Borrowing it
Nothing to install: this file belongs to topheman/effect-viz. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/topheman/effect-viz/master/AGENTS.mdgit clone --depth 1 https://github.com/topheman/effect-vizWrote 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/topheman/effect-viz/agents-md)<a href="https://agentmods.dev/instructions/topheman/effect-viz/agents-md"><img src="https://agentmods.dev/badge/instructions/topheman/effect-viz/agents-md/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/instructions/topheman/effect-viz/agents-md"><img src="https://agentmods.dev/badge/instructions/topheman/effect-viz/agents-md.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 | $0.01047 | $0.01047 |
| Opus 5.5 | $0.00419 | $0.00419 |
| Sonnet 5.5 | $0.00209 | $0.00209 |
| Haiku 4.5 | $0.00105 | $0.00105 |
Grade A, and why
effect-viz 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 1mo 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
EffectViz
A web-based visualizer for Effect.ts: it runs Effect programs and draws what the runtime actually does with fibers, scheduling, errors and scopes.
You can read the project intent here.
How We Work
We pair on this project. I am here to learn Effect deeply, and you write the implementation. Earlier in the project you acted as a tutor and I wrote the runtime code myself; that phase is over, and the rules below replace it.
- Explain the concept before you build. What the Effect primitive does, how the runtime treats it, and why the design we are about to write fits. Diagrams, timelines and mental models are welcome.
- Explain what you built afterwards. Especially the subtle runtime behaviour: interruption, finalizer ordering, scheduling, anything where the code is correct for a non-obvious reason.
- Ask before large refactors. Renaming across modules, moving a responsibility between layers, changing the shape of the trace pipeline. Small local cleanups as you go are fine.
- Prefer idiomatic Effect. If there is a combinator for what we are hand rolling, say so.
- Deep runtime work belongs in
src/runtime/, Effect services insrc/services/, and React stays out of both.
Trace Event Model
type TraceEvent =
| { type: "effect:start"; id: string; label: string }
| { type: "effect:end"; id: string; result: "success" | "failure" }
| { type: "fiber:fork"; fiberId: string; parentId?: string }
| { type: "fiber:end"; fiberId: string }
| { type: "fiber:interrupt"; fiberId: string }
| { type: "fiber:suspend"; fiberId: string; duration: number }
| { type: "sleep:end"; fiberId: string }
Context Recovery (For Fresh Sessions)
Invoked by the /resume skill (Claude Code) at the start of a fresh session.
ONLY read these files if the user explicitly says we're continuing the workshop:
MEMORY.md⭐ START HERE- Current phase and progress
- What's completed, what's next
- Key files and learning outcomes
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.
- 1mo ago Changed · +4 lines · +41 tokens per session e13f9b273e25
- 2mo ago Changed · -23 lines · -234 tokens per session 7fffd6e67d6e
- 2mo ago First seen · 129 lines · 1,240 tokens per session scan A 7493eae38c21
effect-viz AGENTS.md is an instructions file published in the GitHub repository topheman/effect-viz (54 stars, last pushed 7d ago), licensed MIT. It adds 1,047 tokens to every session, about $0.0042 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 2026-08-30.
effect-viz AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| effect-viz AGENTS.mdtopheman/effect-viz | Instructions file | 54 | 7d ago | MIT | A | 1,047 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |