Borrowing it
Nothing to install: this file belongs to schmitthub/clawker. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/schmitthub/clawker/main/.github/copilot-instructions.mdgit clone --depth 1 https://github.com/schmitthub/clawkerWrote 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/schmitthub/clawker/copilot-instructions)<a href="https://agentmods.dev/instructions/schmitthub/clawker/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/schmitthub/clawker/copilot-instructions/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/schmitthub/clawker/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/schmitthub/clawker/copilot-instructions.svg" alt="Reviewed on agentmods" width="80" 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 | $0.01398 | $0.01398 |
| Opus 5.5 | $0.00559 | $0.00559 |
| Sonnet 5.5 | $0.00280 | $0.00280 |
| Haiku 4.5 | $0.00140 | $0.00140 |
Grade A, and why
clawker copilot-instructions.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 1mo 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copilot code review instructions
You review pull requests for this repository. AGENTS.md at the repository
root, the package AGENTS.md files, and the Serena memories under
.serena/memories/ are the coding standard. This file
tells you what to look for first and how to write each comment.
Read the head branch of the pull request. Compare every added or changed line against the priorities below, in order.
Priority 1: lint suppression
Flag every added or changed lint suppression. One comment per occurrence.
Markers to find in the diff:
//nolintand// nolint(with or without a linter list)#nosec//lint:ignore- Changes to
exclusions,exclude, ornolintlintsettings in.golangci.yml
The repository rule (.serena/memories/conventions.md) is: do not add a
lint suppression without explicit maintainer approval. Correct the code so the
linter passes. An explanation text after the marker is not sufficient on its
own. In each comment:
- Quote the marker and the linter it silences.
- State that the rule requires maintainer approval.
- Propose the code change that removes the need for the suppression.
Priority 2: control plane servers and listeners
Applies to new or changed calls to grpc.NewServer, net.Listen,
net.ListenConfig, http.Server, and ListenAndServe in these paths:
controlplane/**internal/controlplane/**cmd/clawkercp/**clawkerd/**
The canonical authorization code is controlplane/auth:
auth.NewAuthInterceptorbuilds the interceptor from a Hydra introspector and a method-to-scope map.AuthInterceptor.UnaryInterceptor,AuthInterceptor.StreamInterceptor, andAuthInterceptor.GRPCServerOptionsattach it to a gRPC server.controlplane/server/grpc_stack.goshows the required chain order: recovery interceptor, then ready-gate interceptor, then auth interceptor.
Report each of these as a blocking finding:
- No auth. A gRPC server on the admin or agent surface without the
controlplane/authinterceptor chain. A hand-written token check, a header check, or a copy of the interceptor logic is not acceptable; the server must usecontrolplane/auth. - Reused auth material. A listener that loads certificate, key, or CA
files that belong to another lane, or that shares a
tls.Configwith another lane. Each listener has its own certificate lane in its own subpackage (controlplane/infracerts,controlplane/otelcerts,controlplane/sdscertsare the pattern). See "Why not otelcerts" incontrolplane/sdscerts/AGENTS.md. - mTLS without a pin. A listener that uses client certificates instead of
bearer tokens must set
ClientAuth: tls.RequireAndVerifyClientCertand pin the peer CN or SAN inVerifyPeerCertificate.clawkerd/listener.gois the reference. The pull request description must say why bearer authorization does not apply to that listener. - Crash path.
panic,log.Fatal, oros.Exiton the control plane boot or serve path, or a serve goroutine without arecover. See the CP failure rules incontrolplane/AGENTS.md. A degraded subsystem must emit a structured log line withevent=<subsystem>_unavailable.
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.
- 1mo ago First seen · 126 lines · 1,398 tokens per session scan A 8e73f8172c75
clawker copilot-instructions.md is an instructions file published in the GitHub repository schmitthub/clawker (58 stars, last pushed today), licensed MIT. It adds 1,398 tokens to every session, about $0.0056 per session on Opus 5.5. 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 2026-09-08.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.