EngramGraph
AGENTS.md4 starsChanged 28 days agoMITView on GitHub
Auto-generated by Universal Dev Standards (UDS). Full standards available in the .standards/ directory. Follow the project's linter and formatter configuration. See .standards/ for detailed coding standards. All standards are in .standards/. Installed standards:
- Installs packages
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 repository55 other files it gives its agents.
- ac-coverageSkill
- adrSkill
- ai-collaboration-standardsSkill
- ai-friendly-architectureSkill
- ai-instruction-standardsSkill
- api-designSkill
- atddSkill
- auditSkill
- bddSkill
- brainstormSkill
- changelogSkill
- checkinSkill
- ci-cdSkill
- code-reviewSkill
- commitSkill
- contract-testSkill
- databaseSkill
- deploySkill
- methodologySkill
- dev-workflowSkill
- docgenSkill
- documentation-guideSkill
- durableSkill
- e2eSkill
- error-code-guideSkill
- git-workflow-guideSkill
- incidentSkill
- journey-test-assistantSkill
- knowledge-graphSkill
- logging-guideSkill
- metricsSkill
- migrateSkill
- observabilitySkill
- orchestrateSkill
- planSkill
- prSkill
- discoverSkill
- project-structure-guideSkill
- pushSkill
- refactorSkill
- releaseSkill
- requirementSkill
- retrospectiveSkill
- reverseSkill
- runbookSkill
- securitySkill
- scanSkill
- skill-builderSkill
- sloSkill
- spec-deriveSkill
- sddSkill
- sweepSkill
- tddSkill
- coverageSkill
- testing-guideSkill
The file
We split this AGENTS.md into the rules it gives an agent
8 rules. About 0 are common, 5 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
3
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
- Very specific: line 16
Follow the project's linter and formatter configuration.
- Distinctive: line 28
Write tests for all new features
- Distinctive: line 29
Run tests before committing
- Distinctive: line 30
Follow the testing pyramid: Unit (70%) > Integration (20%) > E2E (10%)
- Very specific: line 41
All standards are in .standards/.
- Very specific: line 118
Read .standards/ files for complete rules before making changes
- Distinctive: line 119
Do not fabricate APIs, configs, or requirements without verification
- Distinctive: line 120
Follow the anti-hallucination standard: evidence-based responses only
≈ “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
AGENTS.md
Auto-generated by Universal Dev Standards (UDS). Full standards available in the
.standards/directory.
Build & Test
npm install # Install dependencies
npm run build # Build project
npm test # Run testsCode Style
Follow the project's linter and formatter configuration.
See .standards/ for detailed coding standards.
Git Workflow
- Workflow: github-flow
- Merge Strategy: squash
- Commit Language: English
- Format:
<type>(<scope>): <subject>
Testing
- Write tests for all new features
- Run tests before committing
- Follow the testing pyramid: Unit (70%) > Integration (20%) > E2E (10%)
<!-- UDS:STANDARDS:START --><!-- WARNING: This block is managed by UDS (universal-dev-standards). DO NOT manually edit. Use 'npx uds init' or 'npx uds update' to modify. -->This block is an index, not the standards. The rules are NOT reproduced here. Before acting on anything below, open the relevant file under
.standards/and follow its contents. Working from this block alone means working without the standards.
