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 GregoryHo/arcforge --skill writing-skillsgit clone --depth 1 https://github.com/GregoryHo/arcforgeWrote 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/gregoryho/arcforge/writing-skills)<a href="https://agentmods.dev/skills/gregoryho/arcforge/writing-skills"><img src="https://agentmods.dev/badge/skills/gregoryho/arcforge/writing-skills/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/gregoryho/arcforge/writing-skills"><img src="https://agentmods.dev/badge/skills/gregoryho/arcforge/writing-skills.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 | $0.00023 | $0.01855 |
| Opus 5.5 | $0.00009 | $0.00742 |
| Sonnet 5.5 | $0.00005 | $0.00371 |
| Haiku 4.5 | $0.00002 | $0.00186 |
Grade A, and why
writing-skills 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 today.
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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing Skills
A skill exists to squeeze predictability out of a stochastic system. Judge every sentence by one question: does an agent behave more predictably with this text than without it? Text that does not move behavior is cost, not content.
Invocation
Each skill is exactly one kind, decided by disable-model-invocation.
| model-invoked (default) | user-invoked (disable-model-invocation: true) |
|
|---|---|---|
| Trigger | the model decides, from the description alone | the user typing the slash command |
| Failure when wrong | loads when irrelevant | never loads when it would have helped |
Decide with one question: should the agent reach for this on its own? Reuse is not the criterion — a skill used daily is still user-invoked if autonomous loading would derail unrelated work. Authoring methodology and anything a person starts deliberately are user-invoked; anything that must fire the moment its condition appears mid-task is model-invoked. Context load is what a skill costs once loaded; cognitive load is what it costs the agent to decide whether to load it — charged on every unrelated turn, even when nothing loads.
A user-invoked skill is an entry point, not a callable. No other skill's prose invokes it, because that routes around the deliberate start it exists to require. It still gets its router row: that table indexes the skill set, it does not call into it.
Writing the description
The description is the only part always in context. It is a trigger index, not a summary.
| Rule | Why |
|---|---|
| Front-load the leading word | The first word carries retrieval weight; lead with identity, never a hedge |
| One trigger phrase per branch | Three real situations mean three named triggers; one abstract phrase loses all three |
| Synonyms are duplication | "review, critique, assess" is one trigger written three times — it dilutes, it does not widen |
| Never summarize the workflow | Check it: could an agent act on the description alone? If it could, it will, and the body goes unread |
| User-invoked strips the triggers | The user already decided; state plainly what the skill is |
What ships with it
3 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.
- today First seen · 156 lines · 23 tokens per session scan A 058d00d20929
writing-skills is a skill published in the GitHub repository GregoryHo/arcforge (8 stars, last pushed 12d ago), licensed MIT. It adds 23 tokens to every session and 1,855 once invoked, about $0.0001 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 2026-11-07.
writing-skills compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| writing-skillsGregoryHo/arcforge | Skill | 8 | 12d ago | MIT | A | 23 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |