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/epicsagas/episteme/agents-mdgit clone --depth 1 https://github.com/epicsagas/EpistemeWrote 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/epicsagas/episteme/agents-md)<a href="https://agentmods.dev/instructions/epicsagas/episteme/agents-md"><img src="https://agentmods.dev/badge/instructions/epicsagas/episteme/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 | $0.02402 | $0.02402 |
| Opus 5 | $0.01201 | $0.01201 |
| Sonnet 5 | $0.00480 | $0.00480 |
| Haiku 4.5 | $0.00240 | $0.00240 |
Grade A, and why
Episteme 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 4d 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Commands
- Build:
cargo build| Build (release):cargo build --release - Test:
cargo test| Test single:cargo test <test_name>| Test module:cargo test --lib <module>::tests - Lint:
cargo clippy -- -D warnings| Format:cargo fmt| Run:cargo run -- <subcommand> - Gen/Sync: N/A
Project Structure
src/main.rs— CLI entry point (clap derive, 13 subcommands)src/lib.rs— Library root, re-exports primary typessrc/cli.rs— Clap command enum definitionssrc/commands/— CLI subcommand handlers:analysis,build,search,graph,install,service,othersrc/domain/— Business logic (no external deps):graph(KnowledgeGraph, BFS, inverse relation derivation),detectors(16 smell detectors),engine(RefactoringRanker),inference,summarizer,problem_mapper,types(Entity, EntityType, RelationType, SmellType),metrics(CodeMetrics, SmellDetection)src/ports/— Traits (hexagonal boundaries):parser(CodeParser),search(SearchIndex),graph(GraphRepository),embeddings(EmbeddingProvider)src/adapters/— Infrastructure:regex_parsers(GenericParser, 10 langs),python_ast_parser(rustpython-parser),search_engines(FTS5 + cosine),sqlite_db,cache,local_embeddings(fastembed/ONNX),openai_embeddings,service(MCP HTTP daemon),installer(Transport enum, upsert_dir, multi-tool seeding),install_wizard(TUI transport selection),config,metrics,telemetry,paths,hooks,json_loader,constants,error,rate_limiter,structured_logging,chunker,builder,rate_limiter_mwsrc/server/— HTTP layer (axum):api_routes(REST endpoints),api_server,api_app,api_middleware,api_models,mcp_handler(MCP facade),mcp_dispatcher,mcp_search,mcp_graph,mcp_analysis,mcp_schemas,mcp_transport_http,mcp_auth,web_viewer(D3-force graph UI)raw/— Knowledge base source data:code-smells/,design-patterns/,refactoring/,software-engineering/meta/— Generated metadata:relations.json(solves is SSOT; solved_by derived at load time),taxonomy.json,schema.json,code_smells.jsonregistry/— Seedable artifacts:agents/(4 AI agent definitions),skills/episteme/(skill definition)docs/— User documentation:api.md,mcp-integration-guide.md,distribution.md,alcove-integration.mdbenchmarks/— Search quality benchmarks and evaluationmonitoring/— Prometheus + Grafana + Alertmanager configdb/— Pre-built SQLite database (episteme.db)dist/— Release packaging artifacts
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.
- 4d ago First seen · 112 lines · 2,402 tokens per session scan A fee9366d01e5
Episteme AGENTS.md is an instructions file published in the GitHub repository epicsagas/Episteme (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 2,402 tokens to every session, about $0.0120 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
memora CLAUDE.md
Claude Code instructions for agentic-box/memora, covering memora and memory.
neurostack CLAUDE.md
Instructions for raphasouthall/neurostack, covering neurostack - claude code guide, quick reference, installation, mcp server (recommended for claude code) and openai-compatible api.
brain-in-the-fish CLAUDE.md
Instructions for fabio-rovai/brain-in-the-fish, covering brain in the fish, relationship to open-ontologies, module overview, pipeline and mcp tools.
togomcp CLAUDE.md
Claude Code instructions for dbcls/togomcp, covering togomcp, architecture, data layout, parameter conventions and return-shape and error conventions.
codemem CLAUDE.md
Instructions for cogniplex/codemem, covering claude.md, build & test, git workflow, code review and general principles.
nobrainr CLAUDE.md
Claude Code instructions for vicquick/nobrainr, covering nobrainr — collective agent memory service, what this is, canonical categories, architecture and routing (when using a reverse proxy).