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 steph-dove/klaussy-agents --skill implementgit clone --depth 1 https://github.com/steph-dove/klaussy-agentsWrote 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/steph-dove/klaussy-agents/implement)<a href="https://agentmods.dev/skills/steph-dove/klaussy-agents/implement"><img src="https://agentmods.dev/badge/skills/steph-dove/klaussy-agents/implement.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 5.1 | $0.00059 | $0.02076 |
| Opus 5 | $0.00030 | $0.01038 |
| Sonnet 5 | $0.00012 | $0.00415 |
| Haiku 4.5 | $0.00006 | $0.00208 |
Grade A, and why
{{REPO}}-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 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.
This is a copy
92% identical to fastapi-implement — 9 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Here is the task to implement (the user described it in their message).
Do NOT start coding yet. Follow these phases in strict order.
Phase 1: Understand the Task
Read the user's task description carefully. Identify:
- What is being asked — the specific deliverable or behavior change.
- What is NOT being asked — anything outside this scope is off-limits. Do not refactor, rename, restyle, or "improve" anything beyond the task. If you notice other issues, list them at the end but do NOT fix them.
- Acceptance criteria — extract every testable condition from the task. If the task is ambiguous or missing details that would change your approach, ask the user to clarify before proceeding. Do not guess at requirements — wrong assumptions compound into wrong implementations.
- Referenced assets you can't see — block, don't invent. If the task or ticket points at material you need but cannot retrieve — a mockup, screenshot, or design file attached to a GitHub/Jira issue; a Figma link; an image, spec, or doc you have no tool to open — stop and ask the user to provide it (paste the image, drop the file in the repo, share the copy/measurements). A ticket CLI (
gh issue view,glab issue view, and the Jira equivalents) shows an issue's text but does not download its image attachments, and a design you can't see is not one you can fabricate. Never make up UI text, layout, spacing, colors, or copy to keep moving — a plausible-looking invention looks done and is worse than a blocked task. This is a hard block: implementation cannot proceed past a design the human hasn't given you.
Phase 2: Investigate the Codebase
Enter plan mode now. Phases 2 and 3 must happen in plan mode to prevent premature edits.
Before touching any code, do a targeted read-only investigation. This is the most important phase — wrong file targets and wrong data sources are the #1 cause of wasted work. Investigate just enough to confirm you're targeting the right thing, then stop.
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.
- 5d ago First seen · 124 lines · 0 tokens per session scan A b0cea4be73a3
{{REPO}}-implement is a skill published in the GitHub repository steph-dove/klaussy-agents (16 stars, last pushed 11d ago), licensed MIT. It adds 59 tokens to every session and 2,076 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 92% identical to fastapi-implement, differing in 9 lines, and is treated as a copy.
Other skills, from other repositories
compose:tdd
Use when implementing any feature or bugfix, before writing implementation code.
skillshare-implement-feature
Implement a feature from a spec file or description using TDD workflow. Use this skill whenever the user asks to: add a new CLI command, implement a feature from a spec, build new functionality, add a flag, create a new internal package, or write Go code for skillshare. This skill enforces test-first development…
tdd-cycle
Execute full TDD red-green-refactor cycle with validation gates. Use when saying "TDD cycle", "test-driven development", or "full TDD workflow".
implement
Implement a technical design by decomposing it into dependency-ordered vertical slices, executing each with TDD red-green, reviewing each via an isolated sub-agent, and persisting progress to a state file so work survives session restarts. Use when the user has a tech design (doc or settled conversation) and says…
tdd
A Test-Driven Development guide. TDD means writing a failing test first, adding the smallest implementation that passes it, and then improving the code while keeping the tests passing.
implement
Use when an approved plan and task list exist and it is time to turn them into working, tested code — the SDD phase after analyze and before verify. Enforces TDD: a failing test comes before the code that makes it pass, one task at a time, appended to a progress ledger that survives compaction. Delegates test tooling…