Installed Standards
All standards are in .standards/. Installed standards:
.standards/acceptance-criteria-traceability.ai.yaml— acceptance-criteria-traceability.standards/acceptance-test-driven-development.ai.yaml— acceptance-test-driven-development.standards/accessibility-standards.ai.yaml— accessibility-standards.standards/adr-standards.ai.yaml— adr-standards.standards/agent-dispatch.ai.yaml— agent-dispatch.standards/ai-agreement-standards.ai.yaml— ai-agreement-standards.standards/ai-command-behavior.ai.yaml— ai-command-behavior.standards/ai-friendly-architecture.ai.yaml— ai-friendly-architecture.standards/ai-instruction-standards.ai.yaml— ai-instruction-standards.standards/ai-response-navigation.ai.yaml— ai-response-navigation.standards/anti-hallucination.ai.yaml— anti-hallucination.standards/api-design-standards.ai.yaml— api-design-standards.standards/behavior-driven-development.ai.yaml— behavior-driven-development.standards/behavior-snapshot.ai.yaml— behavior-snapshot.standards/changelog.ai.yaml— changelog.standards/checkin-standards.ai.yaml— checkin-standards.standards/class-level-fix.ai.yaml— class-level-fix.standards/code-review.ai.yaml— code-review.standards/commit-message.ai.yaml— commit-message.standards/context-aware-loading.ai.yaml— context-aware-loading.standards/database-standards.ai.yaml— database-standards.standards/deployment-standards.ai.yaml— deployment-standards.standards/developer-memory.ai.yaml— developer-memory.standards/documentation-lifecycle.ai.yaml— documentation-lifecycle.standards/documentation-structure.ai.yaml— documentation-structure.standards/documentation-writing-standards.ai.yaml— documentation-writing-standards.standards/error-codes.ai.yaml— error-codes.standards/feature-discovery-standards.ai.yaml— feature-discovery-standards.standards/feature-manifest-standard.ai.yaml— feature-manifest-standard.standards/flow-based-testing.ai.yaml— flow-based-testing.standards/forward-derivation-standards.ai.yaml— forward-derivation-standards.standards/full-coverage-testing.ai.yaml— full-coverage-testing.standards/git-workflow.ai.yaml— git-workflow.standards/git-worktree.ai.yaml— git-worktree.standards/knowledge-graph-memory.ai.yaml— knowledge-graph-memory.standards/logging.ai.yaml— logging.standards/mock-boundary.ai.yaml— mock-boundary.standards/model-selection.ai.yaml— model-selection.standards/mutation-testing.ai.yaml— mutation-testing.standards/packaging-standards.ai.yaml— packaging-standards.standards/performance-standards.ai.yaml— performance-standards.standards/project-context-memory.ai.yaml— project-context-memory.standards/project-structure.ai.yaml— project-structure.standards/push-standards.ai.yaml— push-standards.standards/refactoring-standards.ai.yaml— refactoring-standards.standards/requirement-engineering.ai.yaml— requirement-engineering.standards/retrospective-standards.ai.yaml— retrospective-standards.standards/reverse-engineering-standards.ai.yaml— reverse-engineering-standards.standards/security-standards.ai.yaml— security-standards.standards/security-testing.ai.yaml— security-testing.standards/self-review-protocol.ai.yaml— self-review-protocol.standards/spec-driven-development.ai.yaml— spec-driven-development.standards/structured-task-definition.ai.yaml— structured-task-definition.standards/systematic-debugging.ai.yaml— systematic-debugging.standards/test-completeness-dimensions.ai.yaml— test-completeness-dimensions.standards/test-driven-development.ai.yaml— test-driven-development.standards/test-governance.ai.yaml— test-governance.standards/testing.ai.yaml— testing.standards/user-journey-testing.ai.yaml— user-journey-testing.standards/verification-evidence.ai.yaml— verification-evidence.standards/versioning.ai.yaml— versioning.standards/virtual-organization-standards.ai.yaml— virtual-organization-standards.standards/options/english.ai.yaml— english.standards/options/github-flow.ai.yaml— github-flow.standards/options/squash-merge.ai.yaml— squash-merge.standards/options/unit-testing.ai.yaml— unit-testing.standards/options/integration-testing.ai.yaml— integration-testing.standards/options/system-testing.ai.yaml— system-testing.standards/options/e2e-testing.ai.yaml— e2e-testing.standards/deferred-item-exit.ai.yaml— deferred-item-exit.standards/open-work-tracking.ai.yaml— open-work-tracking
<!-- UDS:STANDARDS:END -->Important Notes
- Read
.standards/files for complete rules before making changes - Do not fabricate APIs, configs, or requirements without verification
- Follow the anti-hallucination standard: evidence-based responses only
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.

