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/stelis-dev/say-ur-intent/agents-mdgit clone --depth 1 https://github.com/stelis-dev/say-ur-intentWrote 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/stelis-dev/say-ur-intent/agents-md)<a href="https://agentmods.dev/instructions/stelis-dev/say-ur-intent/agents-md"><img src="https://agentmods.dev/badge/instructions/stelis-dev/say-ur-intent/agents-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 | $0.04294 | $0.04294 |
| Opus 5 | $0.02147 | $0.02147 |
| Sonnet 5 | $0.00859 | $0.00859 |
| Haiku 4.5 | $0.00429 | $0.00429 |
Grade A, and why
say-ur-intent 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 3d 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 — 372 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file is the root operating contract for coding agents working in this repository. Read it from disk before every task.
Detailed policy files are binding when the task touches their boundary. Moving a
rule out of this root file does not make it optional or lower priority. The
primary detailed policy is docs/AGENT_DEVELOPMENT_POLICY.md.
Product Purpose
Say Ur Intent is a local-first toolkit that turns natural-language Sui DeFi
intent and structured Sui payment/action proposals into verified, AI-readable
evidence, and is designed to carry a reviewed request through to user-controlled
wallet signing and execution receipt evidence after Say Ur Intent independently
builds or verifies the transaction material. The current release implements
Sui mainnet evidence, local review, and signable account-bound swap review paths
for DeepBook and FlowX. Those paths build local unsigned transaction material
into a local material store, internally bind a Sui transaction digest to that
stored material, derive object ownership, quote/policy provenance,
human-readable review evidence, review-time simulation evidence, and a PTB
visualization from the same stored material and private review artifacts, and
emit a schema-validated wallet review contract on ready_for_wallet_review.
When every required evidence stage completes, the local review page can request
the only transaction-byte handoff path: a same-machine, digest-gated handoff
whose bytes must recompute to the reviewed commitment before the user signs in
their own wallet. After the page reports the signed transaction digest, the
review server re-reads Sui mainnet and records normalized chain receipt
evidence. The review page also displays the server-read chain
receipt facts inline, and a public Receipt Analytics page reads on-chain receipt
facts for any transaction digest, without adding signing or execution authority. MCP responses and ordinary review-session JSON never
expose transaction bytes, request wallet signatures, provide signing readiness,
or execute on the user's behalf.
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.
- 3d ago First seen · 372 lines · 4,294 tokens per session scan A d61c69c0b7b2
say-ur-intent AGENTS.md is an instructions file published in the GitHub repository stelis-dev/say-ur-intent (0 stars, last pushed 28d ago), licensed MIT. It adds 4,294 tokens to every session, about $0.0215 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
rugcheck-ai AGENTS.md
AGENTS.md instructions for MrWizardlyLoaf/rugcheck-ai, covering rugcheck ai — agent guide, connect (no install), tools, source & stack and self-host.
agent-q AGENTS.md
AGENTS.md instructions for stelis-dev/agent-q, covering agents.md, minimal product context, product boundary, 1. start from evidence and 2. think before coding.
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
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
AGENTS.md instructions for ostapondo/Plonk, covering agent rules, layout, adding a module, build & verify and code style.