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/kabirnarang39/wardline/claude-mdgit clone --depth 1 https://github.com/kabirnarang39/wardlineWrote 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/kabirnarang39/wardline/claude-md)<a href="https://agentmods.dev/instructions/kabirnarang39/wardline/claude-md"><img src="https://agentmods.dev/badge/instructions/kabirnarang39/wardline/claude-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 | $0.01372 | $0.01372 |
| Opus 5 | $0.00686 | $0.00686 |
| Sonnet 5 | $0.00274 | $0.00274 |
| Haiku 4.5 | $0.00137 | $0.00137 |
Grade A, and why
wardline CLAUDE.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 6d 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wardline — Engineering Conventions
Wardline is an open source control-plane proxy that sits between AI agents and everything they call (MCP servers, LLM providers, other agents) — enforcing identity, policy, budget, and audit. Go, Apache 2.0.
These conventions apply to all code in this repo. Follow them exactly; they override default behavior.
Architecture: Clean Architecture, dependency rule inward
Four layers, dependencies point one direction only — outer depends on inner, never the reverse:
domain → entities + interfaces only. No I/O, no frameworks, no imports outside stdlib.
usecase → business logic (policy evaluation, budget checks, audit decisions).
Depends on domain interfaces, never on adapters or infra directly.
adapter → translates between usecase and the outside world (HTTP handlers,
YAML/OPA loaders, log writers). Implements domain interfaces.
infra → frameworks, network, filesystem, third-party SDKs. Wired at the
outermost edge only (cmd/wardline/main.go).
A file in domain/ or usecase/ that imports net/http, a YAML library, or any
adapter package is a violation — stop and fix the dependency direction, don't
add an exception.
SOLID, applied concretely
- Single Responsibility — one package, one reason to change. If a package handles both policy matching and audit logging, split it.
- Open/Closed (the one that matters most here) — every pluggable engine
(policy backend, identity issuer, budget meter) is a domain-defined
interface, and adding a new backend means adding a new adapter, never editing the usecase that consumes it. Concrete example:policy.Engineinterface has an OPA/Rego adapter today; Cedar arrives later as a second adapter, zero changes tousecase/policy_eval.go. - Liskov — any implementation of a domain interface must be swappable
without the caller changing behavior/assumptions. If a new
policy.Engineimpl needs the usecase to special-case it, the interface is wrong — fix the interface, not the caller. - Interface Segregation — small, single-purpose interfaces
(
policy.Evaluator,audit.Writer,budget.Meter) over one largeEnginegod-interface. Consumers depend only on the methods they call. - Dependency Inversion — usecases accept interfaces via constructor
injection; concrete adapters are wired only in
cmd/wardline/main.go. Neverimportan adapter package fromusecase/.
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.
- 6d ago First seen · 124 lines · 1,372 tokens per session scan A 72b2746aca1f
wardline CLAUDE.md is an instructions file published in the GitHub repository kabirnarang39/wardline (8 stars, last pushed 3d ago), licensed Apache-2.0. It adds 1,372 tokens to every session, about $0.0069 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
fold CLAUDE.md
Claude Code instructions for fold-run/fold, covering claude.md, what this is, commands, declarations rather than with the federation and architecture.
dingtalk-workspace-cli AGENTS.md
AGENTS.md instructions for DingTalk-Real-AI/dingtalk-workspace-cli, covering repository agent guide, build and test, command framework declaration, flag / help / schema homology and agent schema contract.
azure-sdk-for-go go-code.instructions.md
Instructions for Azure/azure-sdk-for-go: All code should follow the guidelines from the Azure Go SDK Guidelines. This document is a summary of the most important guidelines to follow when contributing to the Azure Go SDK.
gorest AGENTS.md
AGENTS.md instructions for pilinux/gorest, covering agents.md, project overview, build and run commands, build and tidy dependencies.
coral CLAUDE.md
Instructions for cdknorow/coral, covering claude.md - coral go, mission, testing, go unit tests and legacy parity tools (historical reference).
blueclaw AGENTS.md
AGENTS.md instructions for yeomyeonggeori/blueclaw, covering agents.md, core principles, single source of truth, working on this repository and branch names.