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 arcasilesgroup/ai-engineering --skill ai-writing-behaviorgit clone --depth 1 https://github.com/arcasilesgroup/ai-engineeringWrote 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/arcasilesgroup/ai-engineering/ai-writing-behavior)<a href="https://agentmods.dev/skills/arcasilesgroup/ai-engineering/ai-writing-behavior"><img src="https://agentmods.dev/badge/skills/arcasilesgroup/ai-engineering/ai-writing-behavior/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/arcasilesgroup/ai-engineering/ai-writing-behavior"><img src="https://agentmods.dev/badge/skills/arcasilesgroup/ai-engineering/ai-writing-behavior.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 | $0.00103 | $0.01827 |
| Opus 5.5 | $0.00041 | $0.00731 |
| Sonnet 5.5 | $0.00021 | $0.00365 |
| Haiku 4.5 | $0.00010 | $0.00183 |
Grade A, and why
ai-writing-behavior 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 19d 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 — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing Agent Behavior
Write the smallest durable behavior spec that lets people and evaluators distinguish acceptable from unacceptable conduct across real trajectories.
The bundled Agent Behavior specification is the complete format contract for this skill. The skill does not require the Agent Behavior source repository, a network connection, or any documentation outside this directory.
Start from source evidence
- Read the bundled Agent Behavior specification before authoring or validating a behavior. A target project may add local conventions, but do not depend on a source checkout or external documentation for the core format.
- Inspect related
BEHAVIOR.mdfiles before creating a new one. - Read the actual prompts, skills, tool instructions, traces, or user decisions that establish the intended conduct. Separate observed behavior from intended behavior.
- Identify whether the task is a new spec, a revision, a split, or a merge. Preserve existing intent unless the evidence explicitly changes it.
If the repository has manifests, registries, or generated indexes, inspect those before moving or renaming a spec. Folder placement is not necessarily activation.
Decide whether the behavior belongs
Use deciding-what-to-save.md. Prefer a sparse set of high-impact, recurring choices over an inventory of every instruction.
A useful candidate usually has all three:
- a recognizable class of situations in which it applies
- a meaningful choice about how the agent should act
- evidence in a trajectory that could show whether the choice occurred
Do not elevate generic virtues, tool syntax, one-off procedures, implementation details, or a disguised scoring rubric. A named runtime mechanism can be a behavior when using that mechanism is itself a durable, recurring control point and the trajectory can prove whether it happened; make that reason explicit in the spec.
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.
- 19d ago Changed 13ef974bfd9f
- 1mo ago First seen · 167 lines · 103 tokens per session scan A db2812d820aa
ai-writing-behavior is a skill published in the GitHub repository arcasilesgroup/ai-engineering (61 stars, last pushed 2d ago), licensed Apache-2.0. It adds 103 tokens to every session and 1,827 once invoked, about $0.0004 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 2026-09-12.
Other skills, from other repositories
spec-kitty-charter-doctrine
Run charter interview, generation, context, and sync workflows for project governance in Spec Kitty 3.x. Access doctrine artifacts programmatically via DoctrineService. Resolve agent profiles. Load action-scoped governance context iteratively, not all at once. Triggers: "interview for charter", "generate charter"…
322-frameworks-spring-boot-testing-integration-tests
Use when you need to write or improve integration tests — including Testcontainers with @ServiceConnection, @DataJdbcTest persistence slices, TestRestTemplate or MockMvcTester for HTTP, data isolation, and container lifecycle management for Spring Boot 4.0.x. This should trigger for requests such as Review Java code…
setup-husky-dotnet
Use when configuring Git hooks in .NET projects before team commits occur, to enforce commit message standards and code formatting automatically.
314-frameworks-spring-kafka
Use when you need to design or implement Kafka messaging in Spring Boot — including topic design, producer/consumer implementation, JSON serialization with Boot factory customizers, Testcontainers @ServiceConnection integration tests, retries and dead-letter topics, idempotency, and error handling. This should trigger…
audit
Independent, on-demand AL codebase auditor for Business Central. Judges the code against BCQuality (citable knowledge) plus native checks for what BCQuality does not reach. Read-only; advisory verdict. Default scope: objects changed vs main; full codebase on request.
review
WCAG 2.2 AA curated accessibility review — distinguishes automatically detectable, browser-assisted, and manual/human-judgment findings with evidence citations and SC mapping. Composes with design-assessment/design-improvement/frontend-design-review.