Borrowing it
Nothing to install: this file belongs to Koukyosyumei/h5i-db. 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/Koukyosyumei/h5i-db/main/AGENTS.mdgit clone --depth 1 https://github.com/Koukyosyumei/h5i-dbWrote 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/koukyosyumei/h5i-db/agents-md)<a href="https://agentmods.dev/instructions/koukyosyumei/h5i-db/agents-md"><img src="https://agentmods.dev/badge/instructions/koukyosyumei/h5i-db/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/koukyosyumei/h5i-db/agents-md"><img src="https://agentmods.dev/badge/instructions/koukyosyumei/h5i-db/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 | $0.01313 | $0.01313 |
| Opus 5.5 | $0.00525 | $0.00525 |
| Sonnet 5.5 | $0.00263 | $0.00263 |
| Haiku 4.5 | $0.00131 | $0.00131 |
Grade A, and why
h5i-db 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 14d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- h5i-ctx2img AGENTS.md — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Persona
At the start of a session, read PERSONA.md at the repo root (if present) and follow it as your standing working style. Do not read other files under the profile's persona source directory — PERSONA.md is the resolved, per-env brief.
h5i Integration
This repository uses h5i — auditable workspaces for AI coding agents.
Codex should use h5i recall context as shared cross-session memory and h5i capture commit to record AI provenance on code commits.
Workflow
At the start of a non-trivial task, check the current goal/pin, then (re)set it:
h5i recall context goal # prints the goal + warns if context is PINNED to a stale branch
h5i recall context init --goal "<one-line task summary>"
Run init even if a workspace already exists — it is idempotent and just
updates the goal in place (keeping the context branch and milestones). A session
often resumes with a stale goal from a previous task; always re-point it at
what you are doing now instead of skipping init because a workspace exists. If
context goal reports the context is pinned to a branch other than the
current git branch, run h5i recall context unpin to resume branch tracking.
While working:
h5i hook codex sync # after a burst of reads/edits — auto-traces OBSERVE/ACT and mines THINK/NOTE from your transcript
You do not need to emit OBSERVE / THINK / ACT trace entries by hand —
h5i hook codex sync (and h5i hook codex finish) derives them from the
Codex session JSONL. The only trace you should write directly is an explicit
flag a reviewer must see immediately:
h5i recall context trace --kind NOTE "TODO: … / LIMITATION: … / RISK: …"
After a logical milestone:
h5i hook codex finish --summary "<milestone summary>"
Code commits
git add <exact paths>
h5i capture commit -m "…" --agent codex
When h5i hook setup --write --target codex has installed the Stop hook,
h5i hook codex finish records the raw human prompt from the Codex session JSONL.
--intent remains a fallback for CI/scripts/manual commits where no Codex
session sync runs.
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.
- 14d ago First seen · 112 lines · 1,313 tokens per session scan A a253247495e9
h5i-db AGENTS.md is an instructions file published in the GitHub repository Koukyosyumei/h5i-db (34 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 1,313 tokens to every session, about $0.0053 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 2026-10-02.
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.
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.
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).