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.
npx agentmods add instructions/asiaostrich/engramgraph/agents-mdgit clone --depth 1 https://github.com/AsiaOstrich/EngramGraphWrote 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/instructions/asiaostrich/engramgraph/agents-md)<a href="https://agentmods.dev/instructions/asiaostrich/engramgraph/agents-md"><img src="https://agentmods.dev/badge/instructions/asiaostrich/engramgraph/agents-md.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 | $0.01144 | $0.01144 |
| Opus 5 | $0.00572 | $0.00572 |
| Sonnet 5 | $0.00229 | $0.00229 |
| Haiku 4.5 | $0.00114 | $0.00114 |
Grade A, and why
EngramGraph AGENTS.md 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 3d 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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 tests
Code 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%)
Standards Reference
IMPORTANT: When performing related tasks, you MUST read and follow the standards in .standards/:
Core Standards:
.standards/acceptance-criteria-traceability.ai.yaml.standards/acceptance-test-driven-development.ai.yaml.standards/accessibility-standards.ai.yaml.standards/adr-standards.ai.yaml.standards/agent-dispatch.ai.yaml.standards/ai-agreement-standards.ai.yaml.standards/ai-command-behavior.ai.yaml.standards/ai-friendly-architecture.ai.yaml.standards/ai-instruction-standards.ai.yaml.standards/ai-response-navigation.ai.yaml.standards/anti-hallucination.ai.yaml.standards/api-design-standards.ai.yaml.standards/behavior-driven-development.ai.yaml.standards/behavior-snapshot.ai.yaml.standards/changelog.ai.yaml.standards/checkin-standards.ai.yaml.standards/class-level-fix.ai.yaml.standards/code-review.ai.yaml.standards/commit-message.ai.yaml.standards/context-aware-loading.ai.yaml.standards/database-standards.ai.yaml.standards/deployment-standards.ai.yaml.standards/developer-memory.ai.yaml.standards/documentation-lifecycle.ai.yaml.standards/documentation-structure.ai.yaml.standards/documentation-writing-standards.ai.yaml.standards/error-codes.ai.yaml.standards/feature-discovery-standards.ai.yaml.standards/feature-manifest-standard.ai.yaml.standards/flow-based-testing.ai.yaml.standards/forward-derivation-standards.ai.yaml.standards/full-coverage-testing.ai.yaml.standards/git-workflow.ai.yaml.standards/git-worktree.ai.yaml.standards/knowledge-graph-memory.ai.yaml.standards/logging.ai.yaml.standards/mock-boundary.ai.yaml.standards/model-selection.ai.yaml.standards/mutation-testing.ai.yaml.standards/packaging-standards.ai.yaml.standards/performance-standards.ai.yaml.standards/project-context-memory.ai.yaml.standards/project-structure.ai.yaml.standards/push-standards.ai.yaml.standards/refactoring-standards.ai.yaml.standards/requirement-checklist.md.standards/requirement-document-template.md.standards/requirement-engineering.ai.yaml.standards/requirement-template.md.standards/retrospective-standards.ai.yaml.standards/reverse-engineering-standards.ai.yaml.standards/security-standards.ai.yaml.standards/security-testing.ai.yaml.standards/self-review-protocol.ai.yaml.standards/spec-driven-development.ai.yaml.standards/structured-task-definition.ai.yaml.standards/systematic-debugging.ai.yaml.standards/test-completeness-dimensions.ai.yaml.standards/test-driven-development.ai.yaml.standards/test-governance.ai.yaml.standards/testing.ai.yaml.standards/user-journey-testing.ai.yaml.standards/verification-evidence.ai.yaml.standards/versioning.ai.yaml.standards/virtual-organization-standards.ai.yaml
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.
- 3d ago First seen · 120 lines · 1,144 tokens per session scan A c422d1edaa6f
EngramGraph AGENTS.md is an instructions file published in the GitHub repository AsiaOstrich/EngramGraph (2 stars, last pushed 16d ago), licensed MIT. It adds 1,144 tokens to every session, about $0.0057 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 2026-08-31.
Other instructions, from other repositories
samyama-graph CLAUDE.md
Instructions for samyama-ai/samyama-graph, covering claude.md, project overview, build & development commands, build and run tests (1814 unit tests).
kglite CLAUDE.md
Instructions for kkollsga/kglite, covering kglite — claude code conventions, build & test, architecture, the boundary principle (wrappers vs core) — summary and in-memory is the core product.
kivgraph AGENTS.md
Instructions for Luqueee/kivgraph, covering instrucciones de desarrollo de kivgraph, mapa de instrucciones, identidad del proyecto, qué pregunta contesta cada tool de kivgraph and la puerta delante de grep.
sec-ownership-graph CLAUDE.md
Claude Code instructions for alexwoolford/sec-ownership-graph, covering claude.md, what this is, environment & common commands, the reproducibility contract and core conventions (enforced).
kivgraph CLAUDE.md
Instructions for Luqueee/kivgraph, a project described as: A local MCP server for cross-repository semantic code intelligence in TypeScript and Go, backed by a persistent LadybugDB graph.
m_flow AGENTS.md
AGENTS.md instructions for FlowElement-xinliuyuansu/m_flow, covering m-flow — developer & agent reference, 1. repository map, extension points, 2. local development and python backend (requires python 3.10 – 3.13).