
present
Prepare a product presentation.
convert
Command "convert" from Dragoon0x/product-skills, covering /convert, usage and related skills.