Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/SummerEngine/summer-engine-agentnpx agentmods add skills/summerengine/summer-engine-agent/writing-skillsWrote 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/summerengine/summer-engine-agent/writing-skills)<a href="https://agentmods.dev/skills/summerengine/summer-engine-agent/writing-skills"><img src="https://agentmods.dev/badge/skills/summerengine/summer-engine-agent/writing-skills/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/summerengine/summer-engine-agent/writing-skills"><img src="https://agentmods.dev/badge/skills/summerengine/summer-engine-agent/writing-skills.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 | $0.00020 | $0.05165 |
| Opus 5 | $0.00010 | $0.02583 |
| Sonnet 5 | $0.00004 | $0.01033 |
| Haiku 4.5 | $0.00002 | $0.00517 |
Grade A, and why
writing-skills 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 9d 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
83% identical to writing-skills — 98 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 — 658 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing Skills
Overview
Writing skills IS Test-Driven Development applied to process documentation.
Personal skills live in agent-specific directories (~/.claude/skills for Claude Code, ~/.agents/skills/ for Codex)
You write test cases (pressure scenarios with subagents), watch them fail (baseline behavior), write the skill (documentation), watch tests pass (agents comply), and refactor (close loopholes).
Core principle: If you didn't watch an agent fail without the skill, you don't know if the skill teaches the right thing.
REQUIRED BACKGROUND: This skill adapts the RED-GREEN-REFACTOR cycle to documentation. The cycle: write the test first and watch it FAIL for the reason you expect (red), make the smallest change that passes it (green), then clean up without changing behaviour (refactor). A test you never saw fail proves nothing.
Official guidance: For Anthropic's official skill authoring best practices, see anthropic-best-practices.md. This document provides additional patterns and guidelines that complement the TDD-focused approach in this skill.
What is a Skill?
A skill is a reference guide for proven techniques, patterns, or tools. Skills help future Claude instances find and apply effective approaches.
Skills are: Reusable techniques, patterns, tools, reference guides
Skills are NOT: Narratives about how you solved a problem once
TDD Mapping for Skills
| TDD Concept | Skill Creation |
|---|---|
| Test case | Pressure scenario with subagent |
| Production code | Skill document (SKILL.md) |
| Test fails (RED) | Agent violates rule without skill (baseline) |
| Test passes (GREEN) | Agent complies with skill present |
| Refactor | Close loopholes while maintaining compliance |
| Write test first | Run baseline scenario BEFORE writing skill |
| Watch it fail | Document exact rationalizations agent uses |
| Minimal code | Write skill addressing those specific violations |
| Watch it pass | Verify agent now complies |
| Refactor cycle | Find new rationalizations → plug → re-verify |
What ships with it
6 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.
- 9d ago First seen · 658 lines · 20 tokens per session scan A d6c685c1ab74
writing-skills is a skill published in the GitHub repository SummerEngine/summer-engine-agent (59 stars, last pushed 2d ago), licensed MIT. It adds 20 tokens to every session and 5,165 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 83% identical to writing-skills, differing in 98 lines, and is treated as a copy.
Other skills, from other repositories
hearth-playtest
Let the engine hunt bugs for you — bot playtesting via hearth sweep. Seeded bot policies (mash/idle/wander/seek) play a scene headlessly across many seeds and report softlocks, crashes, stuck states, and unmet objectives as a compact evidence report; objectives double as executable acceptance criteria; a failing seed…
tests-run
Execute Unity tests (EditMode or PlayMode) and return per-test results. Supports filtering by test assembly, namespace, class, and method. Refreshes the AssetDatabase first; defers execution across domain reloads if scripts changed. Precondition: every open scene must be saved — dirty scenes abort the run.
roblox-studio-workflow
Modify living Roblox Studio projects safely: inspect Explorer and execution locations, preserve existing structure, reuse modules/remotes, create meaningful Instances, apply Attributes and CollectionService tags, test server/client and multiple devices, inspect Output, and remove experiments/debug objects. Use when an…
self-evolve
Capture reusable patterns from a finished project and lift them into framework-level priors (contracts, modules, skeletons) that future projects inherit. Run only when the user explicitly requests self-evolution; the orchestrator executes the workflow.
game-qa
Verify a game with evidence on its selected target runtime. Launch the actual build and prove real rendering, input, the core loop, at least one designed outcome, restart, and explicit limitations without dressing subjective fun up as a certain verdict. Use for test a generated game, QA a game build, check whether the…
artist-self-evolve
Distill stable art-generation patterns from a completed project, so future projects produce comparable assets without re-discovering the prompts. Lead-dispatched only — orchestrator invokes this skill from its self-evolve flow with a game-slug message; do not self-trigger.