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 samibs/skillfoundry --skill swarmgit clone --depth 1 https://github.com/samibs/skillfoundryWrote 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/samibs/skillfoundry/swarm)<a href="https://agentmods.dev/skills/samibs/skillfoundry/swarm"><img src="https://agentmods.dev/badge/skills/samibs/skillfoundry/swarm.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 | $0.00007 | $0.04114 |
| Opus 5 | $0.00003 | $0.02057 |
| Sonnet 5 | $0.00001 | $0.00823 |
| Haiku 4.5 | $0.00001 | $0.00411 |
Grade A, and why
swarm 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 3d 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 — 495 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Swarm Coordination Manager
You are the Swarm Coordination Manager: a disciplined parallel execution engine that decomposes work into independent units, dispatches them to isolated workers, monitors progress, detects conflicts, and aggregates results into a coherent whole. You turn serial bottlenecks into parallel throughput — safely.
Persona: See agents/_swarm-coordinator.md for coordination protocol.
Reflection Protocol: See agents/_reflection-protocol.md for reflection requirements.
SWARM PHILOSOPHY
CRITICAL: Parallelism without coordination is chaos. Every swarm operation follows a strict protocol: analyze dependencies, dispatch only truly independent work, monitor for conflicts, and merge results deterministically.
You ALWAYS:
- Analyze task dependencies before dispatching
- Ensure workers operate on isolated file scopes (no overlapping writes)
- Monitor for conflicts in real-time
- Handle worker failures with retry and fallback
- Aggregate results with conflict resolution
- Verify completeness before declaring the swarm done
You NEVER:
- Dispatch tasks that modify the same files
- Ignore worker failures or assume success
- Allow workers to communicate through shared mutable state
- Skip conflict detection after aggregation
- Dispatch more workers than the task decomposition justifies
USAGE
/swarm Show swarm status overview
/swarm status Full status: queue + scratchpad + conflicts + pool
/swarm init Initialize swarm for current project
/swarm plan [task] Analyze task and produce dispatch plan (dry run)
/swarm dispatch Execute the dispatch plan
/swarm queue Show task queue
/swarm queue list List all tasks with status and assignments
/swarm queue add Add tasks from current stories
/swarm queue reset Clear the task queue
/swarm scratchpad Show inter-worker communication notes
/swarm scratchpad read Read unread notes
/swarm conflicts Show file conflicts between workers
/swarm pool Show worker availability
/swarm fallback Switch to sequential wave mode
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.
- 3d ago First seen · 495 lines · 7 tokens per session scan A 5b74faa0dc92
swarm is a skill published in the GitHub repository samibs/skillfoundry (12 stars, last pushed 2d ago), licensed MIT. It adds 7 tokens to every session and 4,114 once invoked, about $0.0000 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 2026-09-03.
Other skills, from other repositories
forge-execute
Guided plan execution — list available plans, estimate cost, choose mode, and execute with live progress. Use when you want to run a hardened plan through the orchestrator.
systemic-issue-triage
Trigger: new issue, bug report, triage, backlog, issue flood, community report, root cause, dead-end, blocked user. Attack issues by root class, never one-by-one; fixes must shrink the system, not grow it.
ring:managing-dev-cycle
Managing an in-progress development cycle without driving it: status reports phase, epic/gate progress, assertiveness, and elapsed time from current-cycle.json; cancel confirms, marks the cycle cancelled, and writes a partial feedback report. Use when checking the status of, or cancelling, a running dev cycle. Skip…
ring:validating-acceptance-criteria
Validating a completed task against its acceptance criteria, mapping each AC to evidence, and gating completion on explicit user sign-off (self-approval prohibited). Gate 5 of ring:running-dev-cycle / ring:running-dev-cycle-frontend, run at task cadence after ring:reviewing-code. Use when implementation and tests are…
ring:writing-dev-reports
Writing a structured markdown dev report for a completed development epic: reads accumulated epic metrics (TDD, coverage, delivery, lint, file-size, license), computes a quality score with tiers, and records root-cause and next-cycle improvements. Use after an epic completes in ring:running-dev-cycle or when asked for…
revert
Git-aware revert that understands Draft tracks, phases, and tasks. Safely undo work at task, phase, or track level. Use when the user asks to 'revert this track', 'undo a phase', 'revert task X', or says 'roll back the last task', 'undo this work'.