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/dragginzgame/canic/agents-mdgit clone --depth 1 https://github.com/dragginzgame/canicWrote 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/dragginzgame/canic/agents-md)<a href="https://agentmods.dev/instructions/dragginzgame/canic/agents-md"><img src="https://agentmods.dev/badge/instructions/dragginzgame/canic/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 | $0.03079 | $0.03079 |
| Opus 5 | $0.01540 | $0.01540 |
| Sonnet 5 | $0.00616 | $0.00616 |
| Haiku 4.5 | $0.00308 | $0.00308 |
Grade A, and why
canic 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 today.
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 — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file is normative for automated agents and contributors. If code conflicts with this file, the code is wrong.
Session Handoff
- At the start of a new session, read
docs/status/current.mdfirst. Treat it as the compact handoff and avoid replaying old chat history unless needed.
Repository Scope
- Automated edits are restricted to this Canic repository. Do not modify, format, generate files in, or otherwise mutate sibling or external repositories, even when a Canic design names a downstream integration.
- Treat every repository outside the Canic repository root as read-only unless the maintainer explicitly authorizes creation of a named new repository at an exact target path. That exception permits creating and bootstrapping only the named repository for the stated task; if the target already contains meaningful repository state, stop and request confirmation before modifying it.
- A request to inspect, review, audit, diagnose, design for, or give feedback about another repository never authorizes edits there. Record or report downstream work that remains instead of implementing it unless the maintainer separately gives explicit mutation authority for that existing repository.
CI, Git, and Deployment
- Follow
docs/governance/ci-deployment.md; it is the authoritative policy for commands, git boundaries, versioning, release, network selection, and automation language rules. Do not duplicate its rules here. - Release-blocking guards must validate executable behavior, structured records, exact identifiers, hashes, versions, schemas, or document/link presence. Do not make a release depend on exact explanatory prose, sentence wording, line wrapping, illustrative values, heading inventories, or the absence of ordinary narrative. When a fact needs machine enforcement, give it a machine-readable field instead of parsing prose.
- Development and release preflight must not require contributors to add, remove or rotate status markers by hand. The governed version-bump transaction owns the exact validated-release marker after validation succeeds; a missing, stale or repeated development marker must not block or invalidate an otherwise valid source candidate.
- Every successful one-shot
make release-*flow must cross the post-release Cargo cleanup boundary defined by the authoritative CI/deployment policy.
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.
- today Changed · +6 lines · +76 tokens per session e0f9c67faea7
- yesterday Changed · +13 lines · +164 tokens per session 83b0680463dd
- 6d ago First seen · 225 lines · 2,839 tokens per session scan A 4a60be993bc6
canic AGENTS.md is an instructions file published in the GitHub repository dragginzgame/canic (10 stars, last pushed yesterday), licensed MIT. It adds 3,079 tokens to every session, about $0.0154 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
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
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.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
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.