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 skills add desplega-ai/agent-swarm --skill swarm-scriptsgit clone --depth 1 https://github.com/desplega-ai/agent-swarmWrote 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/skills/desplega-ai/agent-swarm/swarm-scripts)<a href="https://agentmods.dev/skills/desplega-ai/agent-swarm/swarm-scripts"><img src="https://agentmods.dev/badge/skills/desplega-ai/agent-swarm/swarm-scripts.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00082 | $0.02775 |
| Opus 5 | $0.00041 | $0.01388 |
| Sonnet 5 | $0.00016 | $0.00555 |
| Haiku 4.5 | $0.00008 | $0.00278 |
Grade A, and why
swarm-scripts 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.
How it starts
The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Swarm Scripts
A swarm script is TypeScript that runs out of process with a typed Swarm SDK. Only its return value enters your context. Use one when direct tool calls would repeat, flood your context, or need deterministic processing over many records.
When to script
| Situation | Approach |
|---|---|
| 1 to 9 SDK calls, result fits in context | Direct tool calls. |
| 10 or more similar calls, bulk or fan-out | Script. Inline script-run for a one-off, a named script for reuse. |
| Fetch, parse, and transform heavy data | Script, or ctx_* (context-mode) when your harness has it. |
| One large web fetch | ctx_fetch_and_index (context-mode). |
| Multi-agent fan-out, parallel work, deterministic pipeline | Workflow. See workflow-iterate. |
| Work that repeats on a clock | Schedule. See scheduling. |
Named script only when the logic will run two or more times, by you, another agent, a schedule, or a workflow. A one-off goes inline, so the catalog does not fill with scratch saves.
Reference point: a workflow triage that took about 26 tool calls returns as one result of about 4k tokens in about 13 seconds.
Loading the tools
The script tools are deferred. Load them with your harness tool search before the first call: script-search, script-run, script-upsert, script-query-types, script-delete, and for durable runs launch-script-run, get-script-run, list-script-runs.
Run script-query-types before non-trivial work. It returns the live swarm-sdk.d.ts and stdlib declarations, including generated per-app types.
Seed catalog
The swarm ships named scripts at global scope. Each one replaces a multi-step tool chain. script-search with a plain-language description finds them. Call one with script-run and name plus args.
| Script | Args | Use |
|---|---|---|
task-context-gathering |
{ taskId, queries: [...] } |
the task plus a deduplicated multi-query memory recall |
smart-recall |
{ queries: [...] } |
multi-query memory recall without the task |
memory-dedup-check |
{ text, threshold? } |
near-duplicates before you store a memory |
delegate |
{ agentName, task, parentTaskId? } |
a subtask for an agent by name, returns { taskId } |
wait-for-task |
{ taskId } |
waits up to about 25 s for a terminal state, returns { done, status, output }; call again while done is false |
get-child-outputs |
{ parentTaskId } |
every child with status and output |
complete-task |
{ taskId, output } |
finish a task from inside a script |
report-progress |
{ taskId, note } |
a progress note from inside a script |
swarm-overview |
{} |
agents and task counts |
Heartbeat Audit, boot-triage |
see heartbeat-runbook |
the lead's heartbeat data gathering |
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 Changed · +4 lines 4793387927f2
- 8d ago First seen · 154 lines · 82 tokens per session scan A 3919515ee1f5
swarm-scripts is a skill published in the GitHub repository desplega-ai/agent-swarm (749 stars, last pushed today), licensed MIT. It adds 82 tokens to every session and 2,775 once invoked, about $0.0004 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 skills, from other repositories
vector-db-init
Interactively initializes the Vector DB plugin. Guided discovery asks which folders to index, confirms the manifest, then scaffolds vectorprofiles.json for high-performance In-Process or Native Server connections. Mandatory first step before ingestion or search.
update-cli-models
Updates model catalogs and cheapest-model references for all CLI backends (copilot, agy, claude, codex, llama). Researches current model IDs and pricing from official sources, updates the per-CLI JSON files, refreshes cheapestmodels.json/md if the cheapest pick changed, then propagates all copies via…
local-llm-bridge
Local Gemma 4 12B sub-agent. Routes bounded tasks directly to the optimized llama-server at localhost:8089 — no routing proxy, no cloud API, 2–5s typical response. Use for fast, private, cost-free subtask delegation from any cloud primary agent. Part of the runagent.py multi-LLM task router — cli=llama target.
vector-db-launch
Start the Native Python ChromaDB background server. Use when semantic search returns connection refused on port 8110, or when the user wants to enable concurrent agent read/writes.
local-llm-setup
Cross-platform setup wizard for the local Gemma 4 12B inference stack. Automates llama-server installation (binary download or Metal/CUDA/Vulkan/ROCm compile), model download, routing proxy daemon install (launchd/systemd/NSSM), and Mode A/B validation. Covers Day 1 bootstrap and Day 2+ reconfiguration.
vector-db-cleanup
Removes stale and orphaned chunks from the ChromaDB vector store for files that have been deleted or renamed. Use after files are removed or moved to keep the vector index in sync with the filesystem. user: "Clean up the vector store after I deleted some files" assistant: "I'll use vector-db-cleanup to remove orphaned…