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/sbenson2/gamelens/claude-mdgit clone --depth 1 https://github.com/sbenson2/GameLensWrote 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/sbenson2/gamelens/claude-md)<a href="https://agentmods.dev/instructions/sbenson2/gamelens/claude-md"><img src="https://agentmods.dev/badge/instructions/sbenson2/gamelens/claude-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 5.1 | $0.01343 | $0.01343 |
| Opus 5 | $0.00672 | $0.00672 |
| Sonnet 5 | $0.00269 | $0.00269 |
| Haiku 4.5 | $0.00134 | $0.00134 |
Grade A, and why
GameLens CLAUDE.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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GameLens Monorepo
A game designer AI lens for programmers. Free and open source MCP server,
MIT licensed. One tool (lens) + a curated design-doc knowledge base as MCP
resources. Design philosophy only — no engine docs.
v3.0.0 (2026-08-05): renamed from GameCodex (gamecodex on npm) and
went design-philosophy-only — the 29 engine-doc modules (~950 docs), the
module system (GAMEDEV_MODULES), and engine detection were removed; that
content lives in the 2.x tags. v2.0.0 (2026-08-03) was the single-tool
rewrite; v1.0.1 was the final release of the old five-tool surface.
Repo lives at ~/Developer/GameCodex (dir rename to GameLens pending).
Monorepo Structure
GameLens/
├── packages/
│ ├── server/ <- the MCP server (the product) — SPEC.md is the source of truth
│ └── site/ <- marketing site (Next.js) — STALE: predates the lens direction
├── package.json <- npm workspaces root
└── CLAUDE.md <- This file
Commands (run from root)
npm install # install all workspace deps
npm run build # build server (clean dist + tsc)
npm run dev # server watch mode
npm start # start MCP server
npm run typecheck # tsc --noEmit on server
npm test # run all tests
Server (packages/server/)
- The one tool:
src/tools/lens.ts— paramssituation?/lens?/doc?/section?, no action routing. Situation → matched lenses + top matching KB docs; lens id → that lens; doc id → the doc (TOC-gated over 25KB,sectionextracts one heading); nothing → catalog. Precedence: doc > lens > situation. - Doc search:
src/core/search.ts— TF-IDF engine (synonyms, stemming, title boosts; zero deps) indexed over the design docs at startup, powering the in-lens knowledge-base block. - Lens library:
src/core/lenses.ts— 15 lenses (Cerny, MDA, Meier, Swink, juice, flow/Celeste, Fan, kishōtenketsu, core loops, Yu, Valve/RITE, SDT/Bartle, Sirlin/Schreiber, Koster, BotW emergence) +matchLenses/findLens. Pure data + pure functions, fully tested. - Registry:
src/tool-registry.ts— concurrency cap, analytics, never-throw with MCPisError. - Knowledge base:
docs/— ~10 curated game-design docs (genre reference, game feel craft, fundamentals, emergent/puzzle design, level design, postmortems, difficulty & accessibility, resource maps) served as MCP resources (gamelens://docs/{id}) viasrc/core/docs.ts. Design content only — engine/implementation content is out of scope. - Analytics:
src/analytics.ts— local-only daily JSON aggregates (~/.gamelens/analytics/, disable withGAMELENS_ANALYTICS=false). - CLI:
gamelens(serve) /gamelens init(write MCP config) /gamelens status. - Runtime deps:
@modelcontextprotocol/sdk,zod— nothing else.
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 · 104 lines · 1,343 tokens per session scan A e15286924b34
GameLens CLAUDE.md is an instructions file published in the GitHub repository sbenson2/GameLens (1 stars, last pushed 1mo ago), licensed MIT. It adds 1,343 tokens to every session, about $0.0067 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
claudemon CLAUDE.md
Instructions for zamarrowski/claudemon, covering ai agent guidelines, project shape, general guidelines, general rules and guards & defensive code.
unity-code-style-guide AGENTS.md
Instructions for krogh-jacobsen/unity-code-style-guide, covering agents.md — unity 6 c, project setup — edit this block, never do these — they corrupt the project, deprecated in unity 6 and if you read nothing else.
nes-php-glfw copilot-instructions.md
Instructions for oliverearl/nes-php-glfw, covering github copilot development guidelines for nes emulator, agent document source of truth, project overview, code style & standards and documentation.
game-and-watch-retro-go-sd CLAUDE.md
Claude Code instructions for sylverb/game-and-watch-retro-go-sd, covering claude.md, what this project is, build / flash workflow, architecture and three storage tiers, one elf.
base-building-trap-defense-design-agent-skill CLAUDE.md
Instructions for dungnotnull/base-building-trap-defense-design-agent-skill, covering claude.md — skill 250: base-building-trap-defense-design, skill identity, problem this skill solves, harness flow summary and sub-skills.
trident-mcp AGENTS.md
Instructions for mordor-forge/trident-mcp, covering agents.md, what this is, build and test, single-file verification and e2e tests.