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 skills add fellipeutaka/leon --skill implementgit clone --depth 1 https://github.com/fellipeutaka/leonWrote 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/skills/fellipeutaka/leon/implement)<a href="https://agentmods.dev/skills/fellipeutaka/leon/implement"><img src="https://agentmods.dev/badge/skills/fellipeutaka/leon/implement/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/fellipeutaka/leon/implement"><img src="https://agentmods.dev/badge/skills/fellipeutaka/leon/implement.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00016 | $0.01773 |
| Opus 5.5 | $0.00006 | $0.00709 |
| Sonnet 5.5 | $0.00003 | $0.00355 |
| Haiku 4.5 | $0.00002 | $0.00177 |
Grade A, and why
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 1mo 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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implement the work described by the user in the spec or tickets.
The main agent is the orchestrator. It owns the preflight, branch and worktree state, integration, validation, independent review, and delivery. An implementer subagent owns the code for one ticket in one isolated context.
Process
1. Pin the work
Read the complete ticket or spec, identify its acceptance criteria and pre-agreed test seams, and choose the delivery mode below. Record the fixed point for review: the immediate parent branch for a stack, the integration branch for a child ticket, or the trunk/explicit parent for standalone work. If the seams are not settled, ask the user before dispatching implementation.
This step is complete when the scope, seams, blockers, fixed point, target branch, and target worktree are all explicit.
2. Delegate implementation
For any ticket that crosses more than one layer, changes more than one file, or would benefit from a fresh context, dispatch one implementer subagent using the brief in IMPLEMENTER-BRIEF.md. A tiny, isolated edit can stay in the orchestrator context.
Give each subagent its own context and worktree. Dispatch independent frontier tickets in parallel, one worktree per ticket; wait for a blocker before dispatching a dependent ticket. The orchestrator never lets two agents edit the same worktree or branch concurrently.
The implementer subagent calls the Skill tool with "tdd" at the pre-agreed seams, typechecks regularly, runs focused tests during the loop, runs the full suite once, and commits only to its implementation branch. It returns the commit, changed files, checks, and any blocker. It does not choose delivery topology or review its own work.
If the harness has no isolated subagent or worktree capability, execute the same brief in the orchestrator context and record that fallback in the final report.
This step is complete when every dispatched ticket has either returned a verifiable commit and report or has been completed through the documented local fallback.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago Changed · +63 lines 13392f1cdb82
- 1mo ago First seen · 84 lines · 16 tokens per session scan A 693294c53aa7
implement is a skill published in the GitHub repository fellipeutaka/leon (5 stars, last pushed 23d ago), licensed MIT. It adds 16 tokens to every session and 1,773 once invoked, about $0.0001 per session on Opus 5.5. 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
engram-testing-coverage
TDD and coverage standards for Engram. Trigger: When implementing behavior changes in any package.
conductor-implement
Execute tasks from a track's implementation plan following TDD workflow.
principle-test-behavior-not-implementation
Apply when you write, change, or keep a test. Assert what the code's users can observe, so that the test fails when that behavior breaks and keeps passing when only the internals change.
iterative-development
TDD iteration loops using Claude Code Stop hooks - runs tests after each response, feeds failures back automatically.
python
Python development with ruff, mypy, pytest - TDD and type safety.
tdd
This skill should be used when the user wants to implement features or fix bugs using test-driven development. Enforces the RED-GREEN-REFACTOR cycle with vertical slicing, context isolation between test writing and implementation, human checkpoints, and auto-test feedback loops. Uses multi-agent orchestration with the…