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/waelmas/codeplow/agents-mdgit clone --depth 1 https://github.com/waelmas/codeplowWhat 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 | $0.03191 | $0.03191 |
| Opus 5 | $0.01596 | $0.01596 |
| Sonnet 5 | $0.00638 | $0.00638 |
| Haiku 4.5 | $0.00319 | $0.00319 |
Grade A, and why
codeplow 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 yesterday.
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 — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
codeplow - Agent Guide
This file gives AI coding agents (Claude Code, Cursor, Codex, etc.) the context they need to work in this repository.
What this repo is
codeplow is a plugin marketplace for AI coding agents. It bundles installable plugins (currently one: obsidian-kb) with native support for four platforms:
- Claude Code (
.claude-plugin/) - GitHub Copilot CLI — reuses Claude Code's manifests. Same
.claude-plugin/marketplace.json+.claude-plugin/plugin.json, samemarketplace add/plugin installcommand shape; only the binary name differs (copilotvsclaude). No separate.copilot-plugin/directory. Runtime distinction is theCOPILOT_CLI=1env var, which any future hooks can branch on to adapt output format. - Cursor (
.cursor-plugin/) - Codex CLI (
.codex-plugin/+.agents/plugins/)
Users install the marketplace once and get every plugin it contains.
Why the plugins here exist
Understanding the product intent matters when editing skills - every design choice traces back to one of these problems.
obsidian-kbfights two failure modes of AI coding workflows:- Context rot between sessions. Long sessions degrade - decisions made at token 2,000 get lost by token 50,000; starting a new session resets everything, including the decisions. The
/kb-offboard→/kb-onboardloop externalizes the thread into a markdown handoff so new sessions start fresh and briefed. - Doc rot inside the repo. Markdown drifts from code, especially on AI-written projects where the agent generates docs that match a commit and nothing updates them later.
/kb-initand/kb-auditbuild/refresh a KB from live code and flag every stale claim in existing markdown withfile:lineevidence.
- Context rot between sessions. Long sessions degrade - decisions made at token 2,000 get lost by token 50,000; starting a new session resets everything, including the decisions. The
- Category positioning. Not a vector DB (that's claude-mem, Mem0, Zep - different problem: chat retrieval). Not a CLAUDE.md replacement (too shallow by design). Closest sibling is Cline Memory Bank - also markdown - but Cline-only, fixed schema, no audit. See the top-level
README.md"How it compares" section for the full matrix. - Ownership principle. Vaults are plain markdown inside the user's project by default. Committable, grep-able, editable by hand, zero lock-in. This is load-bearing - if you're changing a skill and the change pushes content into a proprietary format or an opaque store, stop and reconsider.
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.
- yesterday First seen · 194 lines · 3,191 tokens per session scan A 8823718c1049
codeplow AGENTS.md is an instructions file published in the GitHub repository waelmas/codeplow (8 stars, last pushed 4mo ago), licensed MIT. It adds 3,191 tokens to every session, about $0.0160 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
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.
buildNext
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
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, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit 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.
langchain 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.