Borrowing it
Nothing to install: this file belongs to e1024kb/wise-claude. 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/e1024kb/wise-claude/main/AGENTS.mdgit clone --depth 1 https://github.com/e1024kb/wise-claudeWrote 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/e1024kb/wise-claude/agents-md)<a href="https://agentmods.dev/instructions/e1024kb/wise-claude/agents-md"><img src="https://agentmods.dev/badge/instructions/e1024kb/wise-claude/agents-md/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/e1024kb/wise-claude/agents-md"><img src="https://agentmods.dev/badge/instructions/e1024kb/wise-claude/agents-md.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 | $0.00807 | $0.00807 |
| Opus 5.5 | $0.00323 | $0.00323 |
| Sonnet 5.5 | $0.00161 | $0.00161 |
| Haiku 4.5 | $0.00081 | $0.00081 |
Grade A, and why
wise-claude 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 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Shared contributor guidance for every coding harness working in wise-claude.
This file contains project instructions, not a loadable agent registry.
Keep harness-specific instructions in that harness's configuration file.
Repository and runtime
plugins/wise/is the canonical, hand-edited Wise plugin. The marketplace index at.claude-plugin/marketplace.jsonpoints to it. There is no build or generation step.- The workflow engine is Python 3.11+ and executes YAML v2 workflows. Its provider adapters support Claude, Codex, Cursor, Gemini and Grok. The main conversation's client and the provider running a child are separate choices.
- Read CONTRIBUTING.md and the relevant workflow documentation before changing the plugin. Consult the instructions within the affected subtree as well.
Code map
plugins/wise/skills/: skill entrypoints and skill-local resources.plugins/wise/references/: shared procedures. Change shared behavior here rather than duplicating instructions across skills.plugins/wise/agents/: SDLC role cards, catalogued in the plugin agent index.plugins/wise/workflows/: bundled workflow definitions, prompts and READMEs.plugins/wise/engine/wise_engine/: schema (defs.py), scheduling, execution, persisted state, preflight and provider adapters.plugins/wise/engine/tests/andplugins/wise/tests/: automated tests.plugins/wise/scripts/andplugins/wise/hooks/: helpers and plugin hooks.scripts/validate_repo.py: repository structure and documentation checks.docs/wise/: user and contributor reference documentation.
Workflow and interaction contracts
- The engine owns workflow scheduling, model/effort resolution and persisted state. The main harness calls its MCP tools or CLI, not workflow steps itself.
- Follow workflow host control for installation discovery, initialization, question routing and gates. Identify the active main client, its GUI/TUI surface and available question tools rather than inferring capabilities from the provider name.
- The main harness owns user interaction: prefer its permitted native control, then a usable rendered MCP form, then the documented main-harness text fallback. Never launch a separate terminal or system dialog as a fallback. Defaults and asynchronous display acknowledgements are not user answers.
- Children relay questions through Wise or their parent. Pass applicable project instructions and task constraints to delegated children; do not assume they inherit the main conversation. Preserve autonomous no-prompt rules and explicit consent gates defined by the invoked skill.
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 Changed · +3 lines · +54 tokens per session e2aa28a26d39
- 1mo ago Changed · +21 lines · +254 tokens per session 72c478fdee24
- 1mo ago Changed · -16 lines · -224 tokens per session 6a837978a6b7
- 1mo ago First seen · 57 lines · 723 tokens per session scan A 603b8c280f94
wise-claude AGENTS.md is an instructions file published in the GitHub repository e1024kb/wise-claude (5 stars, last pushed 7d ago), licensed MIT. It adds 807 tokens to every session, about $0.0032 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 2026-08-31.
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).
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.