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 agentmods add skills/ethanyoq/skill-hub/skill-lifecycle-managernpx skills add EthanYoQ/Skill-hub --skill skill-lifecycle-managergit clone --depth 1 https://github.com/EthanYoQ/Skill-hubWrote 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/ethanyoq/skill-hub/skill-lifecycle-manager)<a href="https://agentmods.dev/skills/ethanyoq/skill-hub/skill-lifecycle-manager"><img src="https://agentmods.dev/badge/skills/ethanyoq/skill-hub/skill-lifecycle-manager.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 | $0.00114 | $0.02708 |
| Opus 5 | $0.00057 | $0.01354 |
| Sonnet 5 | $0.00023 | $0.00542 |
| Haiku 4.5 | $0.00011 | $0.00271 |
Grade A, and why
skill-lifecycle-manager 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 6d 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 — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Lifecycle Manager
Orchestrate skill work as one evidence-backed lifecycle. Keep source, installation, and ownership separate so an update to one copy does not silently overwrite another.
Core Contract
Maintain three boundaries throughout the task:
- Source: where the skill came from, such as GitHub, skills.sh, a Skill Hub checkout, or a local repository.
- Install: where a runtime loads the active skill, such as a global user root or project root.
- Ownership: whether the path is user-maintained, project-maintained, or system/plugin-managed.
- Runtime: which loader owns the active copy, such as Codex, Claude Code, an Agent Skills-compatible host, or more than one runtime.
Do not treat a Skill Hub checkout, _repos source, plugin cache, and global
install as interchangeable even when their skill names match.
When evidence is incomplete, report known facts, candidate hypotheses, verification paths, and temporary mitigation. Do not present an unverified hypothesis as a cause or completed fix.
Start With Lifecycle Triage
Create a compact internal task card before acting:
- Intent: discover, recommend, install, update, sync, merge, audit, cleanup, package, publish, validate, or create/edit.
- Target: skill name, source URL, repository path, installed path, or topic.
- Scope: project, global/user, source repository, managed root, or unknown.
- Runtime: Codex, Claude Code, multiple runtimes, or unknown. Do not assume the runtime executing this skill is the runtime whose skills are being managed.
- Destructive risk: none, overwrite, move, delete, cleanup, or ownership change.
- Evidence needed: source, version, usage, quality, or scope proof.
- Companion skill:
find-skills,skill-installer,skill-creator, or no companion.
Proceed without asking when target, scope, and ownership are clear. Ask a short question only when a reasonable assumption could modify the wrong skill or cross an ownership boundary.
What ships with it
9 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/evals.json 13 KB
- evals/files/sync-hub/projects/example/private-skill/SKILL.md 137 B
- evals/files/sync-hub/skills/01-agent-engineering/sample-skill/SKILL.md 113 B
- evals/files/sync-local/sample-skill/SKILL.md 155 B
- references/governance-and-reporting.md 6.3 KB
- references/runtime-adapters.md 6.4 KB
- references/skill-hub-operations.md 5.7 KB
- references/upstream-audit.md 10 KB
- scripts/check_upstreams.ps1 39 KB runs code
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.
- 6d ago First seen · 278 lines · 114 tokens per session scan A 051bbc7fb9ae
skill-lifecycle-manager is a skill published in the GitHub repository EthanYoQ/Skill-hub (9 stars, last pushed 2d ago), licensed MIT. It adds 114 tokens to every session and 2,708 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 2026-08-31.
Other skills, from other repositories
watch
File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through /do. Use for automatic reactions to file changes; do NOT use for…
review
5-pass structured code review — correctness, security, performance, readability, consistency.
wiki
Markdown-first knowledge base where the LLM acts as librarian. Ingests raw sources, compiles and interlinks topic files, self-maintains an index. No vector DB or embeddings required -- uses LLM-native navigation over structured markdown up to 400K words.
marshal
Meta-orchestrator that takes any direction — broad, specific, or vague — and autonomously chains skills and context into actionable work. Gathers context from codebase, docs, and memory. Only asks the user when it genuinely cannot proceed. Single-session orchestrator.
systematic-debugging
4-phase root cause analysis: observe, hypothesize, verify, fix. Enforces investigation before any code changes. Emergency stop after 2 failed fixes. Prevents shotgun debugging and fix cascades.
escalation-governance
Assess whether to escalate models. Use when evaluating reasoning depth.