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/salakar/pluto/agents-mdgit clone --depth 1 https://github.com/Salakar/plutoWhat 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 | $0.04796 | $0.04796 |
| Opus 5 | $0.02398 | $0.02398 |
| Sonnet 5 | $0.00959 | $0.00959 |
| Haiku 4.5 | $0.00480 | $0.00480 |
Grade A, and why
pluto 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 — 430 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Pluto engineering playbook
This is the fast path for an agent (or a new human) to become productive in the
Pluto repository. It covers the toolchain, the device workflow, tests,
benchmarks, deployment (AOT vs. JIT), hot reload, and the pluto CLI. Read
README.md for the elevator pitch and
docs/GETTING_STARTED.md for the guided first run;
this file is the reference you keep open while working.
What Pluto is
Pluto runs Flutter apps on supported reMarkable e-ink tablets through one discovery-driven product and CLI. Hardware-specific display and lifecycle backends are selected internally:
- a custom software-rendering Flutter embedder (
embedder/, C++), with an e-ink renderer and presenters that drive the panel's waveform controller; - the
plutoCLI (tools/pluto/, Dart) for device discovery, provisioning, build, install, logs, screenshots, and hot reload; - a Flutter Home/launcher (
apps/launcher/) that is the common entry point for Pluto applications; pluto_*Dart packages (packages/) exposing device, settings, pen, touch, sensors, manifest, provision, and UI APIs;- example and product apps (
apps/): counter, motion_lab, ink_lab, validation_lab, ink (drawing), codex (terminal).
Apps ship as release AOT by default. JIT exists only behind explicit --debug
flags for hot reload and can never become the boot default.
Repository map
| Path | What lives there |
|---|---|
embedder/ |
Native embedder, renderer, compositor, profile-selected panel drivers, host preview, CMake presets, C++ tests + benches |
tools/pluto/ |
The pluto CLI (standalone Dart package, resolves outside the workspace) |
tools/setup/ |
setup.sh bootstrap; camera/ panel-capture helper |
tools/build/ |
Host and ARM device builds; target payload assemblers |
tools/device/ |
On-device backends, installer/uninstaller, power/standby, safety harness, diagnostics, shell-contract tests |
tools/engine/ |
Flutter engine rebuild + promotion (pin maintainers only) |
packages/pluto_* |
Dart API packages |
apps/ |
Launcher, examples, ink, codex, validation_lab |
third_party/engine/<hash>/ |
Pinned, checksummed Flutter engine payloads (committed on purpose) |
docs/ |
Getting started, AOT runtime, lifecycle, rendering, icon style, optimisation log, camera |
ci/check.sh |
The complete quality gate |
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 · 430 lines · 4,796 tokens per session scan A 20065e6b5984
pluto AGENTS.md is an instructions file published in the GitHub repository Salakar/pluto (20 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 4,796 tokens to every session, about $0.0240 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 2026-08-30.
Other instructions, from other repositories
wind dynamic.instructions.md
Instructions for fluttersdk/wind, covering dynamic json renderer (lib/src/dynamic/), json schema, security model (whitelist first), state binding (id-keyed widgets) and action dispatch.
flutter_desktop_updater AGENTS.md
Instructions for MarlonJD/flutter_desktop_updater, covering agent instructions for desktopupdater, start here, repository map, validation ladder and local conventions.
wind tests.instructions.md
Instructions for fluttersdk/wind, covering test conventions (test/), layout mirror, required setup, no mockito and lifecycle discipline.
sanad-agent AGENTS.md
Instructions for EastStarAI/sanad-agent, covering sanad agent repository contract, 1. documentation hierarchy, rules for ai agents and developers, 1.1. the strict separation pact and 1.2. the living project wiki & incremental documentation.
OpenNutriTracker CLAUDE.md
Claude Code instructions for simonoppowa/OpenNutriTracker: Canonical agent instructions for this repository live in AGENTS.md.
lotti AGENTS.md
AGENTS.md instructions for matthiasn/lotti, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.