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 Unique-Divine/jiyuu --skill ud-writing-techgit clone --depth 1 https://github.com/Unique-Divine/jiyuuWrote 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/unique-divine/jiyuu/ud-writing-tech)<a href="https://agentmods.dev/skills/unique-divine/jiyuu/ud-writing-tech"><img src="https://agentmods.dev/badge/skills/unique-divine/jiyuu/ud-writing-tech/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/unique-divine/jiyuu/ud-writing-tech"><img src="https://agentmods.dev/badge/skills/unique-divine/jiyuu/ud-writing-tech.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 | $0.00087 | $0.00958 |
| Opus 5.5 | $0.00035 | $0.00383 |
| Sonnet 5.5 | $0.00017 | $0.00192 |
| Haiku 4.5 | $0.00009 | $0.00096 |
Grade A, and why
ud-writing-tech 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UD writing tech
Use this skill to write and edit clear technical documentation for engineers and agents. Choose wording that makes the project clear, even when it departs from general style rules.
General guidance
- Write for readers who work with code, schemas, databases, APIs, commands, services, and operational systems.
- Make the entity type clear when referring to code-formatted symbols.
- Be concise, but don't let brevity create ambiguity.
- Adapt these guidelines when another wording makes the document clearer.
Qualify code symbols with entity type
When referring to a named code symbol, data object, or tool in prose, add a noun that tells the reader what it is.
Backticks identify the exact symbol. The surrounding noun tells the reader what the symbol is.
Prefer:
- table
stats_perp_by_user - database column
market_id - GraphQL field
volume - GraphQL type
PerpBorrowing - function
Delegation - agent skill
nibiru-cli-nibid - command
just fmt - REST endpoint
GET /dexpal/v1/stats - file
graphql/graph/perp.graphqls - service
StatsRefresher
Avoid bare references when the entity type is not obvious:
stats_perp_by_userrefreshesDelegationhandles this- use
nibiru-cli-nibid - run
just fmt
Better:
- table
stats_perp_by_userrefreshes - function
Delegationhandles this - use agent skill
nibiru-cli-nibid - run command
just fmt
How strict to be
- Add a qualifier on first use in a section, as you would define a term or spell out an abbreviation.
- In specs, repeat qualifiers when readers need them to understand a reference.
- Relax the rule when repeated qualifiers make a paragraph noisy and the entity type is already clear.
- Use judgment about how often to repeat qualifiers. Each reference should be clear to the reader.
- Use abbreviations such as
proc,fn,func,db column, andGQL fieldin drafts and working notes when readers understand them. - If the user asks for a polished style or says not to use abbreviations, prefer fuller labels like SQL procedure, function, database column, and GraphQL field.
What ships with it
1 file 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.
- 8d ago First seen · 110 lines · 87 tokens per session scan A 691591a15e34
ud-writing-tech is a skill published in the GitHub repository Unique-Divine/jiyuu (6 stars, last pushed 8d ago), licensed MIT. It adds 87 tokens to every session and 958 once invoked, about $0.0003 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 2026-10-08.
Other skills, from other repositories
repomix
Pack and analyze codebases into AI-friendly single files using Repomix. Use when the user wants to explore repositories, analyze code structure, find patterns, check token counts, or prepare codebase context for AI analysis. Supports both local directories and remote GitHub repositories.
dd-code-generation
Use pup CLI for immediate Datadog operations or generate code for integration into applications.
mma-investigator
Expert system for investigating MMA (Multi-Metric Allocator) behavior on CockroachDB clusters. Helps oncall engineers diagnose load imbalances, understand rebalancing decisions, and identify why MMA did or didn't act.
migrate-state-management
Migrate Redux or React Context to the correct state option (React Query for server state, nuqs for URL/shareable state, Zustand for global client state). Use when refactoring away from Redux/Context, moving state to the right store, or when the user asks to migrate state management.
Linux Malware Analysis
Expert ELF malware analysis — packing, toolchain ID, kill chain, persistence, C2, rootkits, cryptominers, Go/Rust/Mirai patterns, MITRE ATT&CK mapping.
lsp-implement
Find all concrete implementations of an interface or abstract type. Use when you need to know what types satisfy an interface, or what subtypes exist before changing a base type.