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 RudyCity/superagent --skill preventing-subagent-collisionsgit clone --depth 1 https://github.com/RudyCity/superagentWrote 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/rudycity/superagent/preventing-subagent-collisions)<a href="https://agentmods.dev/skills/rudycity/superagent/preventing-subagent-collisions"><img src="https://agentmods.dev/badge/skills/rudycity/superagent/preventing-subagent-collisions/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/skills/rudycity/superagent/preventing-subagent-collisions"><img src="https://agentmods.dev/badge/skills/rudycity/superagent/preventing-subagent-collisions.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00060 | $0.02157 |
| Opus 5 | $0.00030 | $0.01078 |
| Sonnet 5 | $0.00012 | $0.00431 |
| Haiku 4.5 | $0.00006 | $0.00216 |
Grade A, and why
Preventing Subagent Collisions 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 7d 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 — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Preventing Subagent Collisions
Overview
Two separate collision scenarios exist in the 3-tier architecture. Both must be handled:
| Scenario | Tier | Risk |
|---|---|---|
| A — Subagent collision | Superagent → Subagents | Two subagents claim same task or edit same file within one worktree |
| B — Worktree collision | Master Agent → Superagents | Two Superagents in different worktrees both edit shared files (package.json, CHANGELOG.md, AGENTS.md), causing merge conflicts |
Core principle (both scenarios): The parent pre-assigns tasks AND file scopes before spawning. Shared files are never touched in parallel — always serialized.
Scenario A — Subagent Collision (Superagent tier)
The Coordination Model
| File | Purpose | Owner |
|---|---|---|
_implementation_plan.md |
All tasks, file scopes, agent assignments | Parent (via manage_plan) |
_task.md |
Active task checklist — status per task | Parent updates; subagents read only |
_task_history.md |
Archive of completed tasks | Automatic |
Subagents do NOT call manage_plan or modify _task.md. They receive a pre-assigned task in their prompt and report back when done. Parent updates status via manage_tasks.
Plan Template with Agent Assignments
# Feature X Implementation Plan
## Proposed Changes
- [ ] [agent: researcher] Research existing auth patterns — src/auth/**
- [ ] [agent: coder-a] Implement JWT middleware — src/auth/jwt.ts, src/auth/middleware.ts
- [ ] [agent: coder-b] Implement billing service — src/billing/**, tests/unit/billing/**
- [ ] [agent: reviewer] Review and test all changes — tests/**, docs/**
## Shared Files (Read-Only for Parallel Agents)
- src/types/index.ts
- src/config/constants.ts
- package.json
If an agent needs to modify a shared file: STOP and report to parent.
## Verification Plan
### Automated Tests
`bun test`
### Manual Verification
Verify no conflicts in git log.
Spawn with fileScope
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.
- 7d ago First seen · 235 lines · 60 tokens per session scan A 653b5dbc86f5
Preventing Subagent Collisions is a skill published in the GitHub repository RudyCity/superagent (21 stars, last pushed 2d ago), licensed MIT. It adds 60 tokens to every session and 2,157 once invoked, about $0.0003 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
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.