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 HirogaKatageri/hirokata --skill domain-softwaregit clone --depth 1 https://github.com/HirogaKatageri/hirokataWrote 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/hirogakatageri/hirokata/domain-software)<a href="https://agentmods.dev/skills/hirogakatageri/hirokata/domain-software"><img src="https://agentmods.dev/badge/skills/hirogakatageri/hirokata/domain-software/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/hirogakatageri/hirokata/domain-software"><img src="https://agentmods.dev/badge/skills/hirogakatageri/hirokata/domain-software.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 | $0.00180 | $0.03251 |
| Opus 5.5 | $0.00072 | $0.01300 |
| Sonnet 5.5 | $0.00036 | $0.00650 |
| Haiku 4.5 | $0.00018 | $0.00325 |
Grade A, and why
domain-software 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 — 266 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The software domain profile
You are the strategist and this page is your domain. agents/strategist.md carries the
method — read the requirement, survey, cut the work into tickets, assert what may run
together, emit the graph, record every deviation. That method knows nothing about software on
purpose. This page is what makes it a software plan.
Load this before Step 2 of your workflow. A guild with no domain: key in
.guild/config.yaml uses this profile, so on a code project it loads by default and nothing
about your behaviour changes.
Six slots. Each is a question the method asks and this profile answers.
Slot 1 — What surveying the current state means
The strategist's method already tells you to read the guild's own library and decision log; that part is domain-free and stays in the agent. This is the rest of it, for a code project:
- Read project docs:
CLAUDE.md,README.md,ARCHITECTURE.mdif they exist - Identify project type: Check
package.json,pubspec.yaml,requirements.txt, etc. - Find related code: Search for existing patterns related to the requirement
- Map the architecture: Understand directory structure, module organization, key abstractions
- Note conventions: Coding style, naming patterns, error handling approaches, test patterns
When to delegate research. Use the Agent tool inline — do not queue a handoff. Research is needed if:
- The requirement involves a library, framework, API, or protocol you are not confident about,
AND no
docrow covers it - The requirement depends on a third-party service whose current API shape you have not verified (and docs are absent or stale)
- The codebase uses a technology whose conventions you cannot infer from the files you read
- A key technical decision hinges on information not present in the codebase or docs
Slot 2 — What two concurrent tickets contend for
In this domain, a ticket owns a set of FILE PATHS, and two tickets may run together only if
their sets are disjoint. That set is what goes into task.files.
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 Changed · +52 lines · +24 tokens per session 939dd68d7854
- 1mo ago First seen · 214 lines · 156 tokens per session scan A fea3f2a2f641
domain-software is a skill published in the GitHub repository HirogaKatageri/hirokata (6 stars, last pushed 9d ago), licensed MIT. It adds 180 tokens to every session and 3,251 once invoked, about $0.0007 per session on Opus 5.5. 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 2026-09-09.
Other skills, from other repositories
unslop
Humanize LLM output so it reads like a careful human wrote it. Subtracts AI-isms (sycophancy, tricolons, em-dash overuse, "delve"/"tapestry"/"testament", hedging stacks, tidy five-paragraph shapes), engineers burstiness and calibrated uncertainty, and preserves technical accuracy. Supports intensity levels: subtle…
unslop-file
Humanize natural-language memory files (CLAUDE.md, todos, preferences, docs) by removing AI-isms and adding burstiness while preserving every code block, URL, path, command, and heading exactly. Two modes: --deterministic (fast, regex-based, no API) and LLM (default, calls Claude for rewrite). Humanized version…
unslop-commit
Rewrites commit messages so they sound like a careful human engineer wrote them. Strips AI/marketing slop ("comprehensive solution", "robust implementation", "leverage", "enhance", "seamlessly", "This commit..."). Keeps Conventional Commits format. Subject ≤72 chars (aim ≤50), imperative mood. Body only when "why"…
unslop-help
Quick-reference card for unslop modes, sub-skills, and slash commands. One-shot display, not a persistent mode. Trigger: /unslop-help, "unslop help", "what unslop commands", "how do I use unslop".
simulator-charts
Simulator.Company chart and dashboard specialist. Use when the user wants to create, configure, or query charts (line, bar, stackedBar, pie, …), dashboards, or financial time-series visualisations on a graph layer. Trigger on any of these intents: — Creating: "create chart", "add chart", "create dashboard", "add…
simulator-init
Simulator.Company environment setup specialist. Use when the user wants to connect to Simulator.Company, set up credentials, authenticate, configure the workspace, or start working with Simulator for the first time. Activate when the user says "init", "setup", "connect to simulator", "login to simulator", "configure…