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 OneDro1d/dark-factory --skill df-dispatch-subagentsgit clone --depth 1 https://github.com/OneDro1d/dark-factoryWrote 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/onedro1d/dark-factory/df-dispatch-subagents)<a href="https://agentmods.dev/skills/onedro1d/dark-factory/df-dispatch-subagents"><img src="https://agentmods.dev/badge/skills/onedro1d/dark-factory/df-dispatch-subagents/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/onedro1d/dark-factory/df-dispatch-subagents"><img src="https://agentmods.dev/badge/skills/onedro1d/dark-factory/df-dispatch-subagents.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 | $0.00072 | $0.01642 |
| Opus 5 | $0.00036 | $0.00821 |
| Sonnet 5 | $0.00014 | $0.00328 |
| Haiku 4.5 | $0.00007 | $0.00164 |
Grade A, and why
df-dispatch-subagents 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 8d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dark Factory — Dispatching Sub-Agents (Promise Theory)
Overview
A sub-agent is an autonomous promiser: it cannot be coerced, it lives in its own private context, and it makes best-effort promises, not guarantees. You don't command it — you specify a promise and assess the evidence it returns. Apply this every time you dispatch one.
When to delegate — an obligation, not an option
If it CAN be delegated under Promise Theory, it MUST be. Promise Theory is self-limiting, so this is a rule with its own brake built in: a task is delegable iff (a) the promise is crisply statable AND (b) it returns unforgeable evidence you can verify without redoing the work. If you cannot name both, it is not delegable — do it inline. Optimize for quality, not token budget: parallel fan-out costs more, and that is accepted.
Evidence is RAW, never prose. A sub-agent returns file:line, diffs, exit codes, verbatim command or query output — never "looks fine". Prose is forgeable: a confident summary is indistinguishable from a correct one, so a prose return means the promise was never verifiable and the task was not actually delegable. Raw evidence has a second purpose beyond forgeability — it preserves your own situational model. Delegate the fetching, keep the seeing; the map you build while reading real evidence is the byproduct that makes the next decision good.
Which tier — sort by judgment, never by the verb
Default HIGH; downgrade only on proven mechanicality — proven by a test, not by taste. Rank the task by irreducible judgment × verifiability, and never by the verb in its description: "write some code" can be the hardest judgment in the mission, and "analyse this" can be mere enumeration.
| Tier | Fits | Evidence it must return |
|---|---|---|
| Cheapest / retrieval | pure retrieval — locate, enumerate, fetch | raw values, paths, line numbers |
| Mid | bounded implementation against a spec you wrote, where a test (not taste) decides correctness | diff + test output |
| High, fanned out | adversarial review where diversity is the point: N refuters per finding, each prompted to kill it | each refuter's own citation, separately |
| Most capable, inline (you) | mission model, design, security judgment, the is-this-really-done gate | — you are the one being verified |
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.
- 8d ago First seen · 71 lines · 72 tokens per session scan A ca84deca8789
df-dispatch-subagents is a skill published in the GitHub repository OneDro1d/dark-factory (0 stars, last pushed yesterday), licensed Apache-2.0. It adds 72 tokens to every session and 1,642 once invoked, about $0.0004 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 2026-09-01.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…