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 Arenukvern/skill_steward --skill repo-quality-system-lifecyclegit clone --depth 1 https://github.com/Arenukvern/skill_stewardWrote 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/arenukvern/skill_steward/repo-quality-system-lifecycle)<a href="https://agentmods.dev/skills/arenukvern/skill_steward/repo-quality-system-lifecycle"><img src="https://agentmods.dev/badge/skills/arenukvern/skill_steward/repo-quality-system-lifecycle/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/arenukvern/skill_steward/repo-quality-system-lifecycle"><img src="https://agentmods.dev/badge/skills/arenukvern/skill_steward/repo-quality-system-lifecycle.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 | $0.00115 | $0.04419 |
| Opus 5 | $0.00057 | $0.02210 |
| Sonnet 5 | $0.00023 | $0.00884 |
| Haiku 4.5 | $0.00012 | $0.00442 |
Grade A, and why
repo-quality-system-lifecycle 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 11d 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 — 279 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repo Quality System Lifecycle
Use this skill to make a repository legible, safe, and improvable for humans and agents. It is broader than Agent Skill authoring and narrower than product implementation.
When to use
- Setting up Engineering Stewardship in an app, library, CLI/tool, plugin, harness, or meta repo.
- Auditing whether a repo has enough charter, docs, decisions, validation, evidence, and safety metadata for agents to work without hidden local context.
- Designing a repo quality contract before adding harness actions, diagnostics, or automation.
- Separating repo stewardship proof from product runtime correctness.
- Auditing a multi-repo integration chain where one repo must publish, tag, or stabilize before a consumer repo can truthfully cut over.
- Deciding whether repeated repo friction should stay native, become docs/FAQ, become an API/schema/generator, become harness proof, or be deleted/collapsed.
- Auditing broad product claims such as platform support, compatibility, maturity, or "works everywhere" language against live evidence and owner boundaries.
- Running a repository ecology review over plans, specs, docs, skills, schemas, tools, evidence, and validation surfaces to choose explicit dispositions.
When not to use
- Writing product/domain features directly; use the repo's native stack and product skills.
- Creating or packaging an Agent Skill; use
skill-authoring-lifecycle. - Maintaining a
steward.yamlaction contract, probes, benchmarks, or CLI/MCP parity after the baseline exists; usemcp-harness-repo-maintainer. - Generalizing a proven harness across producer/consumer repos; use
harness-engineering-lifecycle.
Workflow
1. Classify the repo
Pick one primary archetype. Do not let every repo become a harness repo.
| Archetype | Primary artifact | First proof |
|---|---|---|
| App | Product behavior and runtime | Product validation gate plus debugging path |
| Library | Public API and package contract | Tests, package dry-run, compatibility note |
| CLI/tool | Commands and machine-readable outputs | --help, --json, golden output or command test |
| Plugin | Host integration | Manifest, permissions, install/rollback note |
| Harness/action contract | Agent-facing action/probe/benchmark | Quick-safe action and benchmark scenario |
| Meta/governance | Skills, docs, policies, validators | Skill validation, eval cases, registry consistency |
What ships with it
16 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.
- evals/cases/boldest-useful-path-trigger.yaml 1.5 KB
- evals/cases/copy-install-friction-disposition-trigger.yaml 761 B
- evals/cases/evolutionary-simplicity-cli-trigger.yaml 1.4 KB
- evals/cases/generational-architecture-trigger.yaml 872 B
- evals/cases/loop-smell-catalog-trigger.yaml 1.1 KB
- evals/cases/minimal-evidence-bootstrap-trigger.yaml 617 B
- evals/cases/multi-repo-integration-sequence-trigger.yaml 1.2 KB
- evals/cases/owner-boundary-disposition-trigger.yaml 936 B
- evals/cases/pain-to-disposition-routing-trigger.yaml 1008 B
- evals/cases/product-feature-dormant.yaml 443 B
- evals/cases/product-impact-guardrail-trigger.yaml 934 B
- evals/cases/repeated-pdsa-disposition-trigger.yaml 2.1 KB
- evals/cases/repo-quality-baseline-trigger.yaml 518 B
- evals/cases/repository-ecology-review-trigger.yaml 775 B
- references/evals.md 4.6 KB
- references/sources.md 1.5 KB
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.
- 11d ago First seen · 279 lines · 115 tokens per session scan A 1fc566f6d535
repo-quality-system-lifecycle is a skill published in the GitHub repository Arenukvern/skill_steward (11 stars, last pushed 27d ago), licensed MIT. It adds 115 tokens to every session and 4,419 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
iflytek-hyper-tts
A text-to-speech tool that turns written text into an MP3 recording. It can use an authorized voice and adjust speaking speed, volume, and pitch.
iflytek-ocr-invoice
An image-reading tool that extracts structured information from Chinese invoices, receipts, bills, and tickets. OCR means turning text in a photo or scan into computer-readable data.
iflytek-pdf-image-ocr
AI-powered OCR service for images and PDF documents using iFlytek's advanced recognition APIs.
iflytek-voiceclone-tts
A tool for creating a speech model from recorded audio and then generating speech that uses the cloned voice. Voice cloning means training software to imitate a person’s voice.
animated-sketch-diagram
A tool for making animated diagrams and flowcharts in a hand-drawn ink style, with paper-like backgrounds, simple icons, and moving dots along connections. It produces a self-contained HTML file and can also create a looping GIF.
iflytek-text-proofread
A tool that checks Chinese writing through iFlytek’s official document-proofreading service. It looks for spelling, punctuation, wording, factual, terminology, and sensitive-content problems.