Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
Wrote 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/xg-gh-25/swarmai/s_project-manager)<a href="https://agentmods.dev/skills/xg-gh-25/swarmai/s_project-manager"><img src="https://agentmods.dev/badge/skills/xg-gh-25/swarmai/s_project-manager/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/xg-gh-25/swarmai/s_project-manager"><img src="https://agentmods.dev/badge/skills/xg-gh-25/swarmai/s_project-manager.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00101 | $0.09714 |
| Opus 5 | $0.00051 | $0.04857 |
| Sonnet 5 | $0.00020 | $0.01943 |
| Haiku 4.5 | $0.00010 | $0.00971 |
Grade D, and why
project-manager scanned grade D with 2 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 11d 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.
Subtle steeringmediumPrompt injection
Instructions that bias recommendations or shape behaviour without the user noticing.
- **No index refresh** — the in-prompt PROJECTS.md index was removed 2026-08-14; a project is discoverable the moment its `Projects/<name>/` dir exists (recall + Glob). Nothing to refresh; never tell the user to "wait fo Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
mv "Projects/ProjectName" ~/.Trash/ 2>/dev/null || rm -rf "Projects/ProjectName" How it starts
The opening of the file, as written. The whole thing — 696 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Manager
Manage projects in the SwarmWS workspace. Each project uses DDD (Domain-Driven Design) structure with 4 knowledge documents that give Swarm deep understanding of the project's domain.
These 4 docs are section ② KNOWLEDGE of the canonical six-section DDD structure (DDD_SPEC_VERSION 1.0) — see "The Canonical DDD Structure" below. CREATE scaffolds the ①②③④⑥ SKELETON (dirs + manifests + purpose-READMEs); their content accretes as the project grows; only ⑤
bindings.yamlwaits for BIND.
DDD Structure
Every project gets these files (templates with instructions for the user):
| File | Domain | Purpose |
|---|---|---|
| PRODUCT.md | Strategic alignment | Vision, priorities, success criteria, non-goals |
| TECH.md | Technical context | Architecture, stack, codebase location, dev commands, conventions |
| IMPROVEMENT.md | Historical patterns | What worked, what failed, known issues, security history |
| PROJECT.md | Current context | Current focus, open items, recent decisions, blockers |
| .artifacts/ | Pipeline outputs | Research, design docs, changesets, reviews, test reports |
The SwarmAI project is the default project that ships with every installation. It cannot be deleted but can be freely edited. It serves as a working example of the DDD structure.
The Canonical DDD Structure — six sections (DDD-agent-brain spec §3.6)
DDD_SPEC_VERSION: 1.0— this skill provisions DDDs conforming to spec version 1.0 (the six-section canonical structure). Because a DDD can carrys_ddd-managerto create MORE DDDs (self-propagation), the structure is a VERSIONED spec: declaring the version here is what keeps propagated DDDs from drifting. Source of truth:Projects/AIDLC/Knowledge/Designs/2026-07-11-ddd-agent-brain-paradigm-design.md§3.6.
A DDD is a product's domain BRAIN = its control plane. It OWNs cognitive assets (holds them, is their source of truth) and GOVERNs physical assets (points at + controls them via data/pointers — never contains code, never runs a pipeline: 指+治, 不含+不跑). The 4 knowledge documents above are section ② KNOWLEDGE — ONE of the six sections, not a competing structure. The full canonical shape:
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.
- 11d ago First seen · 696 lines · 101 tokens per session scan D 4cc9d928221f
project-manager is a skill published in the GitHub repository xg-gh-25/SwarmAI (44 stars, last pushed 4d ago), licensed MIT. It adds 101 tokens to every session and 9,714 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it D with 2 findings (subtle steering, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
digest
NOTE: this skill requires connected chat / email / project-tracker / docs MCPs, which are typically only present in Cowork — the Code variant exists for parity but most users will want the Cowork variant. Cross-tool rollup of what's pending, what shipped, and what's blocked across chat / email / project tracker /…
roadmap
Render a per-project feature roadmap — a Band×Status grid (Shipped/Current/Next/Later × done/in-progress/blocked/buildable) synthesized from CLAUDE.md + PROGRESS.md, persisted to a committed ROADMAP.md with staleness-aware refresh. Modes: '/roadmap' (nearest project), '/roadmap ' (a projectslist tag), '/roadmap…
stitch
Build or verify cross-repo STITCH.md linking backend + frontends in a product group. Modes: create, verify, diff, section. Uses CODEMAPs as drift source by default. Trigger: '/stitch create ', '/stitch diff '.
aria-assist
Morning product-management review across all your projects. Use when the user runs /aria-assist, asks for a morning review / daily PM digest / "what should I do today across my products", or when the launchd job fires it headless. Two modes - generate (headless: read facts, deep-review ACTIVE projects, apply logged…
backlog
View and manage pending backlog items. Use when user says '/backlog', '/backlog insights', '/backlog clear', 'what's pending', 'show backlogs', 'check backlog status'. (Code port — ADR-094.).
parallel-feature-development
Coordinate parallel feature development with file ownership strategies, conflict avoidance rules, and integration patterns for multi-agent implementation. Use this skill when decomposing a large feature into independent work streams, when two or more agents need to implement different layers of the same system…