Not in the top 1,000 by GitHub stars
amanning3390/deepswarm
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 614d635bc06f
No earlier version was observed for comparison.
122GitHub stars
0stars in 7 days
1skill in this repository
0commits in 30 days
Heat
0.4- Star growth, last 7 daysNot available
- Star growth, last 24 hoursNot available
- Rank movement, last 7 daysNot available
- Commits, last 30 daysNot available
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekNot available
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
30-day change not yet available: not enough history.
Individual skills in this repository
How it works
deepswarm
When your agent uses it
Use when running parallel AI workers for any long-running or multi-turn batch API task. Auto-calculates optimal workers + stagger. Supports tiered delegation (V4 Pro orchestrator → V4 Flash workers). 99.95% API success rate at scale.
What it loads into context
Frontmatter
131 tokensAlways available to the agent
SKILL.md
1,870 tokensWhen the skill is activated
Reference documents
2,012 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- When to Use
- Quick Start
- Task Definition (task.yaml)
- Tiered Model Delegation
- Auto-Optimization
- Multi-Turn Task Support
- Task-Agnostic Worker Design
- Common Pitfalls
- Verification Checklist
Scripts executed separately
scripts/filter.pyscripts/seed.pyscripts/swarm.pyscripts/worker.pytemplates/prompts.py
Files
PLAN.mddoc2,556 bytesREADME.mddoc2,946 bytesSKILL.mdcore7,813 bytesSKILL.mdcore7,813 bytesSKILL.mdcore7,813 bytesarchitecture.htmlasset23,636 bytesreferences/api-rate-limits.mddoc1,076 bytesreferences/generation-patterns.mddoc757 bytesscripts/filter.pyruns10,132 bytesscripts/seed.pyruns4,846 bytesscripts/swarm.pyruns6,161 bytesscripts/worker.pyruns6,106 bytestask.yamlasset1,098 bytestemplates/prompts.pyruns12,384 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubSkills included
- deepswarm
Repository facts
- License
- No license detected
- Created
- May 4, 2026
- Last pushed
- May 5, 2026
- Forks
- 5
- Open issues
- 1
- Project activity
- Slowing
Before you install
Network or broad shellAutomated signals, not a guarantee
Checked Nov 5, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 2 notes
SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- No dangerous shell commands
- 20 network referencesin 7 files: scripts/swarm.py:39 SKILL.md:62 architecture.html:5 and 4 more
- No hidden or obfuscated text
- No instruction overrides
- 5 executable scriptsin 5 files: scripts/filter.py:1 scripts/seed.py:1 scripts/swarm.py:1 and 2 more
- 14 references to secretsin 4 files: scripts/swarm.py:32 scripts/worker.py:12 README.md:22 and 1 more
- No requests to vote in Hot
Show all 39 signals by file
README.md
SKILL.md
- Network accessline 62
orchestrator_model: deepseek-v4-pro # Plans, monitors, handles errors worker_model: deepseek-v4-flash # Executes batches (cheaper!) worker_api_base: https://api.deepseek.com/v1/chat/completions - Network accessline 63
worker_model: deepseek-v4-flash # Executes batches (cheaper!) worker_api_base: https://api.deepseek.com/v1/chat/completions worker_max_tokens: 4096 - Network accessline 64
worker_api_base: https://api.deepseek.com/v1/chat/completions
architecture.html
- Network accessline 5
<meta name="viewport" content="width=device-width, initial-scale=1.0"> <title>DeepSwarm 2.0 Architecture</title> <link href="https://fonts.googleapis.com/css2?family=JetBrains+Mono:wght@400;500;600;700&display=swap" rel="stylesheet"> - Network accessline 6
<title>DeepSwarm 2.0 Architecture</title> <link href="https://fonts.googleapis.com/css2?family=JetBrains+Mono:wght@400;500;600;700&display=swap" rel="stylesheet"> <style> - Network accessline 7
<link href="https://fonts.googleapis.com/css2?family=JetBrains+Mono:wght@400;500;600;700&display=swap" rel="stylesheet">
scripts/filter.py
- Executable scriptline 1
#!/usr/bin/env python3
scripts/seed.py
- Executable scriptline 1
#!/usr/bin/env python3
scripts/swarm.py
- Executable scriptline 1
#!/usr/bin/env python3 - Access to secretsline 32
[Credential-related source omitted] - Access to secretsline 33
[Credential-related source omitted] - Access to secretsline 34
[Credential-related source omitted] - Access to secretsline 35
[Credential-related source omitted] - Access to secretsline 36
[Credential-related source omitted] - Network accessline 39
model = task.get("worker_model", "deepseek-v4-flash") base = task.get("worker_api_base", "https://api.deepseek.com/v1/chat/completions") - Network accessline 40
base = task.get("worker_api_base", "https://api.deepseek.com/v1/chat/completions") - Network accessline 43
try: r = requests.post(base, - Network accessline 44
r = requests.post(base, - Access to secretsline 45
