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/ensemblr-hq/ensemblr/agents-mdgit clone --depth 1 https://github.com/ensemblr-hq/ensemblrWrote 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/ensemblr-hq/ensemblr/agents-md)<a href="https://agentmods.dev/instructions/ensemblr-hq/ensemblr/agents-md"><img src="https://agentmods.dev/badge/instructions/ensemblr-hq/ensemblr/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 5.1 | $0.04131 | $0.04131 |
| Opus 5 | $0.02065 | $0.02065 |
| Sonnet 5 | $0.00826 | $0.00826 |
| Haiku 4.5 | $0.00413 | $0.00413 |
Grade A, and why
ensemblr 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 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 — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Instructions
These instructions apply to this repository.
Project Naming
- This project was previously called
piductor, thenEnsemble. If agents find references topiductororEnsemblein code, documentation, branches, commits, issues, or planning notes, interpret them as references toEnsemblrunless the local context clearly says otherwise. The current product name isEnsemblr(domainensemblr.dev).
App Scaffolding Requires Current Official Docs
When scaffolding an app, project, framework integration, SDK integration, CLI setup, or cloud-service setup, agents must not rely on training data, memory, or recalled commands.
Required workflow:
- Inspect the local repo first so generated files and commands fit the existing project direction.
- Use Context7 MCP before selecting install steps, package names, CLI flags, templates, or generated-file structure.
- Start with
resolve-library-idfor the relevant library, framework, SDK, CLI, or cloud service unless the exact Context7 library ID is already known. - Call
query-docswith the selected library ID and the full scaffolding question. - If Context7 is unavailable, incomplete, or lacks the relevant tool, check the current official documentation online.
- Prefer official install directions, official starter templates, and official CLI tools such as documented
create,init, or generator commands. - Do not invent or guess package names, versions, CLI flags, templates, config keys, or setup steps.
- If official docs and local repo conventions conflict, preserve local conventions where possible and call out the tradeoff before making a risky change.
- In the final response, mention the documentation source and the exact official command or CLI path used.
Scaffold provenance guardrail:
- Do not hand-author generated app structure from memory when an official generator exists.
- Run the official generator in
.context/or another disposable directory first, then copy or adapt from that generated output. - If the generator conflicts with npm, hooks, existing files, or other repo policy, stop and explain the conflict before choosing a workaround.
- Record scaffold provenance in the final response or a tracked audit note: documentation source, exact generator command, generated files used, and every intentional deviation.
- Treat manually added package names, versions, config keys, templates, or generated-file structure as invalid unless they are directly backed by current official docs, generator output, or an explicit user decision.
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 · 158 lines · 4,131 tokens per session scan A 11cf4292bb56
ensemblr AGENTS.md is an instructions file published in the GitHub repository ensemblr-hq/ensemblr (7 stars, last pushed yesterday), licensed Apache-2.0. It adds 4,131 tokens to every session, about $0.0207 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
outline-apps AGENTS.md
AGENTS.md instructions for OutlineFoundation/outline-apps, covering welcome to the outline monorepo!, repository structure, the npm run action command, common actions and other useful commands.
outline-apps CLAUDE.md
Claude Code instructions for OutlineFoundation/outline-apps: This project uses AGENTS.md instead of CLAUDE.md.
repoprompt-ce AGENTS.md
AGENTS.md instructions for repoprompt/repoprompt-ce, covering agent notes, contribution preflight, run, debug and uncoordinated equivalents.
diri AGENTS.md
AGENTS.md instructions for cristicretu/diri, covering diri repository instructions, scope, completed remote architecture baseline, rust workspace map and remote architecture invariants.
tuicommander AGENTS.md
AGENTS.md instructions for sstraus/tuicommander, covering tuicommander — project rules, doc sync, tests, web-ui testing with agent-browser (browser mode, not tauri) and visual.
clave CLAUDE.md
Claude Code instructions for codika-io/clave, covering clave, commands, architecture, conventions and signing and notarization.