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/lynxlangya/techne/claude-mdgit clone --depth 1 https://github.com/lynxlangya/techneWrote 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/lynxlangya/techne/claude-md)<a href="https://agentmods.dev/instructions/lynxlangya/techne/claude-md"><img src="https://agentmods.dev/badge/instructions/lynxlangya/techne/claude-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 | $0.02509 | $0.02509 |
| Opus 5 | $0.01255 | $0.01255 |
| Sonnet 5 | $0.00502 | $0.00502 |
| Haiku 4.5 | $0.00251 | $0.00251 |
Grade A, and why
techne CLAUDE.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 4d 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 — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Repository status: early skill library
techne (τέχνη — Greek for craft · skill · art) is a fresh start from the
old atools-js utility library, but it is no longer docs-only. Current main
contains:
skills/as the source of truth for tool-neutral skill bodies..claude-plugin/as the Claude Code plugin skin and development marketplace..cursor-plugin/plugin.jsonandgemini-extension.jsonas thin host skins.INSTALL.mdas the install matrix for Claude, Codex, Cursor, Gemini, Kimi, and the universal Agent Skills fallback.skills/anchor-viz/, the first real skill: a typed diagram router for codebase architecture, request interactions, data models, state models, and type structures, with a mechanical provenance gate.skills/anchor-repro/, the second real skill: a repro-first bugfix gate that forces fail → fix → same-probe verification through a run ledger.skills/anchor-vet/, the third real skill: an evidence-gated diff review helper that computes scope, blast radius, claims, findings, and verdict admissibility.skills/anchor-intake/, the fourth real skill: a written engineering brief interrogation gate that accounts a fixed rubric before work starts.
There is still no root app, no root package manager, no CI, and no repo-wide
test runner. skills/anchor-viz/scripts/package.json only pins helper dependencies
for that skill's Mermaid validator; skills/anchor-repro/scripts/repro_ledger.py,
skills/anchor-vet/scripts/vet_gate.py, and skills/anchor-intake/scripts/intake_gate.py
are dependency-free Python 3 stdlib (POSIX-only). Do not infer commands,
dependencies, or architecture from the legacy library; that direction was
abandoned.
Project intent
Per the README, techne is a home for "Skills and agents for the AI era." Absent other direction from the user, treat new work as improving shared skill/agent bodies and their thin distribution skins, not as rebuilding a published utility package.
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.
- 4d ago First seen · 182 lines · 2,509 tokens per session scan A bb90d1063483
techne CLAUDE.md is an instructions file published in the GitHub repository lynxlangya/techne (105 stars, last pushed 2mo ago), licensed MIT. It adds 2,509 tokens to every session, about $0.0125 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
hiveshare CLAUDE.md
Instructions for KB-perByte/hiveshare, covering hiveshare — claude.md, repo layout, build & run, key env vars (server) and naming: hive vs memory.
llm-safe-haven CLAUDE.md
Instructions for pleasedodisturb/llm-safe-haven, covering llm safe haven, what this is, project structure, tdd — non-negotiable (adopted 2026-08-17) and the contract.
kleosrules AGENTS.md
Instructions for kleosr/kleosrules, a project described as: Cursor harness pack: user rules, skills, Bash hooks, local HANDOFF memory. macOS, Linux, Windows (WSL).
finding-unknowns-skills CLAUDE.md
Claude Code instructions for Neeeophytee/finding-unknowns-skills, covering repo notes, what ships, and the gate that decides, version lives in three manifests — move them together, files that must be edited together and shipped guidance is not this file.
coding-agent-safety-gate AGENTS.md
Instructions for ASER-ho/coding-agent-safety-gate, covering agents / 代理规则, 仓库类型 / repository type and ai 代理规则 / rules for ai coding agents.
data-scientist copilot-instructions.md
Instructions for realnghon/data-scientist, covering github copilot — 项目指令：data scientist 工作流 and 共享核心 — 回答前请阅读.