[Credential-related source omitted]
scripts/worker.py
- Executable scriptline 1
#!/usr/bin/env python3 - Access to secretsline 12
[Credential-related source omitted] - Access to secretsline 13
[Credential-related source omitted] - Access to secretsline 15
[Credential-related source omitted] - Access to secretsline 18
[Credential-related source omitted] - Network accessline 25
model = config.get("worker_model", config.get("model", "deepseek-v4-flash")) base = config.get("worker_api_base", config.get("api_base", "https://api.deepseek.com/v1/chat/completions")) - Network accessline 26
base = config.get("worker_api_base", config.get("api_base", "https://api.deepseek.com/v1/chat/completions")) - Access to secretsline 28
[Credential-related source omitted] - Network accessline 30
resp = requests.post(base, - Access to secretsline 31
[Credential-related source omitted]
task.yaml
- Network accessline 17
[Credential-related source omitted] - Access to secretsline 17
[Credential-related source omitted] - Network accessline 18
worker_model: deepseek-v4-flash # Executes batches (cheaper!) worker_api_base: https://api.deepseek.com/v1/chat/completions worker_max_tokens: 4096 - Network accessline 19
worker_api_base: https://api.deepseek.com/v1/chat/completions
templates/prompts.py
- Executable scriptline 1
Executable file - Network accessline 114
"change": ["error handling with retry logic", "timeout configuration for external calls", "structured logging with correlation IDs"], "pattern": ["error handling: wrap external calls with retry and circuit breaker", "API versioning: use - Network accessline 115
"pattern": ["error handling: wrap external calls with retry and circuit breaker", "API versioning: use /v1/ prefix with deprecation headers"], "url": ["https://api.example.com/v1/users", "https://api.example.com/health"], "time": [" - Network accessline 116
"url": ["https://api.example.com/v1/users", "https://api.example.com/health"],
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
Signal confidence: 32 facts
- Access to secrets in code of documentationREADME.md:22Low confidence
- Network access in prose of documentationREADME.md:89Low confidence
- Network access in code of the SKILL.mdSKILL.md:62High confidence
- Network access in code of the SKILL.mdSKILL.md:63High confidence
- Network access in code of the SKILL.mdSKILL.md:64High confidence
- Executable script in code of a file that runsscripts/filter.py:1High confidence
- Executable script in code of a file that runsscripts/seed.py:1High confidence
- Executable script in code of a file that runsscripts/swarm.py:1High confidence
- Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuescripts/swarm.py:32Low confidence
- Access to secrets in code of a file that runsscripts/swarm.py:33High confidence
- Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuescripts/swarm.py:34Low confidence
- Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuescripts/swarm.py:35Low confidence
- Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuescripts/swarm.py:36Low confidence
- Network access in code of a file that runsscripts/swarm.py:39High confidence
- Network access in code of a file that runsscripts/swarm.py:40High confidence
- Network access in code of a file that runsscripts/swarm.py:43High confidence
- Network access in code of a file that runsscripts/swarm.py:44High confidence
- Access to secrets in code of a file that runsscripts/swarm.py:45High confidence
- Executable script in code of a file that runsscripts/worker.py:1High confidence
- Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuescripts/worker.py:12Low confidence
- Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuescripts/worker.py:13Low confidence
- Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuescripts/worker.py:15Low confidence
- Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuescripts/worker.py:18Low confidence
- Network access in code of a file that runsscripts/worker.py:25High confidence
- Network access in code of a file that runsscripts/worker.py:26High confidence
- Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuescripts/worker.py:28Low confidence
- Network access in code of a file that runsscripts/worker.py:30High confidence
- Access to secrets in code of a file that runsscripts/worker.py:31High confidence
- Executable script in prose of a file that runstemplates/prompts.py:1Low confidence
- Network access in code of a file that runstemplates/prompts.py:114High confidence
- Network access in code of a file that runstemplates/prompts.py:115High confidence
- Network access in code of a file that runstemplates/prompts.py:116High confidence
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Compatible | Standard SKILL.md SKILL.md | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.
