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/senna-lang/herdr-agent-usage/agents-mdgit clone --depth 1 https://github.com/senna-lang/herdr-agent-usageWrote 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/senna-lang/herdr-agent-usage/agents-md)<a href="https://agentmods.dev/instructions/senna-lang/herdr-agent-usage/agents-md"><img src="https://agentmods.dev/badge/instructions/senna-lang/herdr-agent-usage/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 | $0.00784 | $0.00784 |
| Opus 5 | $0.00392 | $0.00392 |
| Sonnet 5 | $0.00157 | $0.00157 |
| Haiku 4.5 | $0.00078 | $0.00078 |
Grade A, and why
herdr-agent-usage 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 4d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Instructions
Scope
These instructions apply to the entire repository. Treat the rules below as architectural constraints, not preferences.
Provider Extensibility
- The set of providers is open-ended. Assume that providers will be added, removed, or changed.
- Provider-neutral code MUST NOT depend on the current provider count or duplicate the provider list outside the canonical registry.
- A provider implementation MUST conform to the shared provider contracts and register through the same mechanism as every other provider.
- Provider-specific code MAY translate authentication, session, transcript, model, or API formats into shared domain types. It MUST NOT redefine shared domain behavior.
Provider Symmetry
- Shared code MUST interact with every provider through the same provider-neutral contracts.
- Shared code MUST operate on common domain types rather than branch on provider names, model names, or vendor-specific types.
- No provider may receive a privileged path through shared layers. A change of provider must change the adapter and its data, not the surrounding architecture.
- If a requirement applies across providers, add it to the shared contract. If it exists only because of an external provider format or capability, contain it within that provider's adapter.
- Provider adapters may differ internally only where their external systems differ. Those differences MUST end at the adapter boundary.
Directory and Package Boundaries
- Treat each directory as an architectural module and preserve the repository's dependency direction.
- This repository is written in Go. A package's exported identifiers are its public API; unexported identifiers are implementation details. Consumers MUST depend on the package API rather than another package's implementation details.
- Provider packages MUST NOT import one another. Behavior shared by multiple providers belongs in a provider-neutral package at the appropriate dependency layer.
- The Go
internalvisibility boundary and every lint rule configured in.golangci.ymlare mandatory. - Do not bypass a boundary with deep imports, duplicate implementations, or convenience dependencies. If the desired dependency violates the graph, move the shared abstraction to the correct layer instead.
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.
- 4d ago First seen · 59 lines · 784 tokens per session scan A 887858de4c4d
herdr-agent-usage AGENTS.md is an instructions file published in the GitHub repository senna-lang/herdr-agent-usage (28 stars, last pushed today), licensed MIT. It adds 784 tokens to every session, about $0.0039 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 2026-08-30.
Other instructions, from other repositories
collie CLAUDE.md
Claude Code instructions for AltanS/collie, covering claude.md — working agreement for this repo, decision records — read before reopening a settled question, versioning — mandatory, build / run (operational facts that are easy to forget) and linting — one linter, one config.
collie AGENTS.md
AGENTS.md instructions for AltanS/collie: The working agreement for this repo lives in CLAUDE.md — read it before changing anything. This file exists so agents that look for AGENTS.md find it too; there is one set of rules, not two, so nothing is restated here.
herdr-sidebar CLAUDE.md
Instructions for alexarthurs/herdr-sidebar, covering herdr-sidebar monorepo, build / test / lint, plugin dev workflow, windows caveats (verified against herdr 0.7.1 and 0.8.x) and release flow (verified for v0.7.0).
herdr-cache-alert CLAUDE.md
Instructions for AltanS/herdr-cache-alert, covering claude.md — working agreement for this repo, the claim contract — mandatory, versioning — mandatory, build / run and architecture — the four layers.
herdr-extensions CLAUDE.md
Instructions for vonzelle-vzt/herdr-extensions, covering claude.md — herdr-extensions, what this is, repository map, 🔴 the five things that fail silently and conventions.
herdr-agent-watcher AGENTS.md
AGENTS.md instructions for winoooops/herdr-agent-watcher, covering agents.md — agent watcher, project overview, runtime architecture, module map and build and test commands.