Borrowing it
Nothing to install: this file belongs to frostney/GocciaScript. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/frostney/GocciaScript/main/.agents/skills/software-engineering-excellence/SKILL.mdgit clone --depth 1 https://github.com/frostney/GocciaScriptWrote 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/frostney/gocciascript/software-engineering-excellence)<a href="https://agentmods.dev/skills/frostney/gocciascript/software-engineering-excellence"><img src="https://agentmods.dev/badge/skills/frostney/gocciascript/software-engineering-excellence/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/frostney/gocciascript/software-engineering-excellence"><img src="https://agentmods.dev/badge/skills/frostney/gocciascript/software-engineering-excellence.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00049 | $0.02279 |
| Opus 5.5 | $0.00020 | $0.00912 |
| Sonnet 5.5 | $0.00010 | $0.00456 |
| Haiku 4.5 | $0.00005 | $0.00228 |
Grade A, and why
software-engineering-excellence 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 — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Software engineering excellence
Carry the user's intent to a verified result with less steering and rework. Maintainability governs tradeoffs. Establish the requested outcome, constraints and acceptance criteria before choosing implementation mechanics; reuse settled answers instead of reopening them.
Discover and choose the right layer
Read applicable project instructions, relevant code, tests and durable decisions. Run the named reproduction or inspect the requested artifact when possible. Treat historical notes and issue descriptions as leads to verify. Use the full data; split it across workers when it is too big for one context. Sample only when the person asks.
Before replacing a selected toolkit's capabilities, inspect its overview and consumer guidance as well as the immediate subcommand. Reuse project build, test, formatting and workflow commands. Add an adapter only for a demonstrated missing capability. Generic execution mechanics belong in the harness or a reusable helper; product-specific contracts belong in the repository.
Make the smallest complete change at the layer that owns the behavior. Preserve required success, failure and transition paths. Include blockers that invalidate the requested result; keep unrelated improvements outside its completion bar. Follow native language idioms and the project's conventions.
Continue the authorized work
Treat an action-oriented request, such as "can you…" or "I want…", as an instruction to do the work. A plain-language request for a workflow's outcome, such as "open a PR" or "file an issue", runs that workflow with its gates. An explicit instruction about one choice, such as a label, an endpoint or showing a draft first, replaces only that default.
Implementation authority persists across questions, corrections, diagnoses, worker returns and compaction. Update the affected decision or requirement while retaining the parent objective. A question calls for an answer; it does not silently cancel the remaining work. Follow an explicit change of direction. Before acting on a request, restate its literal ask in one line. When offering options, include the direction the person named; never swap in a different approach without saying so.
What ships with it
5 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.
- yesterday Changed · +39 lines caab9c340a14
- 3d ago Changed 16b2bde01a06
- 22d ago Changed · +3 lines b0cf520e7737
- 24d ago Changed · +2 lines c539e3510d12
- 26d ago Changed · +20 lines · +21 tokens per session 64808966f532
- 29d ago Changed · +41 lines · -34 tokens per session 413e816ba912
- 1mo ago First seen · 100 lines · 62 tokens per session scan A 40a4675f2bea
software-engineering-excellence is a skill published in the GitHub repository frostney/GocciaScript (20 stars, last pushed yesterday), licensed MIT. It adds 49 tokens to every session and 2,279 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
migrate-oxlint
Guide for migrating a project from ESLint to Oxlint. Use when asked to migrate, convert, or switch a JavaScript/TypeScript project's linter from ESLint to Oxlint.
debug-task
Diagnose and fix moon tasks that are broken, misconfigured, or behaving unexpectedly. Use this skill when a moon task is failing, not running, skipped, hanging, producing stale or wrong output, cached when it shouldn't be, re-running every time, or missing outputs after a cache hit. Also covers pipeline hangs, tasks…
investigate
Investigate a specific issue report with strict, evidence-driven diagnosis.
ax-cpp-agent-observability
Use when writing C++ code with axllm for agent tracing, centralized and multi-tenant usage accounting, action logs, runtime diagnostics, replay, and production debugging.
ax-go-agent-observability
Use when writing Go code with github.com/ax-llm/ax/packages/go for agent tracing, centralized and multi-tenant usage accounting, action logs, runtime diagnostics, replay, and production debugging.
ax-java-agent-observability
Use when writing Java code with dev.axllm:ax for agent tracing, centralized and multi-tenant usage accounting, action logs, runtime diagnostics, replay, and production debugging.