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 eugenelim/agent-ready-repo --skill author-or-update-agent-skillgit clone --depth 1 https://github.com/eugenelim/agent-ready-repoWrote 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/eugenelim/agent-ready-repo/author-or-update-agent-skill)<a href="https://agentmods.dev/skills/eugenelim/agent-ready-repo/author-or-update-agent-skill"><img src="https://agentmods.dev/badge/skills/eugenelim/agent-ready-repo/author-or-update-agent-skill/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/eugenelim/agent-ready-repo/author-or-update-agent-skill"><img src="https://agentmods.dev/badge/skills/eugenelim/agent-ready-repo/author-or-update-agent-skill.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 | $0.00154 | $0.01418 |
| Opus 5 | $0.00077 | $0.00709 |
| Sonnet 5 | $0.00031 | $0.00284 |
| Haiku 4.5 | $0.00015 | $0.00142 |
Grade A, and why
author-or-update-agent-skill 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 8d 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Author or update an agent skill
Build the smallest portable skill that changes an agent's decisions for the requested task. Preserve the user's intent, existing behavior, and authority.
Modes
frame is the default and is read-only. Move to create or update only
after an explicit mode transition and immediately before the first write.
Identifying which mode the work will need is not entering it. Naming the target
and the eventual mode is this workflow's first step and happens in frame;
entering create or update is a separate act that happens immediately before
the first write. Until that transition the receipt reports Mode: frame,
however far the plan has progressed — a fully specified patch that has not been
authorized is still framing. Report the mode you are acting in, never the one
the request names or the one the work is heading toward.
knowledge-provider is entered read-only and never carries write authority on
entry; move from knowledge-provider to a write only after the user authorizes
that write in its own explicit transition.
- frame — clarify the activation boundary, observable outcome, non-goals, authority, portability floor, and evidence. Read references/frame.md.
- create — after the user authorizes creation and confirms a confined destination, create the new portable skill. Read references/create.md.
- update — after the user authorizes mutation and confirms the existing skill root, preserve its supported behavior while making the requested change. Read references/update.md.
- knowledge-provider — design a governed, read-only knowledge corpus and the router that serves it. Entry is read-only: the mode reads and plans, and any write waits for its own authorization. Read references/knowledge-provider-pattern.md, references/provenance.md, references/retrieval-evaluation.md, and references/security-boundaries.md.
What ships with it
18 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/eval_queries.json 772 B
- evals/evals.json 10 KB
- evals/files/hook-plugin-design-SKILL.md 1.2 KB
- evals/files/node-browser-suite-SKILL.md 557 B
- evals/files/pytest-suite-SKILL.md 684 B
- evals/files/subagent-composition-SKILL.md 1.1 KB
- evals/files/update-existing-SKILL.md 360 B
- references/create.md 903 B
- references/frame.md 802 B
- references/knowledge-provider-pattern.md 1.1 KB
- references/knowledge-surfaces.md 1.3 KB
- references/language-extension-seams.md 744 B
- references/provenance.md 1012 B
- references/provider-contract.md 4.4 KB
- references/retrieval-evaluation.md 1008 B
- references/safety-and-authority.md 1.4 KB
- references/security-boundaries.md 994 B
- references/update.md 814 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.
- 8d ago First seen · 117 lines · 154 tokens per session scan A 3b471136a404
author-or-update-agent-skill is a skill published in the GitHub repository eugenelim/agent-ready-repo (21 stars, last pushed today), licensed Apache-2.0. It adds 154 tokens to every session and 1,418 once invoked, about $0.0008 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 2026-09-03.
Other skills, from other repositories
supervisor
Autonomous multi-agent quality supervisor and release gate. Use when a user wants the best possible result, asks for rigorous review, or when a substantive answer/deliverable should be challenged before release. Decomposes the task, fans out independent subagents, uses specialist and adversarial judges, verifies…
hns-lsel-curator
Local Self-Evolution Loop (LSEL) curator — the CLUSTER + drain engine for the GOOS-local PROPOSE→APPLY seam closure (SPEC-LSEL-LOCAL-EVOLUTION-001). Companion-offset drain of .moai/lessons-inbox.jsonl with a drain-side severity filter that drops the 65% Bash-timeout/sandbox noise, eventkey clustering with a frequency…
hns-workflow-ci-loop
Unified CI watch + auto-fix loop skill. Polls gh pr checks after /moai sync PR creation, classifies required vs auxiliary failures, attempts safe automated patches (max 3 iterations), and escalates semantic failures to the user. Use for CI loop workflow — NOT for general loop iteration patterns (see…
moai-harness-learner
Harness learning subsystem coordinator. Produces Tier 4 auto-update proposal payloads consumed by the orchestrator (which surfaces them via AskUserQuestion) and orchestrates Apply/Rollback flows. Triggers when harness learning proposals are pending or learning lifecycle management is needed.
moai-platform-chrome-extension
Chrome Extension Manifest V3 development specialist covering service workers, content scripts, message passing, chrome. APIs, side panel, declarativeNetRequest, and Chrome Web Store publishing. Use when building browser extensions.
moai-domain-humanize
AI text humanization and 윤문 (post-editing) specialist that detects and removes AI tells while preserving meaning, facts, and figures. Covers Korean, English, Japanese, and Chinese with a shared severity model (S1/S2/S3), quality grades (A/B/C/D), and 30%/50% over-editing guardrails. Use to make AI-generated text read…