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 skills add salazarsebas/Cougr --skill cougr-game-startergit clone --depth 1 https://github.com/salazarsebas/CougrWrote 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/salazarsebas/cougr/cougr-game-starter)<a href="https://agentmods.dev/skills/salazarsebas/cougr/cougr-game-starter"><img src="https://agentmods.dev/badge/skills/salazarsebas/cougr/cougr-game-starter/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/salazarsebas/cougr/cougr-game-starter"><img src="https://agentmods.dev/badge/skills/salazarsebas/cougr/cougr-game-starter.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00068 | $0.01458 |
| Opus 5.5 | $0.00027 | $0.00583 |
| Sonnet 5.5 | $0.00014 | $0.00292 |
| Haiku 4.5 | $0.00007 | $0.00146 |
Grade A, and why
cougr-game-starter 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 today.
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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cougr Game Starter
Build a new game as a small, shippable vertical slice. Treat cougr-core as the architectural foundation, not as decoration added after the game logic is already tangled.
Workflow
- Classify the game before writing code.
- Scaffold a minimal project and add
cougr-core. - Model the game state in ECS terms.
- Implement contract APIs as thin entrypoints over game logic.
- Add tests that prove the loop works.
- Leave the project with documentation that another engineer can extend.
Read bundled references as needed:
- Read references/bootstrap.md before creating or restructuring a project.
- Read references/patterns.md when deciding how to model entities, components, systems, and contract APIs.
- Read references/prototype-checklist.md before finishing work or when deciding what belongs in a first prototype.
Step 1: Classify The Game
Reduce the request to a concrete gameplay loop before creating files.
Capture:
- player count
- turn-based vs real-time tick updates
- hidden information vs fully public state
- win and loss conditions
- smallest playable loop
- one or two mechanics that make the prototype worth building
Prefer a narrow first milestone:
pong, not full sports simulationbattleshipplacement and attack loop, not matchmaking and rankings- one arena combat loop, not inventory, guilds, and tournaments at once
If the user asks for a large game, implement the thinnest coherent slice first and state that scope in the project README.
Step 2: Scaffold The Project
Scaffold with the cougr CLI. Do not hand-write the project layout, Cargo.toml, or a starter contract skeleton, cougr new already generates a canonical lib.rs / components.rs / systems.rs layout with a passing test suite, and hand-rolling one only reproduces what the CLI does correctly.
cargo install cougr-cli
cougr new <name> --template <template>
cd <name>
cargo test
What ships with it
3 files 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.
- today First seen · 169 lines · 68 tokens per session scan A 01140378a7c0
cougr-game-starter is a skill published in the GitHub repository salazarsebas/Cougr (53 stars, last pushed 16d ago), licensed MIT. It adds 68 tokens to every session and 1,458 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-11-07.
cougr-game-starter compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| cougr-game-startersalazarsebas/Cougr | Skill | 53 | 16d ago | MIT | A | 68 | Claude Code, Codex |
| smart-contractsrylsherdamz-rgb/stellar-forge | Skill | 17 | 5d ago | MIT | A | 44 | Claude Code |
| cargo-fuzztrailofbits/skills | Skill | 8.0k | yesterday | CC-BY-SA-4.0 | A | 90 | Claude Code, Codex |
| rust-developmentnavikt/copilot | Skill | 60 | yesterday | MIT | A | 27 | Claude Code, Codex |
| cranposesamoylenkodmitry/Cranpose | Skill | 59 | yesterday | Apache-2.0 | A | 44 | Claude Code |
| et-test-writeFlameskyDexive/Legends-Of-Heroes | Skill | 936 | 1mo ago | MIT | A | 60 | Claude Code, Codex |
| mutation-testnwiizo/ccswarm | Skill | 156 | 24d ago | MIT | A | 25 | Claude Code |