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/nnunley/fmpl/agents-mdgit clone --depth 1 https://github.com/nnunley/fmplWhat 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 | $0.01434 | $0.01434 |
| Opus 5 | $0.00717 | $0.00717 |
| Sonnet 5 | $0.00287 | $0.00287 |
| Haiku 4.5 | $0.00143 | $0.00143 |
Grade A, and why
fmpl 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 2d 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Workflow rules and gotchas for working in this repo. Codebase inventory,
key-file locations, and doc pointers live in DEV.md.
Design Principles (read first)
Durable invariants live in docs/design-principles.md.
These override iteration scope when in conflict. If you are about to make a
change that would violate a principle, stop — the principle wins, the change
needs to be reframed. Currently captured: metacircular bootstrap (DESIGN-001),
single canonical list-form for structured data (DESIGN-002), symbols for type
names (DESIGN-003), tree-based IR with named temporaries (DESIGN-004), grammar
inheritance deferred (DESIGN-005).
Orientation
FMPL is a streaming-first DSL for AI agents: prototype objects, OMeta-style
PEG grammars, pattern matching via @, and an Indexed RPN bytecode VM.
- Core flow: Source → Lexer (logos) → Parser → AST → Compiler → Indexed RPN bytecode → VM
- Bootstrap pipeline:
ast::parse(source)→ast @ ast_to_ir.expr→ir::compile(ir)→code::eval(code)— the FMPL-in-FMPL path being built toward self-hosting - Current limitations are tracked in
docs/known-gaps.md, grouped by root cause.
Build & Test
just build # REQUIRED build: bootstraps the FMPL-generated parser, then builds
just test # full suite with the canonical parser active
cargo test -p fmpl-core <name> # targeted test during development
just repl # REPL (dot-prefixed commands: .help, .quit)
just web # web server (port 3000)
just tui # TUI (Ctrl+L for LLM chat)
- Plain
cargo buildsilently uses the Rust fallback parser, not the canonical FMPL-generated one. Usejust build(or run the two bootstrap steps in README).canonical_pipeline_parityfails loudly if the fallback is active. - Changing parser codegen (
ir_to_rust.rs) or anything the generated parser embeds? Read the bump policy infmpl-core/src/parser_epoch.rsand bumpPARSER_EPOCH. - Feature flags:
fjall-persistence(durable storage),trampolined-grammar(bounded stack),cross_compile(dormant — needs the externalexecution_tapecrate, see Cargo.toml comments). - Test helpers:
eval(&mut vm, source)for VM tests,parse(source)for parser tests;wiremockfor async HTTP tests (seetests/async_curl.rs).
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.
- 2d ago First seen · 108 lines · 1,434 tokens per session scan A 2d3e4e204f93
fmpl AGENTS.md is an instructions file published in the GitHub repository nnunley/fmpl (5 stars, last pushed 1mo ago), licensed MIT. It adds 1,434 tokens to every session, about $0.0072 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
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.