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/hazelnutparadise/insyra/agents-mdgit clone --depth 1 https://github.com/HazelnutParadise/insyraWrote 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/hazelnutparadise/insyra/agents-md)<a href="https://agentmods.dev/instructions/hazelnutparadise/insyra/agents-md"><img src="https://agentmods.dev/badge/instructions/hazelnutparadise/insyra/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 | $0.05377 | $0.05377 |
| Opus 5 | $0.02688 | $0.02688 |
| Sonnet 5 | $0.01075 | $0.01075 |
| Haiku 4.5 | $0.00538 | $0.00538 |
Grade A, and why
insyra 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 6d 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 — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file is the primary guidance for AI coding agents working in this repository. CLAUDE.md re-exports it via @AGENTS.md.
What This Repo Is
Insyra (github.com/HazelnutParadise/insyra) is a Go data analysis library (v0.3.x, "Huashan") providing:
DataListandDataTableas the core data structures- CCL (Column Calculation Language) — a domain-specific expression language for column transforms
- A CLI/REPL (
insyrabinary) built with Cobra - Sub-packages for stats, plotting, LP, Python interop, parallel processing, file I/O, etc.
Required artifacts
Each entry says when reading it stops being optional. That trigger is the part that only exists here — the files describe their own contents.
ENG.md— the project's standing technical decisions: architecture, test seams, the precision contract, the measured thresholds, the assumptions everything rests on. Read it before changing architecture, choosing a test seam, deciding what precision something runs at, or writing a migration. Do not re-derive any of it from scratch; if a decision there is wrong, change it there.delivery-status.md— where the project currently stands: phase, blockers, next output, next ticket. Read it first on arrival. It is deltas only, not a roadmap or a changelog.openspec/changes/— the tickets. Pick up anything whose blockers are all done; the milestone order indelivery-status.mdcarries the blocking edges, because OpenSpec has none between changes. Completed changes live inarchive/.
Change Workflow — OpenSpec (required)
Every non-trivial change goes through the OpenSpec workflow. This repo is
OpenSpec-initialized (see openspec/). Do NOT implement a feature, breaking
change, new package, or substantial fix straight into the code — drive it
through a change first:
- Propose — create the change (proposal + spec deltas + tasks) under
openspec/changes/<change-id>/(openspec-propose/openspec-new-change). - Apply — implement the tasks (
openspec-apply-change). - Verify — confirm the implementation matches the artifacts
(
openspec-verify-change). - Archive — once the change is implemented and merged, archive it into
openspec/changes/archive/(openspec-archive-change). Completed changes must be archived, not left sitting inopenspec/changes/.
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.
- 6d ago First seen · 278 lines · 5,377 tokens per session scan A a9778431df2c
insyra AGENTS.md is an instructions file published in the GitHub repository HazelnutParadise/insyra (56 stars, last pushed today), licensed MIT. It adds 5,377 tokens to every session, about $0.0269 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 2026-08-30.
Other instructions, from other repositories
oh-my-posh copilot-instructions.md
Copilot instructions for JanDeDobbeleer/oh-my-posh: All agent guidance for this repository lives in AGENTS.md: project overview, key commands, architecture orientation, coding and commit conventions, skills, and the project-knowledge workflow. Follow it in full.
chatgpt-cli AGENTS.md
AGENTS.md instructions for kardolus/chatgpt-cli, covering agents.md, 1) repo map (where things usually live), 2) build & test workflow (use makefile first), 3) go version and 4) testing expectations (required).
Better-Fullstack AGENTS.md
AGENTS.md instructions for Marve10s/Better-Fullstack, covering guidelines, web ui, workflow and bun.
bex CLAUDE.md
Claude Code instructions for bex-co/bex, covering claude.md, repo map, commands, local cluster workflow and environment variables.
bitbucket-cli AGENTS.md
AGENTS.md instructions for avivsinai/bitbucket-cli, covering agents.md and codex notes.
second-brain CLAUDE.md
Claude Code instructions for henrydaum/second-brain, covering second brain — architecture notes, ⚡ the kernel (read first), the layout (trees.py), what ships in the app's tree (bundled/) and the kernel boundary (the one rule).