tnl-feature

tnl-feature is a command for Claude Code from janaraj/tnl. It costs 18 tokens per session (433 once invoked), scanned A, original, MIT.

A command workflow for proposing and implementing a feature through a TNL, a written contract describing the required behavior and tests. It requires user approval of that contract before code is changed.

In plain words
What is it for?
Use it to clarify a feature, identify related TNL files, propose testable behavior, wait for approval, and then implement the approved change.
Why use it?
It prevents coding from starting while the feature’s meaning or scope is still unclear. The approved contract provides concrete requirements for implementation and verification.

Command for Claude Code

Install

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.

agentmods
npx agentmods add commands/janaraj/tnl/tnl-feature
Clone the repo
git clone --depth 1 https://github.com/janaraj/tnl

Made for: Claude Code.

Wrote 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.

agentmods badge for tnl-feature

README.md
[![agentmods](https://agentmods.dev/badge/commands/janaraj/tnl/tnl-feature.svg)](https://agentmods.dev/commands/janaraj/tnl/tnl-feature)
Your own site
<a href="https://agentmods.dev/commands/janaraj/tnl/tnl-feature"><img src="https://agentmods.dev/badge/commands/janaraj/tnl/tnl-feature.svg" alt="Measured on agentmods" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 433 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00018 $0.00433
Opus 5 $0.00009 $0.00217
Sonnet 5 $0.00004 $0.00087
Haiku 4.5 $0.00002 $0.00043

Measured 5d ago against content hash ce8e25d1c58d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tnl-feature 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 5d 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.

.claude/commands/tnl-feature.md · 39 lines

What it actually says

/tnl-feature

Arguments: $ARGUMENTS

Run the TNL workflow for the feature described in arguments. Follow these steps exactly.

1. Scope

Read tnl/workflow.tnl and any tnl/*.tnl whose paths: or surfaces: overlap with the code you are about to touch. If the TNL MCP server is configured, use the get_impacted_tnls tool with the likely target code paths.

2. Clarify

If the request admits more than one reasonable interpretation, ask targeted clarifying questions BEFORE proposing a TNL. Do NOT silently pick an interpretation.

3. Propose

Draft a TNL diff:

  • New behavioral surface → new tnl/<slug>.tnl with id: matching the filename stem.
  • Modified behavior → edit to the existing TNL.

Every MUST clause must be concrete and testable (specific file paths, function names, test names). If the MCP propose_tnl_diff tool is configured, use it to stage the proposal and return a diff_id.

4. Wait for approval

Do NOT write code until the user approves the TNL diff. Incorporate any edits the user makes before proceeding.

5. Implement

Write the code and tests the approved TNL requires. Modify only files listed in the TNL's paths: unless the user explicitly agrees to scope expansion. If propose_tnl_diff staged the diff, call approve_tnl_diff now to write the TNL file and regenerate its sidecar.

6. Self-attest

List each MUST clause from workflow.tnl plus the feature TNL(s) touched. For each state: (a) satisfied — by which file/function/test, (b) could not satisfy — why, or (c) did not apply — why. The list MUST be exhaustive.

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.

  1. 5d ago First seen · 39 lines · 18 tokens per session scan A ce8e25d1c58d

Subscribe to this mod's changes

tnl-feature is a command published in the GitHub repository janaraj/tnl (8 stars, last pushed 4mo ago), licensed MIT. It adds 18 tokens to every session and 433 once invoked, about $0.0001 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.