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.
git clone --depth 1 https://github.com/aborroy/aiup-alfrescoWrote 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/commands/aborroy/aiup-alfresco/behaviours)<a href="https://agentmods.dev/commands/aborroy/aiup-alfresco/behaviours"><img src="https://agentmods.dev/badge/commands/aborroy/aiup-alfresco/behaviours.svg" alt="Measured on agentmods" 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 | $0.01927 |
| Opus 5 | $0.00012 | $0.00963 |
| Sonnet 5 | $0.00005 | $0.00385 |
| Haiku 4.5 | $0.00002 | $0.00193 |
Grade A, and why
behaviours 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 — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/behaviours — Behaviour/Policy Generator
In-Process SDK only — deploys inside the ACS JVM as a Platform JAR. For asynchronous event-driven reactions to repository changes from an external app, use
/events(Out-of-Process) instead.
Generate Alfresco behaviour classes for synchronous node event handling.
Input
Read REQUIREMENTS.md to identify behaviour requirements and resolve the Platform JAR
project's Root path from Section 2 (Project Architecture).
- If Section 2 contains no
Platform JARproject, stop and explain that/behavioursonly applies to the in-process repository addon project.
Output Files
1. Behaviour Class
{platform-project-root}/src/main/java/{package}/behaviour/{Name}Behaviour.java
- Implement appropriate policy interface (
OnCreateNodePolicy,OnUpdatePropertiesPolicy,OnAddAspectPolicy, etc.) - Register behaviour in
init()method usingPolicyComponent - Inject required Alfresco services
2. Spring Bean Configuration
Add bean definition to {platform-project-root}/src/main/resources/alfresco/module/{module-id}/context/service-context.xml
Conventions
{module-id}is the Platform JAR artifactId — the bare artifact ID (e.g.behaviours), not the fullmodule.idproperty value (e.g.com.someco.behaviours). Derive it as{platform-artifactId}from Section 2 ofREQUIREMENTS.mdor from<artifactId>in the platformpom.xml. Never use{groupId}.{artifactId}as the directory name.{platform-project-root}is.for Platform JAR only mode, or{name}-platform/for Mixed mode- Use
JavaBehaviourwithNotificationFrequency.TRANSACTION_COMMIT(default) orEVERY_EVENTwhere specified - Bind to specific types/aspects from the content model
- Log at appropriate levels
- Handle transaction context properly
- Never generate behaviours inside the Event Handler project
SearchService Query Rules
Rule 1 — Always use AFTS; never use Lucene query language
Every SearchParameters object must use SearchService.LANGUAGE_FTS_ALFRESCO.
SearchService.LANGUAGE_LUCENE is deprecated since ACS 6.x, incompatible with Search
Enterprise (Elasticsearch/OpenSearch), and must never appear in generated code.
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 · 185 lines · 23 tokens per session scan A 5fe441161c95
behaviours is a command published in the GitHub repository aborroy/aiup-alfresco (13 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 23 tokens to every session and 1,927 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 2026-08-30.
Other commands, from other repositories
design-api-integration
Design an integration with a third-party API so its failures and changes stay contained.
design-caching
Design a caching layer with explicit invalidation, chosen for a specific access pattern rather than added generally.
api-contract
Write a human-readable API contract companion as Markdown in the user's repository. Use when invoked as /document-design-system:api-contract. Produce designed HTML or PDF only when asked.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.