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/sentientui/mcp/agents-mdgit clone --depth 1 https://github.com/SentientUI/mcpWhat 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 | $0.01603 | $0.01603 |
| Opus 5 | $0.00801 | $0.00801 |
| Sonnet 5 | $0.00321 | $0.00321 |
| Haiku 4.5 | $0.00160 | $0.00160 |
Grade A, and why
mcp 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 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SentientUI — AI Agent Guide
SentientUI is a UI personalization platform that assigns visitors to variant components and reorders page sections per persona. The MCP gives agents read + limited write access to project data.
Key Concepts
Persona / Cluster — visitors are clustered by behavior into labeled groups. A reliability_score (0–1) measures confidence in the assignment. Low reliability means the engine won't personalize for that session even if a cluster is assigned.
Variant — a version of an adaptive component. There are two kinds, and the difference matters:
- Code-native variants are declared in the customer's code (
<Adaptive variants={{…}}>). They register automatically the first time the SDK requests an assignment after deploy, and they go live immediately — there is no draft step and nocreate_variantcall. Their content lives in the repo, not in SentientUI. - No-code / managed variants have no code; their content is stored on the SentientUI API (dashboard WYSIWYG,
<AdaptiveText>, orcreate_variant). These start as draft aftercreate_variantand must be activated from the dashboard before traffic is assigned. There is no MCP tool to activate or resume variants.
Only call create_variant for the no-code path. If the user is writing (or you are writing) the variant in code, do not call create_variant — deploying the code registers it.
Guardrail — automatic safety circuit that pauses variants whose CVR drops below threshold. list_guardrail_events shows what's been paused. Pausing via pause_variant is irreversible via MCP (no resume tool).
Shadow mode — project-level flag (toggled in dashboard settings). When ON: personalization is computed and logged but visitors receive the default layout/variant. Use it to validate the algorithm before committing to live changes.
Insights — AI-generated. Two tiers: narrator observations (generation requires Starter+; Free plans can only view already-stored bullets) + advisor recommendations (Growth tier). Insights go stale after 6 hours. Always check isStale before presenting them.
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 First seen · 89 lines · 1,603 tokens per session scan A 8d646a30a3cd
mcp AGENTS.md is an instructions file published in the GitHub repository SentientUI/mcp (0 stars, last pushed 5d ago), licensed MIT. It adds 1,603 tokens to every session, about $0.0080 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
llm-context.py CLAUDE.md
Instructions for cyberchitta/llm-context.py, covering claude.md, working notes (gitignored) and draining the field notes.
openrouter-mcp-multimodal AGENTS.md
Instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).
seekstone CLAUDE.md
Instructions for shaqmughal/seekstone, covering claude.md, what this repo is, commands, the harness itself (run after npm install) and architecture.
Plonk AGENTS.md
Instructions for ostapondo/Plonk, covering agent rules, layout, adding a module, build & verify and code style.
mcp-dockhand copilot-review.instructions.md
Instructions for strausmann/mcp-dockhand: When reviewing pull requests in this repository.
second-brain AGENTS.md
Instructions for LindaHaviv/second-brain, covering instructions for ai coding agents, what to read first, the rules (non-negotiable), common tasks, the sanctioned way and enforcement, not just instructions.