DinoStack
AGENTS.md14 starsChanged 12 days agoApache-2.0View on GitHub
This file is a minimal activation stub loaded into every Kimi Code CLI session in this repository. The full methodology body (delegation, risk classification, quality gates, git workflow, and the two rules files) is NOT embedded here - it is trigger-loaded via the dinostack skill (DS-185, mirroring the DS-143 change that moved the equivalent always-loaded body out of Claude Code's ~/.claude/CLAUDE.md). Note: This file is auto-generated by .kimi/build.sh. Do not edit it directly. Activation mode/profile is read from ~/.claude/agentic-engineering.json -…
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 31,774 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository17 other files it gives its agents.
- AGENTS.mdAGENTS.md
- bin/AGENTS.mdAGENTS.md
- .codex/AGENTS.mdAGENTS.md
- .github/workflows/AGENTS.mdAGENTS.md
- hooks/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- .cursor/rules/agent-methodology.mdcCursor rule
- .cursor/rules/code-standards.mdcCursor rule
- .cursor/rules/conventions.mdcCursor rule
- .cursor/rules/frontmatter/agent-methodology.yamlCursor rule
- .cursor/rules/frontmatter/code-standards.yamlCursor rule
- .cursor/rules/frontmatter/conventions.yamlCursor rule
- dinostackSkill
- contentSkill
- dinostackSkill
- dinostackSkill
The file
We split this AGENTS.md into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 18
Before acting on any software development task in this repository (code edits, debugging, testing, deployment, architecture decisions, git …
≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Agentic Engineering Protocol
This file is a minimal activation stub loaded into every Kimi Code CLI session in this
repository. The full methodology body (delegation, risk classification, quality gates, git
workflow, and the two rules files) is NOT embedded here - it is trigger-loaded via the
dinostack skill (DS-185, mirroring the DS-143 change that moved the equivalent always-loaded
body out of Claude Code's ~/.claude/CLAUDE.md).
Note: This file is auto-generated by .kimi/build.sh. Do not edit it directly.
Activation
Activation mode/profile is read from ~/.claude/agentic-engineering.json - the same shared
config file every adapter uses. Run bash .kimi/install.sh to configure it.
Load the skill on trigger
Before acting on any software development task in this repository (code edits, debugging,
testing, deployment, architecture decisions, git operations, agent orchestration, code review,
refactoring, dependency management, project setup), load the dinostack skill:
/skill:dinostack(full methodology), or/skill:<command-name>for a specific command (e.g./skill:ds-wrap,/skill:ds-skeptic,/skill:ds-implement-ticket)- or read
.kimi/skills/dinostack/SKILL.mddirectly (local copy) or~/.kimi/skills/dinostack/SKILL.md(global install) if skill loading is unavailable
The skill embeds the full methodology body - it loads on trigger, not automatically at session start. When in doubt, invoke it.
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.