dotnet-production-agent-skills / global-instructions
AGENTS.md4 starsChanged 51 days agoMITView on GitHub
Load focused Agent Skills for detailed workflows; do not duplicate their full instructions here.
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 31,700 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 repository37 other files it gives its agents.
- api-contract-safetySkill
- api-endpoint-deprecationSkill
- aspnet-core-api-developmentSkill
- background-services-dotnetSkill
- bug-investigationSkill
- code-qualitySkill
- code-reviewSkill
- context-resetSkill
- dependency-managementSkill
- deployment-readiness-dotnetSkill
- diff-reviewSkill
- distributed-workflowsSkill
- dotnet-architectureSkill
- dotnet-implementationSkill
- dotnet-securitySkill
- ef-core-safetySkill
- exception-handlingSkill
- git-workflowSkill
- google-bigquery-dotnetSkill
- google-cloud-pubsub-dotnetSkill
- google-firestore-dotnetSkill
- http-client-integrationsSkill
- integration-testing-dotnetSkill
- observability-dotnetSkill
- performance-diagnostics-dotnetSkill
- poc-developmentSkill
- production-debuggingSkill
- production-hotfixSkill
- production-loggingSkill
- redis-dotnetSkill
- relational-database-dotnetSkill
- retry-resilienceSkill
- safe-terminalSkill
- shared-code-impactSkill
- targeted-validationSkill
- task-routerSkill
- unit-testingSkill
The file
We split this AGENTS.md into the rules it gives an agent
4 rules. About 1 is common, 2 are distinctive, and 1 is very specific to this project.
≈1
Common · estimate
Many files like this have a rule of this kind.
≈2
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
- could be automatic: a setting could enforce it
- Distinctive: line 4
Before changing shared code, identify its callers and whether the requirement is global or flow-specific.
- Distinctive: line 6
After a coherent change, review the complete diff and run proportionate targeted validation.
- Common: line 7
Do not commit, push, change credentials/tool configuration, or perform destructive operations without authorization.
- Very specific: line 9
Before terminal execution, apply safe-terminal: verify shell and project context, diagnose the actual failure, and retry only after an …
≈ “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
Global engineering guardrails
- Implement the requested behavior without changing unrelated behavior. Do not perform opportunistic cleanup.
- Before changing shared code, identify its callers and whether the requirement is global or flow-specific.
- Preserve existing architecture and public contracts unless the request requires a change.
- After a coherent change, review the complete diff and run proportionate targeted validation. Preserve pre-existing user changes.
- Do not commit, push, change credentials/tool configuration, or perform destructive operations without authorization.
- Never add
Co-authored-by:trailers (case-insensitive), co-author metadata, AI/agent signatures, credits, or generated-by footers to commits or pull requests. Do not inject attribution through trailers, templates, API fields, or Git identity overrides. Inspect complete commit/PR messages before creation and new commits before pushing. If tooling adds attribution, stop before publishing and report it; do not bypass hooks or rewrite existing commits without authorization. Applygit-workflowfor the full procedure. - Before terminal execution, apply
safe-terminal: verify shell and project context, diagnose the actual failure, and retry only after an evidence-based correction. Never move into Git/tool installation directories or inject terminal control sequences to recover a project command. Keep executable lookup separate from repository selection.
Load focused Agent Skills for detailed workflows; do not duplicate their full instructions here.
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.