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/marlonjd/flutter_desktop_updater/agents-mdgit clone --depth 1 https://github.com/MarlonJD/flutter_desktop_updaterWrote 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/marlonjd/flutter_desktop_updater/agents-md)<a href="https://agentmods.dev/instructions/marlonjd/flutter_desktop_updater/agents-md"><img src="https://agentmods.dev/badge/instructions/marlonjd/flutter_desktop_updater/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 | $0.00674 | $0.00674 |
| Opus 5 | $0.00337 | $0.00337 |
| Sonnet 5 | $0.00135 | $0.00135 |
| Haiku 4.5 | $0.00067 | $0.00067 |
Grade A, and why
flutter_desktop_updater 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 5d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Instructions For desktop_updater
This file is the repo map for agentic work. Keep it short; deeper project
knowledge belongs in docs/.
Start Here
- Read this file first, then follow the most local instruction file that applies to the files you touch.
- Use the architecture map for system boundaries and dependency direction.
- Use the documentation map to locate canonical product, security, reliability, publishing, and platform guidance.
- Use the harness operating model for validation, evidence, and maintenance rules.
- Use the agent harness for repository-native capabilities, verification mapping, and certification boundaries.
- Use the execution-plan ledger to find active and completed work.
- Do not create, switch, rename, or delete branches unless the user explicitly asks for that branch action.
- Do not post GitHub comments or PR reviews through connector identities. Draft text for the user instead.
Repository Map
- Public package API:
lib/desktop_updater.dart,lib/updater_controller.dart, andlib/widget/. - Update runtime core:
lib/src/core/. - Network and file transports:
lib/src/io/. - Release, package, verify, and migration CLIs:
bin/andlib/src/release_cli/. - Native plugin code:
macos/,windows/, andlinux/. - Example host app and platform smoke tools:
example/. - Package docs:
README.md,docs/, anddoc/. - Durable design decisions: docs/design-docs/.
- Repository-backed execution plans: docs/exec-plans/.
Validation Ladder
Use the narrowest useful command first, then widen before handoff:
flutter test --no-pub test/<focused_test>.dart
dart format --output=none --set-exit-if-changed .
flutter analyze --no-fatal-infos
flutter test --no-pub
dart pub publish --dry-run
For harness-only changes, run dart run tool/harness_gate.dart --structural
before the focused documentation test. A structural pass is not the
source/attestation-bound harness-ready claim.
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.
- 5d ago First seen · 71 lines · 674 tokens per session scan A 775386490851
flutter_desktop_updater AGENTS.md is an instructions file published in the GitHub repository MarlonJD/flutter_desktop_updater (52 stars, last pushed 15d ago), licensed MIT. It adds 674 tokens to every session, about $0.0034 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
Pulse AGENTS.md
AGENTS.md instructions for Regncreative/Pulse, covering agents.md, pulse, vision, mission and philosophy.
appwrite AGENTS.md
AGENTS.md instructions for appwrite/appwrite, covering appwrite, commands, stack, layout and libraries.
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.
wind docs.instructions.md
Instructions for fluttersdk/wind, covering documentation conventions (doc/), file shape (every doc file), wfoo, basic usage and props.
leopardo-hr AGENTS.md
Instructions for kitokoh/leopardo-hr, covering agents.md - guide de travail leopardo rh, ⚡ spec-driven development — spec kit (nouveau 2026-08-14), commandes disponibles (github copilot skills), presets actifs (injectes automatiquement dans toute spec) and workflow standard (remplace la creation manuelle d'issues).
webf CLAUDE.md
Claude Code instructions for openwebf/webf, covering webf development guide, 📚 folder-specific guides, 🚀 quick start, repository structure and common commands.