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/yarlson/yarstack/behavior-implementnpx skills add yarlson/yarstack --skill behavior-implementgit clone --depth 1 https://github.com/yarlson/yarstackWhat 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 | $0.00048 | $0.00599 |
| Opus 5 | $0.00024 | $0.00300 |
| Sonnet 5 | $0.00010 | $0.00120 |
| Haiku 4.5 | $0.00005 | $0.00060 |
Grade A, and why
behavior-implement 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 yesterday.
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 — 30 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test-Driven Implementation
Own the implementation cycle for one coherent observable behavior.
Keep the implementation simple and limited to current requirements. Reuse an existing source of truth when the same rule or knowledge would otherwise be maintained in more than one place, but do not combine unrelated behavior merely because the code looks similar. Add abstractions, flexibility, and configuration only when a concrete current need justifies them.
Workflow
- Read the requested behavior, repository instructions, and closest implementation and test patterns.
- Confirm that focused automated tests are proportionate. For engineering tooling and infrastructure, use this workflow only when native checks cannot credibly prove important behavior, concrete complexity or failure risk warrants regression coverage, and a focused deterministic test boundary fits the task. Otherwise leave this skill and use direct implementation with the applicable native checks.
- Identify the observable outcome, important side effects, and state preserved on failure. At each dependency boundary, name the supported contract that makes the outcome reliable. Do not base a guarantee on undocumented or incidental behavior, or claim more than the contract supports.
- Choose the smallest reliable mechanism with complexity and maintenance cost proportionate to the behavior. If no supported mechanism can meet the requirement without material scope growth, stop before implementation, explain the gap, and ask for direction instead of silently approximating the outcome.
- Use
test-designwhen selecting the test level, cases, fixtures, or test boundary is non-trivial; otherwise extend the existing test pattern directly. - Write the smallest focused test and confirm it fails because the behavior is missing or wrong. Treat the test as maintained product code. Reuse existing focused helpers, extract cohesive repeated setup without hiding scenario values, and prefer named table-driven cases only when they share one execution path.
- Change the minimum production code needed to pass without weakening the assertion.
- Refactor only as needed for clarity, rerunning the focused test after each behavior-preserving change.
- Use
crap-index-assesswhen the request targets CRAP or the repository's configured CRAP check covers changed methods. Treat the result as maintainability evidence, not a replacement for behavioral tests. - Run relevant surrounding tests and repository-required checks.
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.
- yesterday First seen · 30 lines · 48 tokens per session scan A 22238808c4e0
behavior-implement is a skill published in the GitHub repository yarlson/yarstack (3 stars, last pushed 4d ago), licensed MIT. It adds 48 tokens to every session and 599 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 2026-08-31.
Other skills, from other repositories
opensrc
Fetch dependency source code to give AI agents deeper implementation context. Use when the agent needs to understand how a library works internally, read source code for a package, fetch implementation details for a dependency, or explore how an npm/PyPI/crates.io package is built. Triggers include "fetch source for"…
release-cli
Release a new version of the tokenmaxxing CLI to npm. Use when explicitly asked to release or publish @851-labs/tokenmaxxing, including checking main, bumping apps/cli/package.json, updating CHANGELOG.md, committing, tagging cli-vX.Y.Z, pushing, monitoring generated native package publishing, and smoke testing the…
ship-mobile-app
Build, change, debug, and prepare production mobile apps across domain meaning, local and server state, lifecycle, platform, and release boundaries. Use for non-trivial Flutter, React Native, iOS, or Android work involving persistence, sync, auth, offline behavior, notifications, permissions, native integrations…
verify-regression-tests
Verify that a regression test actually detects the defect it claims to guard against. Use after adding or reviewing a bug-fix guard, reproducing the original failure after a fix, or investigating a suspiciously green regression test. Do not use for general TDD, broad test-suite audits, mutation-score optimization…
repository-bootstrap
Audit and establish or upgrade the canonical repository governance baseline. Use only when explicitly asked to bootstrap, standardize, or upgrade a repository; do not use for feature development or source-code restructuring.
repository-hygiene
Perform a read-only evidence-based audit of stale docs, agent files, scripts, generated artifacts, duplicate code, and optional tools. Use only when explicitly asked for cleanup or governance review; do not delete or refactor during the audit.