barrilete-kit
llms.txt6 starsChanged 7 days agoMITView on GitHub
TODO: one line with what the product is, the decision that defines it and how the repo is laid out. Instructions for models: read this file and AGENTS.md. Aspirational spec = /README.md. Narrative = docs/development/vision.md. Code that runs = docs/development/architecture.md. Order = docs/development/roadmap.md. Long term (do not implement) = docs/development/horizon.md. Why = docs/decisions/. TODO: one-line rules a model must not break. - Hub - Glossary: domain words - Contexts: bounded contexts and their limits - GitHub naming convention — labels…
In this repository16 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- llms.txtllms.txt
- add-memberSkill
- create-issueSkill
- db-migrationSkill
- debugSkill
- git-workflowSkill
- implement-issueSkill
- improve-skillsSkill
- orchestrateSkill
- plan-featureSkill
- project-statusSkill
- remove-memberSkill
- review-prSkill
- update-docsSkill
The file
Files
# <PROJECT> > TODO: one line with what the product is, the decision that defines it and how the repo is laid out. Instructions for models: read this file and AGENTS.md. Aspirational spec = /README.md. Narrative = docs/development/vision.md. Code that runs = docs/development/architecture.md. Order = docs/development/roadmap.md. Long term (do not implement) = docs/development/horizon.md. Why = docs/decisions/. TODO: one-line rules a model must not break. ## Documentation <!-- Rule: a document goes into this list only once it has content. If it only says "TODO: fill in", it is not listed: a model that reads it gains nothing and may assume nothing is defined. When you fill it in, add it with its line. Exception (ADR-003 D7): the glossary and the contexts are listed from the start, even as TODO templates. --> - [Hub](README.md) - [Glossary: domain words](reference/glossary.md) - [Contexts: bounded contexts and their limits](reference/contexts.md) - [GitHub naming convention](github-naming-convention.md) — labels in ../.github/labels.yml - [Decisions (ADRs)](decisions/README.md) <!-- template:start --> - [ADR-001: kit language, labels and names in English (kit ADR)](decisions/ADR-001-language-labels-and-names-in-english.md) <!-- template:end --> - [ADR-002: structured validation of the red test](decisions/kit/ADR-002-structured-red-validation.md) - [ADR-003: minimal DDD, glossary and bounded-context map](decisions/kit/ADR-003-minimal-ddd-glossary-and-contexts.md) - [ADR-004: `/orchestrate` launch mode per role (bk or subagent)](decisions/kit/ADR-004-orchestrate-launch-mode-per-role.md) - [ADR-005: tasks and events for bk agents](decisions/kit/ADR-005-tasks-and-events-for-bk-agents.md) - [ADR-006: rules store for agents](decisions/kit/ADR-006-rules-store-for-agents.md) - [Map for agents: docs by change, sensitive paths](agents-map.json) - [Subagent contract: common rules and output](agents/subagent-contract.md) - [Finding classes of review-pr (generated by `scripts/agents/sync-rules` from barrilete-rules, ADR-006)](agents/classes.yml) - [AGENTS.md](../AGENTS.md) - [Spec](../README.md) ## Anchor code - TODO: the 4 or 5 files through which the system is understood (route mounting, schema, states).
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

