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 KimYx0207/Meta_Kim --skill meta-theorygit clone --depth 1 https://github.com/KimYx0207/Meta_KimWrote 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/kimyx0207/meta_kim/meta-theory)<a href="https://agentmods.dev/skills/kimyx0207/meta_kim/meta-theory"><img src="https://agentmods.dev/badge/skills/kimyx0207/meta_kim/meta-theory/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/kimyx0207/meta_kim/meta-theory"><img src="https://agentmods.dev/badge/skills/kimyx0207/meta_kim/meta-theory.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Agent Snooping · line 239 Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
- high Agent Snooping · line 240 Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
- high System Prompt Leakage · line 464 Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.Fix: Remove any instructions that reveal, print, or output system prompts or internal rules. System instructions should never be exposed to end users.
- medium Rogue Agent · line 229 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00057 | $0.17669 |
| Opus 5 | $0.00028 | $0.08835 |
| Sonnet 5 | $0.00011 | $0.03534 |
| Haiku 4.5 | $0.00006 | $0.01767 |
Grade B, and why
meta-theory scanned grade B with 1 finding 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 2d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- Claude Code project and global inventories: `.claude/agents/`, `.claude/skills/`, `.claude/commands/`, `.claude/hooks/`, `.claude/settings.json`, `~/.claude/agents/`, `~/.claude/skills/`, `~/.claude/commands/`, `~/.cla How it starts
The opening of the file, as written. The whole thing — 522 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Meta-Theory Dispatcher
Purpose
Run Meta_Kim as an executable governance system, not a theory essay. The main thread locks intent, gathers evidence, chooses route, delegates bounded work, reviews, verifies, and synthesizes. It must not become a generic implementation worker for non-trivial work. Machine contract: config/contracts/core-loop-contract.json is the compact default-path contract for this skill. It binds ordinary durable work and explicit meta-theory shortcuts to npm run meta:theory:run, requires the eight-stage spine, and defines which gates block, warn, or stay progressive.
The default governed runner remains planned-only. When the maintainer explicitly supplies --execute-stage-dag, the P-117 bridge executes the existing coreLoop.stageDagPacket in read-only shadow mode through either --stage-runner-runtime codex or --stage-runner-runtime claude, with the P-118 kernel retaining durable node commits; --resume-stage-dag continues only the exact bound unfinished run. The ready-set executor defaults to native concurrency. --stage-runner-orchestrator langgraph may dynamically load an explicitly installed, currently tested @langchain/[email protected] and use only its Functional API entrypoint plus task; it consumes the scheduler-selected ready set and may not define topology or persistence. Both runtimes keep the same graph, checkpoint, and local merge authority. A native terminal result proves invocation, while Review still owns semantic acceptance. Do not claim write execution, external effects, a runtime-specific graph, LangGraph checkpoint authority, or live OpenAI/Claude SDK adapters without credential-backed evidence. The process timeout is a safety fuse, never a task/token/cost budget.
Global-First Owner Discovery
Discovery is global-first, capability-first: not project-local, not agent-name-first. The run searches the relevant sources — local canonical assets, capability indexes, global runtime homes, package scripts, MCP / runtime configs, and external discovery (findskill / meta-scout) — using the cached-inventory, project-light, stop-on-match policy in config/contracts/core-loop-contract.json. A reusable global owner that already matches the boundary wins over creating a project-local copy. Full source-by-source guidance lives in references/global-owner-discovery.md; it must not override the machine contract's stage order, full-scan triggers, or stage-internal parallel policy.
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/eval-contract.md 3.1 KB
- references/create-agent.md 33 KB
- references/dev-governance.md 34 KB
- references/evolution-writeback.md 4.0 KB
- references/global-owner-discovery.md 8.1 KB
- references/intent-amplification.md 9.1 KB
- references/meta-theory.md 21 KB
- references/owner-resolution.md 6.8 KB
- references/path-selection.md 4.4 KB
- references/planning-files.md 8.0 KB
- references/rhythm-orchestration.md 14 KB
- references/runtime-claude.md 19 KB
- references/runtime-codex.md 30 KB
- references/spine-state.md 11 KB
- references/ten-step-governance.md 15 KB
- references/verification-evidence.md 9.1 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.
- 2d ago Changed · +2 lines e656136818e3
- 11d ago First seen · 520 lines · 57 tokens per session scan B 67b490e804b8
meta-theory is a skill published in the GitHub repository KimYx0207/Meta_Kim (273 stars, last pushed yesterday), licensed Apache-2.0. It adds 57 tokens to every session and 17,669 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
chinese-git-workflow
A reference for configuring Git with Chinese code-hosting services such as Gitee, Coding.net, GitLab China, and CNB, including SSH, HTTPS, credentials, CI, and repository mirroring.
chinese-documentation
A Chinese technical-documentation style guide covering spacing, punctuation, numbers, terminology, and links when Chinese and English appear together.
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
ijfw-workflow
Use when the user says: 'build', 'create', 'plan', 'new project', 'brainstorm', 'design', 'UI', 'website', 'dashboard', 'app', 'help me build', 'launch', 'book', 'campaign', or anything project-level. Skill body decides Quick vs Deep path.
ijfw-plan
Use when the user says 'plan this', 'plan it', 'make a plan', 'let's plan', 'draft a plan', 'how should we tackle this', 'break this down', or invokes '/ijfw-plan'. Produces a falsifiable PLAN.md (software, book, campaign, design, research) with task breakdown, dependency wave-table, and success criteria — gated by…
ijfw-writing-skills
Authoring discipline for new IJFW skills. Use when creating a new skill, writing a skill, making a skill that does X, or asked to add a skill. Trigger: create a new skill, write a skill, new skill, make me a skill, skill that does, /ijfw-writing-skills.