📦

swarm

Name: swarm
Author: nbashaw

Content revision r2 High Risk 📁 Filesystem access⚙️ External commands

Coordinate Autonomous Coding Agents

Complex coding work can lose context across many implementation and review steps. Swarm coordinates iterative agents through a shared plan, review gates, tests, and completion checks.

Supports: Claude Codex Code(CC)

⚠️ 38 Poor

Stop for confirmation before installing.

Review the plan and obtain explicit user consent before changing files.

Install with my Agent

Copy this request to your Agent. It includes the canonical Skill page and manifest.

Agent request

Review the Skillstore skill "swarm" from https://skillstore.io/skills/nbashaw-swarm.md and its manifest at https://skillstore.io/api/skills/nbashaw-swarm/manifest. Verify the artifact. Stop and obtain explicit user consent before installing or changing files.

Your Agent should still show its plan and request any confirmation required by the security policy.

Agent-readable resources

Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.

Markdown detail GET /skills/nbashaw-swarm.md Signed manifest GET /api/skills/nbashaw-swarm/manifest Signed lockfile GET /api/skills/nbashaw-swarm/lockfile

Test it

Using "swarm". Plan a multi-file authentication refactor with unit and integration tests.

Expected outcome:

A phased plan covering discovery, implementation, migration, tests, and final review.
Named reviewer, simplifier, tester, and gatekeeper checkpoints.
A shared log format and measurable completion criteria.

Using "swarm". Run the approved migration plan in dry-run mode.

Expected outcome:

A preview identifies the selected agent, plan path, iteration limit, completion marker, and command that would launch the workflow.

Using "swarm". Report the completed workflow.

Expected outcome:

The completion report states the iteration count, gatekeeper decision, test status, change summary, and plan log location.

Security Audit

High Risk

v9 • 8/9/2026 Open versioned report

Most static findings are false positives caused by Markdown backticks, shell arithmetic, test commands, and local completion markers. One temporary-file issue is confirmed, and semantic review found a high-risk autonomous execution path that runs agents with reduced or disabled permission controls.

Files scanned

812

Lines analyzed

Review items

False positives ignored

Confirmed security concerns (1)

High

assets/swarm.sh:103-141

Autonomous Agents Run With Reduced Permission Controls

The runner repeatedly launches Codex in full-auto mode or Claude with --dangerously-skip-permissions. Agents can edit files and run repository commands without per-action confirmation, increasing the impact of malicious repository content or flawed plans.

The executable script directly contains both reduced-confirmation command lines inside its autonomous iteration loop. The behavior is also described as intentional in the skill documentation.

Capability review items (1)

These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.

Medium

assets/test_swarm.sh:9

Temp directory access

TEST_PLAN="/tmp/test_plan_$$.md"

The test writes to a predictable /tmp filename based on the process ID. On a shared system, a precreated symlink could redirect the write and clobber another file.

Risk Factors

📁 Filesystem access (8)

assets/PLAN_TEMPLATE.md:85 assets/PLAN_TEMPLATE.md:86 assets/swarm.sh:67 assets/swarm.sh:76 assets/swarm.sh:82 assets/test_swarm.sh:32 assets/test_swarm.sh:128 assets/test_swarm.sh:9

⚙️ External commands (50)

Audited by: codex View Audit History →

Share & cite this report

Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.

Open versioned report

Copy report link

https://skillstore.io/skills/nbashaw-swarm/audits/9?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/nbashaw-swarm/security.svg)](https://skillstore.io/skills/nbashaw-swarm?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/nbashaw-swarm?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/nbashaw-swarm/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/nbashaw-swarm.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>

Academic citations (APA · BibTeX · CFF)

APA citation

nbashaw. (2026). swarm security audit report (audit version 9) [Author version unspecified]. Skillstore. https://skillstore.io/skills/nbashaw-swarm/audits/9

BibTeX citation

@techreport{nbashaw-nbashaw-swarm-2026,
  author = {nbashaw},
  title = {swarm security audit report (audit version 9)},
  institution = {Skillstore},
  year = {2026},
  number = {9},
  url = {https://skillstore.io/skills/nbashaw-swarm/audits/9},
  note = {Author version unspecified}
}

CITATION.cff

cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "swarm security audit report (audit version 9)"
version: "unspecified"
type: report
authors:
  - name: "nbashaw"
date-released: "2026-08-09"
url: "https://skillstore.io/skills/nbashaw-swarm/audits/9"
identifiers:
  - type: other
    value: "skillstore:nbashaw-swarm:audit:9"
    description: "Skillstore immutable audit report identifier"

Skillstore Score

Why this score Evidence Confidence: Medium

Architecture

Maintainability

Content

Community

Spec Compliance

What You Can Build

Refactor a subsystem

Coordinate implementation, simplification, tests, and final verification across several files.

Migrate a codebase

Track a staged framework or API migration with explicit checks after each phase.

Expand test coverage

Plan coverage work, run targeted tests, review gaps, and verify completion evidence.

Try These Prompts

Plan a coding task

Use Swarm to plan [task]. Ask me for the goal, affected files, test commands, and preferred plan location before creating the plan.

Execute an approved plan

Use Swarm to execute [plan file]. Start with a dry run, summarize the command, and wait for my approval before launching agents.

Coordinate a migration

Create a Swarm plan for migrating [system] from [current state] to [target state]. Include rollback points, compatibility tests, and review gates.

Run a constrained autonomous workflow

Plan and execute [goal] within [directories]. Use [test commands], preserve [constraints], stop on unexpected changes, and provide gatekeeper evidence before completion.

Best Practices

Use measurable completion criteria and exact verification commands.
Review the generated plan and dry-run output before starting autonomous execution.
Run the workflow in an isolated worktree or container with limited credentials.

Avoid

Do not use Swarm for typos, single-line fixes, or tasks requiring frequent decisions.
Do not launch agents against an unreviewed plan or untrusted repository instructions.
Do not treat completion markers as proof without checking tests and gatekeeper evidence.