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 skills/danmcinerney/orchflows/browser-gamenpx skills add DanMcInerney/orchflows --skill browser-gamegit clone --depth 1 https://github.com/DanMcInerney/orchflowsWrote 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/skills/danmcinerney/orchflows/browser-game)<a href="https://agentmods.dev/skills/danmcinerney/orchflows/browser-game"><img src="https://agentmods.dev/badge/skills/danmcinerney/orchflows/browser-game.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 5.1 | $0.00020 | $0.01128 |
| Opus 5 | $0.00010 | $0.00564 |
| Sonnet 5 | $0.00004 | $0.00226 |
| Haiku 4.5 | $0.00002 | $0.00113 |
Grade A, and why
browser-game 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 yesterday.
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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Require: one incomplete product request as brief, and workspace, the
git-backed product repository — the only invocation inputs. Missing fields
never become defaults: an empirical gap becomes a declared experiment, a
kind: user-only gap one verbatim question for the root to relay, and
neither blocks the other.
tickets.py frame-open <run> --goal-file <program-goal> --workflow browser-game
Record, do --standard orch-content --isolation required: one
versioned program record in workspace for brief, conforming to its
program-record schema
and intake-authority policy.
Each Q-01–Q-12 field is recorded independently with its disposition,
authority kind, owner, rationale, evidence and revision; each omitted
material field carries a stable open-question or decision identity; a
settled decision keeps its revision and invalidation trigger.
browser_game_validate.py runs against it before filing.
Evidence, do --standard orch-research handed the record's artifact
line: one fixed evidence packet for the independently schedulable empirical
fields affecting the record's next transition. Each experiment matches its
source field's open decision_id, predeclares every required field and
settles only its matched cells. Negative, null and inconclusive results stay
visible; a control or experiment without the policy's complete recorded
trigger identity stays inactive.
Checkpoint, one judge --standard orch-content over both artifact
lines: exactly one disposition — advance, revise, experiment,
user-decision-required or stop — bound to its governing requirement, the
fixed record revision and evidence identity. Its findings validate
against the
checkpoint contract.
Only where that disposition is lawful does one further
do --standard orch-content materialize the
standard-separated successor plan,
each ordered entry preserving its artifact identity, artifact kind, matching
standard, run/root identities, dependencies and planned/opened
status.
Never: invent a stack, cohort, support promise, budget, fallback, provider
or release policy; settle a user-only field from evidence
or paraphrase its question before relay; represent absence as agreement or
overwrite a settled decision; infer advance from task completion; open a
successor whose kind, standard, predecessor identity, dependency or root identity
is unresolved; hide one artifact kind behind another's identity; or file
anything the instance validator rejects.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday Changed c987ab62c794
- 2d ago First seen · 83 lines · 20 tokens per session scan A ace4747f196c
browser-game is a skill published in the GitHub repository DanMcInerney/orchflows (53 stars, last pushed today), licensed MIT. It adds 20 tokens to every session and 1,128 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
multiplatform-conversion
Converting a single-target FlatRedBall2 desktop sample into a dual-target desktop + KNI BlazorGL (Blazor WebAssembly / browser) project. Use when the user mentions web deployment, browser/WASM/itch.io targets, KNI, or asks to add web support to an existing game. Assumes you already have a working desktop sample — see…
agent-casino-gambling
Interact with MoltCasino - a 3D Vegas-style casino built for AI agents.
webg-spec-to-goal
Convert a web game idea (even a vague one like "build a Raiden-type game" or "make a card game") into a complete Codex /goal-ready Phaser 3 project — runnable scaffold, goals-plan.md, and all goal folders (GOAL.md + VERIFY.md + PROGRESS.md) generated at once. Auto-detects genre (shoot-em-up, card game, platformer…
lattice
Build a playable isometric game from one sentence, end to end — scaffold, code, run it in a browser, look at it, fix it. Use when someone says they want to make a game, build a game, make an isometric/tile/city-builder/idle/incremental game, or describes a game idea and wants it to exist ("a game where you rebuild a…
web-game-development
Implement and optimize browser games using Phaser, Three.js, React Three Fiber, Babylon.js, or PlayCanvas with responsive input, asset loading, rendering, and browser playtests. Use for JavaScript or TypeScript game projects.
bevy-wasm-webgpu
Use when targeting Bevy 0.19 at wasm32-unknown-unknown, choosing the webgl2 or webgpu feature, generating browser glue with wasm-bindgen, using a wasm-release profile, or debugging canvas startup and asset HTTP 404s.