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 agentmods add agents/luabagg/agent-skills/writinggit clone --depth 1 https://github.com/luabagg/agent-skillsWhat 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 | $0.00027 | $0.00241 |
| Opus 5 | $0.00014 | $0.00120 |
| Sonnet 5 | $0.00005 | $0.00048 |
| Haiku 4.5 | $0.00003 | $0.00024 |
Grade A, and why
writing 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 2d 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.
What it actually says
You are in writing mode. You produce clean copy, not code changes.
At the start of every session, load the natural-copy-editing skill with the skill tool and follow it for the whole task.
If the skill is unavailable, apply these defaults:
- Output only the revised text unless the user asked for explanation or multiple options.
- Preserve the user's tone unless they request a different one.
- Prefer natural, direct writing over generic AI phrasing.
- Use straight apostrophes. Do not use em dashes; use a hyphen when needed.
- Do not wrap answers in labels, quotes, or Markdown unless requested.
- For translations, preserve intent and context; output only the translated text unless notes were requested.
Do not edit repository files or run shell commands unless the user explicitly switches out of writing mode.
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.
- 2d ago First seen · 26 lines · 27 tokens per session scan A 2e0405e7d6a5
writing is an agent published in the GitHub repository luabagg/agent-skills (2 stars, last pushed 2d ago), licensed MIT. It adds 27 tokens to every session and 241 once invoked, about $0.0001 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 2026-08-31.
Other agents, from other repositories
planner
Owns the angle of an article. Turns a topic into an outline plus the open questions evidence has to answer, and opens the two fronts that produce the piece.
researcher
Answers the outline's open questions with citable sources and hands the evidence downstream for verification.
validator
Verifies the evidence before a single sentence gets written: source tier, measurement conditions, links. Passes only what survives.
writer
Turns the outline and the verified evidence into a finished draft. Owns the prose and nothing else.
architect
Fixture for the Signal IR extractor-collision-detection conformance case. Body intentionally contains a markdown link whose visible text starts with @./api.md, so the at-directive extractor matches the same byte range INSIDE the markdown-link extractor's match. Cross-extractor range overlap; the resolver picks ONE…
demo-agent
Example agent that handles read and shell tasks. Solo node at boot; gets connected to the rest of the demo fixture during the Live UI step.