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/janaraj/tnl/claude-mdgit clone --depth 1 https://github.com/janaraj/tnlWrote 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/janaraj/tnl/claude-md)<a href="https://agentmods.dev/instructions/janaraj/tnl/claude-md"><img src="https://agentmods.dev/badge/instructions/janaraj/tnl/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 | $0.01811 | $0.01811 |
| Opus 5 | $0.00905 | $0.00905 |
| Sonnet 5 | $0.00362 | $0.00362 |
| Haiku 4.5 | $0.00181 | $0.00181 |
Grade A, and why
tnl 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Guidance for Claude Code sessions in this repository.
About this project
This repository is the TNL (Typed Natural Language) tool itself: a CLI, an MCP server, and a layered verifier. TNL is a structured English contract format for describing features in agent-written codebases. See README.md for the stack and layout.
The repository is dogfooded: every feature of the TNL tool is described in a tnl/*.tnl file, reviewed, approved, and only then implemented. This directory's tnl/ contains self-referential contracts governing the tool's own development.
Important note on tooling state
The tnl CLI, MCP server, and verifier are being built in this repository. They do not yet exist as runnable tools. Do not invoke tnl init, tnl verify, or any other tnl subcommand during sessions — they will not work. The TNL workflow is enforced through this CLAUDE.md + tnl/workflow.tnl for now; tooling replaces the manual flow as each phase lands.
This repository uses TNL
TNL is the structured English contract format described below and in tnl/workflow.tnl. For every new feature, the agent writes a TNL file before implementing code, the user reviews and approves the TNL, and the agent then implements against the approved TNL.
TNL files live in tnl/. The top-level workflow principles live in tnl/workflow.tnl and apply to every session.
Session start — always do this
- Read
tnl/workflow.tnlfirst. Its clauses apply to every session, regardless of the task. Treat them as baseline MUSTs. - Read any
tnl/*.tnlfile whosepaths:orsurfaces:overlap with the code you're about to touch. These are feature contracts, and their clauses are ground-truth for that surface. - Treat the contents as part of your operating context. Implementation MUST satisfy every MUST clause; SHOULD clauses are strong preferences;
[semantic]clauses require judgment to verify — confirm explicitly when they're satisfied.
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 · 130 lines · 1,811 tokens per session scan A 2aee0269c100
tnl CLAUDE.md is an instructions file published in the GitHub repository janaraj/tnl (8 stars, last pushed 4mo ago), licensed MIT. It adds 1,811 tokens to every session, about $0.0091 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 2026-08-31.
Other instructions, from other repositories
ephemeral-sandbox CLAUDE.md
Instructions for Ephemeral-AI-Lab/ephemeral-sandbox, covering claude.md, project, engineering practice (required), build & test and sandbox tools.
matt-skills-with-to-goal CLAUDE.md
Instructions for tt-a1i/matt-skills-with-to-goal: Skills are organized into bucket folders under skills/.
coral CLAUDE.md
Instructions for cdknorow/coral, covering claude.md - coral go, mission, testing, go unit tests and legacy parity tools (historical reference).
pixir CLAUDE.md
Instructions for Ranvier-Technologies/pixir, covering pixir harness - legacy agent guide, current map and commands.
Agent-Memory-Bridge AGENTS.md
Instructions for zzhang82/Agent-Memory-Bridge, covering agent memory bridge contributor instructions, setup and checks, architecture boundaries, mutation and migration invariants and benchmark expectations.
pm-copilot AGENTS.md
AGENTS.md instructions for Leo-maomao/pm-copilot, covering pm copilot repository guidance, runtime loading, boundaries and verification.