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 | $0.00073 | $0.02319 |
| Opus 5.5 | $0.00029 | $0.00928 |
| Sonnet 5.5 | $0.00015 | $0.00464 |
| Haiku 4.5 | $0.00007 | $0.00232 |
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 17d 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 — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repo Quality System Lifecycle
Concept bridge
Load digests in references/ when the docs tree is absent: stewardship-loop, evolutionary-simplicity, generational-architecture-ladder. Full essays on docs.page.
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.
Ordinary work: work discipline. Do not restate it. steward adopt writes the full procedure into a new AGENTS.md.
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; useharness-engineering-lifecycle. - Generalizing a proven harness across producer/consumer repos; use
harness-engineering-lifecycle.
What ships with it
23 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 821 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 1.3 KB
- evals/cases/minimal-evidence-bootstrap-trigger.yaml 617 B
- evals/cases/multi-repo-integration-sequence-trigger.yaml 1.3 KB
- evals/cases/owner-boundary-disposition-trigger.yaml 1004 B
- evals/cases/pain-to-disposition-routing-trigger.yaml 1.1 KB
- evals/cases/product-feature-dormant.yaml 443 B
- evals/cases/product-impact-guardrail-trigger.yaml 1.0 KB
- evals/cases/repeated-pdsa-disposition-trigger.yaml 2.3 KB
- evals/cases/repo-quality-baseline-trigger.yaml 518 B
- evals/cases/repository-ecology-review-trigger.yaml 786 B
- references/ecology-review.md 8.6 KB
- references/evals.md 5.0 KB
- references/evolutionary-simplicity.md 1.9 KB
- references/generational-architecture-ladder.md 2.3 KB
- references/multi-repo.md 577 B
- references/product-impact.md 1.5 KB
- references/sources.md 1.8 KB
- references/stewardship-loop.md 1.5 KB
- references/work-discipline.md 932 B
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.
- 17d ago Changed · -141 lines · -6 tokens per session e96dab184ca4
- 27d ago Changed · +16 lines · -46 tokens per session 36836a08a95e
- 1mo ago Changed · +14 lines · +10 tokens per session 45b601f78a38
- 2mo 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 (13 stars, last pushed 4d ago), licensed MIT. It adds 73 tokens to every session and 2,319 once invoked, about $0.0003 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.
repo-quality-system-lifecycle compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| repo-quality-system-lifecycleArenukvern/skill_steward | Skill | 13 | 4d ago | MIT | A | 73 | Claude Code |
| iflytek-hyper-ttsiflytek/iFly-Skills | Skill | 214 | 2d ago | Apache-2.0 | A | 92 | Claude Code, Codex |
| iflytek-ocr-invoiceiflytek/iFly-Skills | Skill | 214 | 2d ago | Apache-2.0 | A | 77 | Claude Code, Codex |
| iflytek-pdf-image-ocriflytek/iFly-Skills | Skill | 214 | 2d ago | Apache-2.0 | A | 81 | Claude Code, Codex |
| iflytek-voiceclone-ttsiflytek/iFly-Skills | Skill | 214 | 2d ago | Apache-2.0 | A | 99 | Claude Code, Codex |
| animated-sketch-diagramiflytek/iFly-Skills | Skill | 214 | 2d ago | Apache-2.0 | A | 182 | Claude Code, Codex |
| iflytek-text-proofreadiflytek/iFly-Skills | Skill | 214 | 2d ago | Apache-2.0 | A | 88 | Claude Code, Codex |