Borrowing it
Nothing to install: this file belongs to HiAgencia/hi-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/HiAgencia/hi-claude/main/AGENTS.mdgit clone --depth 1 https://github.com/HiAgencia/hi-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/hiagencia/hi-claude/agents-md)<a href="https://agentmods.dev/instructions/hiagencia/hi-claude/agents-md"><img src="https://agentmods.dev/badge/instructions/hiagencia/hi-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/hiagencia/hi-claude/agents-md"><img src="https://agentmods.dev/badge/instructions/hiagencia/hi-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 | $0.01629 | $0.01629 |
| Opus 5.5 | $0.00652 | $0.00652 |
| Sonnet 5.5 | $0.00326 | $0.00326 |
| Haiku 4.5 | $0.00163 | $0.00163 |
Grade A, and why
hi-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 19d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
hi-claude (plugin source)
hi-claude governs this work — the format, the practice, the retroactivity of every session. Its seven principles, their four axes and the hierarchy that settles conflicts between them are defined in
skills/memory-protocol/constitution.md, which the session hook injects when the user's global CLAUDE.md does not carry the principles block. Where form, criterion or scope is in doubt, hi-claude decides.
Claude Code plugin packaging the hi-claude working method: seven principles on four axes with the hierarchy that settles them, governed memory, a curated CLAUDE.md, a register of open work, every content with a declared destination instead of a new file, text that gets pruned when it stops being true, subagents that investigate and never decide, an inventory of what a project can use, a turn that does not end stale, and audits. This repo is BOTH the plugin and its marketplace.
Start here
docs/ESTADO.md— what exists: every hook, skill and auditor with what it guarantees, plus the contract gotchas that were measured rather than deduced.docs/ROADMAP.md— a pointer: open work for this plugin is kept in the maintainers' workspace, one level up, where both repos are visible. The runnable session-done criterion lives there, in its§0.docs/INDEX.md— everything else.
Project structure
.claude-plugin/ manifests (plugin.json + marketplace.json)
.gitattributes pins hooks/** -text — load-bearing, see Gotchas
LICENSE MIT, Hi Agencia
hooks/ hooks.json + run-hook.cmd (polyglot) + json-lib + one script per ROLE, named by
role because an event can carry more than one: PostToolUse has `tracker` (turn
bookkeeping) and `report-received` (a subagent's report just came back)
skills/ memory-protocol (+ constitution, references), roadmap (+ references),
work-protocol, delegation, seeding-doubts, heavy-runs, setup (+ templates es/en), audit
agents/ read-only auditors (CLAUDE.md, memory, organization, ROADMAP, inventory, currency)
BRAND/ Hi Agencia logo (white = dark mode, dark = light mode, used by README)
docs/ ROADMAP.md, ESTADO.md, INDEX.md
tests/ run-hook-tests.sh + fixtures/ (stdin payloads)
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.
- 19d ago Changed d73e0c786cce
- 20d ago First seen · 71 lines · 1,629 tokens per session scan A c7d3298aa03d
hi-claude AGENTS.md is an instructions file published in the GitHub repository HiAgencia/hi-claude (2 stars, last pushed 20d ago), licensed MIT. It adds 1,629 tokens to every session, about $0.0065 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 2026-09-28.
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).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.