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 skills/rtk-ai/rtk/tdd-rustnpx skills add rtk-ai/rtk --skill tdd-rustgit clone --depth 1 https://github.com/rtk-ai/rtkWhat 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 | $0.00045 | $0.01972 |
| Opus 5 | $0.00023 | $0.00986 |
| Sonnet 5 | $0.00009 | $0.00394 |
| Haiku 4.5 | $0.00005 | $0.00197 |
Grade A, and why
tdd-rust 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 2d 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 — 290 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RTK TDD Workflow
Enforce Red-Green-Refactor for all RTK filter development.
The Loop
1. RED — Write failing test with real fixture
2. GREEN — Implement minimum code to pass
3. REFACTOR — Clean up, verify still passing
4. SAVINGS — Verify ≥60% token reduction
5. SNAPSHOT — Lock output format with insta
Step 1: Real Fixture First
Never write synthetic test data. Capture real command output:
# Capture real output from the actual command
git log -20 > tests/fixtures/git_log_raw.txt
cargo test 2>&1 > tests/fixtures/cargo_test_raw.txt
cargo clippy 2>&1 > tests/fixtures/cargo_clippy_raw.txt
gh pr view 42 > tests/fixtures/gh_pr_view_raw.txt
# For commands with ANSI codes — capture as-is
script -q /dev/null cargo test 2>&1 > tests/fixtures/cargo_test_ansi_raw.txt
Fixture naming: tests/fixtures/<command>_raw.txt
Step 2: Write the Test (Red)
#[cfg(test)]
mod tests {
use super::*;
use insta::assert_snapshot;
fn count_tokens(s: &str) -> usize {
s.split_whitespace().count()
}
// Test 1: Output format (snapshot)
#[test]
fn test_filter_output_format() {
let input = include_str!("../tests/fixtures/mycmd_raw.txt");
let output = filter_mycmd(input).expect("filter should not fail");
assert_snapshot!(output);
}
// Test 2: Token savings ≥60%
#[test]
fn test_token_savings() {
let input = include_str!("../tests/fixtures/mycmd_raw.txt");
let output = filter_mycmd(input).expect("filter should not fail");
let input_tokens = count_tokens(input);
let output_tokens = count_tokens(&output);
let savings = 100.0 * (1.0 - output_tokens as f64 / input_tokens as f64);
assert!(
savings >= 60.0,
"Expected ≥60% token savings, got {:.1}% ({} → {} tokens)",
savings, input_tokens, output_tokens
);
}
// Test 3: Edge cases
#[test]
fn test_empty_input() {
let result = filter_mycmd("");
assert!(result.is_ok());
// Empty input = empty output OR passthrough, never panic
}
#[test]
fn test_malformed_input() {
let result = filter_mycmd("not valid command output\nrandom text\n");
// Must not panic — either filter best-effort or return input unchanged
assert!(result.is_ok());
}
}
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.
- 2d ago First seen · 290 lines · 45 tokens per session scan A 2f2aede1ea58
tdd-rust is a skill published in the GitHub repository rtk-ai/rtk (78,131 stars, last pushed yesterday), licensed Apache-2.0. It adds 45 tokens to every session and 1,972 once invoked, about $0.0002 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 skills, from other repositories
tdd-rust
TDD workflow for RTK filter development. Red-Green-Refactor with Rust idioms. Real fixtures, token savings assertions, snapshot tests with insta. Auto-triggers on new filter implementation.
linked-intent-dev
Guide for linked-intent development (LID). Consult for ALL code changes. Walks changes through a mode-aware six-phase workflow (HLD → LLD → EARS → intent-narrowing edge audit → tests-first → code) with mandatory stops between each phase. Bugs walk the arrow like any other change — no short-circuit. Enforces cascade…
build-teaql-app
Build or change a TeaQL application in Java, Rust, Go, Swift, Python, C#/.NET, or TypeScript, including Kotlin/JVM applications that consume Java-generated libraries. Mandatory order: first draft and save a complete KSML model, then verify the client and evaluate that saved model, repair it through repeated evaluation…
build-executor
Govern implementation from an approved execution contract. Invoke when execution-contract.md is approved and the user wants disciplined build work, TDD execution, or guarded batch-by-batch implementation.
agent-teams
Claude Code Agent Teams - default team-based development with strict TDD pipeline enforcement.
ap-implementer
L3 executor - G4 IMPLEMENT. Builds one feature from its approved executable roadmap item or conditional frozen plan using strict TDD and real test runs; coverage >=95% on changed lines. Reports PLAN-CONFLICT rather than improvising.