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 xg-gh-25/SwarmAI --skill s_ddd-managergit clone --depth 1 https://github.com/xg-gh-25/SwarmAIWrote 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_ddd-manager)<a href="https://agentmods.dev/skills/xg-gh-25/swarmai/s_ddd-manager"><img src="https://agentmods.dev/badge/skills/xg-gh-25/swarmai/s_ddd-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_ddd-manager"><img src="https://agentmods.dev/badge/skills/xg-gh-25/swarmai/s_ddd-manager.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Data Exfiltration · line 40 Code or instructions that leak agent conversation context to external services, potentially exposing sensitive user interactions.Fix: Remove any code that sends prompts, responses, or session data externally. Preserve user privacy; never exfiltrate conversation content.
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 | $0.00141 | $0.02555 |
| Opus 5 | $0.00071 | $0.01277 |
| Sonnet 5 | $0.00028 | $0.00511 |
| Haiku 4.5 | $0.00014 | $0.00255 |
Grade A, and why
ddd-manager 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 — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DDD Manager (s_ddd-manager) — the self-propagation seed
Provision a NEW spec-compliant DDD (the canonical six-section structure), and manage the
lifecycle of existing ones. Because every DDD carries s_ddd-manager, a DDD can create
more DDDs — the ①–⑥ spec spreads to Kiro / Claude Code / any runtime without SwarmAI's
backend.
DDD-native decouple of SwarmAI's
s_project-manager. Same CREATE-with-extraction + BIND lifecycle discipline, re-homed to pure filesystem: nodata.db, noartifact_cli, no SwarmAI services. Ships INSIDE every DDD (copied from the official template at CREATE).
The canonical six-section structure this provisions
<ddd>/
├── .project.json / aim.json / AGENTS.md / .crux_template.md # ① Identity & manifest
├── PRODUCT/TECH/IMPROVEMENT/PROJECT.md + Knowledge/ # ② Knowledge
├── gates/ (+ context/includes/) # ③ Gates (accrete)
├── skills/ ← the 3 DDD-native skills live here # ④ Capabilities
├── bindings.yaml # ⑤ Delivery contract (on BIND)
└── REFRESHER.md # ⑥ Code-intel refresher
The 3 ④ skills: s_ddd-manager s_ddd-persist s_repo-to-ddd — copied in at CREATE.
Do NOT scaffold agents//agent-sops/ (AIM-export form, generated at export, not native).
Lifecycle: CREATE → BIND → PULL → DEVELOP → SYNC-BACK
CREATE is below. BIND+ apply only to a repo-bound DDD (a no-repo DDD stops at CREATE — its 4 docs ARE the deliverable).
CREATE a new DDD
Step 1 — name + optional codebase path
PascalCase preferred; if not PascalCase, note the convention but accept the user's choice. Path (optional) is an existing codebase to extract context FROM (recorded in TECH.md — never a symlink).
Step 2 — validate
test -e "Projects/<Name>" → refuse duplicates; <Name> == a reserved default is refused.
Step 3 — GATHER CONTEXT before writing (CRITICAL: never write blank templates)
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 · 157 lines · 141 tokens per session scan A c7be79182cfe
ddd-manager is a skill published in the GitHub repository xg-gh-25/SwarmAI (44 stars, last pushed 4d ago), licensed MIT. It adds 141 tokens to every session and 2,555 once invoked, about $0.0007 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
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…