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/managedcode/prompterone/agents-mdgit clone --depth 1 https://github.com/managedcode/PrompterOneWrote 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/managedcode/prompterone/agents-md)<a href="https://agentmods.dev/instructions/managedcode/prompterone/agents-md"><img src="https://agentmods.dev/badge/instructions/managedcode/prompterone/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 | $0.19178 | $0.19178 |
| Opus 5 | $0.09589 | $0.09589 |
| Sonnet 5 | $0.03836 | $0.03836 |
| Haiku 4.5 | $0.01918 | $0.01918 |
Grade A, and why
PrompterOne 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 — 658 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Project: PrompterOne
Stack: .NET 10, Blazor WebAssembly, Razor Class Library, TUnit, bUnit, Playwright
Current Shape
PrompterOne is a standalone browser-first WebAssembly app.
src/PrompterOne.Webis the only runnable host.src/PrompterOne.Sharedcontains routed Razor UI, exactdesignstyling, and browser interop.src/PrompterOne.Corecontains TPS, RSVP, preview, workspace, media-scene, and streaming domain logic.tests/contains all automated test projects.- The shipped Blazor UI under
src/PrompterOne.Sharedis the visual and interaction source of truth; do not keep or restore a separate repo-localdesign/prototype tree.
There is no backend in the runtime shape. The app must boot directly in the browser from the WebAssembly host.
Rule Precedence
- Read the solution-root
AGENTS.mdfirst. - Read the nearest local
AGENTS.mdfor the area you will edit. - Apply the stricter rule when both files speak to the same topic.
- Local
AGENTS.mdfiles may refine or tighten root rules, but they must not silently weaken them. - If a local rule needs an exception, document it explicitly in the nearest local
AGENTS.md, ADR, or feature doc.
Conversations (Self-Learning)
Learn the user's stable habits, preferences, and corrections. Record durable rules here instead of relying on chat history.
Before doing any non-trivial task, evaluate the latest user message.
If it contains a durable rule, correction, preference, or workflow change, update AGENTS.md first.
If it is only task-local scope, do not turn it into a lasting rule.
Update this file when the user gives:
- a repeated correction
- a permanent requirement
- a lasting preference
- a workflow change
- a high-signal frustration that indicates a rule was missed
Extract rules aggressively when the user says things equivalent to:
- "never", "don't", "stop", "avoid"
- "always", "must", "make sure", "should"
- "remember", "keep in mind", "note that"
- "from now on", "going forward"
- "the workflow is", "we do it like this"
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 · 658 lines · 19,178 tokens per session scan A 50286f349aa6
PrompterOne AGENTS.md is an instructions file published in the GitHub repository managedcode/PrompterOne (42 stars, last pushed 3mo ago), licensed MIT. It adds 19,178 tokens to every session, about $0.0959 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 2026-09-03.
Other instructions, from other repositories
BlazorBindings.Maui AGENTS.md
AGENTS.md instructions for Dreamescaper/BlazorBindings.Maui, covering mobile guidelines, platform, razor and component conventions and blazor bindings generation.
Connapse CLAUDE.md
Claude Code instructions for Destrayon/Connapse, covering claude.md, build & run, build, run web app (requires backing services) and full stack via docker.
Hosted_Agents_Workshop_dotNET AGENTS.md
Instructions for microsoft/Hosted_Agents_Workshop_dotNET, covering agents.md, repository purpose, general rules, documentation rules and code and build rules.
vela-skill AGENTS.md
AGENTS.md instructions for dbhq-uk/vela-skill, covering agents.md, what this is, layout, the three constraints that define this tool and why razor works here and nowhere else.
KittyClaw AGENTS.md
AGENTS.md instructions for Ekioo/KittyClaw, covering kittyclaw — agent guide, run, → http://localhost:5230, debug instance (isolated) and repository layout.
KittyClaw CLAUDE.md
Claude Code instructions for Ekioo/KittyClaw, a project described as: A kanban board for managing projects with tickets, columns, labels, and activity tracking — designed to be driven by AI agents via its API.