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/Kim_Service --skill kim-decisiongit clone --depth 1 https://github.com/KimYx0207/Kim_ServiceWrote 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/kim_service/kim-decision)<a href="https://agentmods.dev/skills/kimyx0207/kim_service/kim-decision"><img src="https://agentmods.dev/badge/skills/kimyx0207/kim_service/kim-decision/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/kim_service/kim-decision"><img src="https://agentmods.dev/badge/skills/kimyx0207/kim_service/kim-decision.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 | $0.00148 | $0.05964 |
| Opus 5 | $0.00074 | $0.02982 |
| Sonnet 5 | $0.00030 | $0.01193 |
| Haiku 4.5 | $0.00015 | $0.00596 |
Grade A, and why
kim-decision 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 12d 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 — 579 lines — stays where its author put it; the contents beside it link to each section on GitHub.
KIM Skill
Operating target
Deliver a usable decision or artifact.
The method stays abstract.
The final answer may use concrete evidence.
Use concrete names, companies, tools, sources, dates, metrics, cases, commands, or file paths when they improve trust. Verify them or mark them as unconfirmed.
Do not use a named person as an internal role.
Do not write "think like this person."
Turn useful thinking patterns into abstract models.
Core-problem gate
Before expanding the frame, name the core problem internally in one sentence:
- What decision, defect, design gap, offer, path, or artifact is the user actually asking for?
- What outcome would make the user consider the work successful?
- What evidence would change the answer?
- What is explicitly out of scope for this answer?
- What unknown, if any, blocks a safe or useful answer?
- What is the smallest useful output that moves the user forward?
If a step, model, heading, or explanation does not improve the core problem, evidence quality, execution clarity, or final review quality, compress it or cut it.
Do not let the method become the deliverable. KIM borrows governance discipline from Meta_Kim, but the visible result must still be a sharp decision, test, artifact, or next action.
Path scale
Choose the smallest path that can responsibly close the core problem:
| Path | Use when | Visible shape |
|---|---|---|
| Fast path | Single focused question, local/read-only evidence, no high-stakes external claim | Verdict, leverage point, next action, pass condition |
| Standard path | Product/business/content/strategy decision with meaningful uncertainty | Problem cut, evidence, judgment, 24-hour action, review ruler |
| Regulated path | High-risk, current external facts, legal/financial/security stakes, multi-step execution, or durable public decision | Full evidence labels, explicit assumptions, research attempts, pass/kill gates, open gaps |
Escalate when evidence is weak or risk is high. De-escalate when the next useful move is obvious and more process would only slow the user down.
What ships with it
41 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.
- .gitattributes 100 B
- .gitignore 48 B
- CHANGELOG.md 2.8 KB
- docs/images/alipay.jpg 163 KB
- docs/images/contact-qr.png 825 KB
- docs/images/wechat-pay.jpg 70 KB
- docs/zh-CN/examples/calibration.md 878 B
- docs/zh-CN/examples/creation.md 998 B
- docs/zh-CN/examples/debugging.md 917 B
- docs/zh-CN/examples/decision.md 973 B
- docs/zh-CN/references/business.md 2.8 KB
- docs/zh-CN/references/distillation.md 2.0 KB
- docs/zh-CN/references/execution.md 2.5 KB
- docs/zh-CN/references/gates.md 2.3 KB
- docs/zh-CN/references/master-lens.md 4.0 KB
- docs/zh-CN/references/method.md 2.1 KB
- docs/zh-CN/references/models.md 2.4 KB
- docs/zh-CN/references/output.md 6.7 KB
- docs/zh-CN/references/path.md 1.3 KB
- docs/zh-CN/references/verification.md 2.5 KB
- docs/zh-CN/SKILL.md 7.9 KB
- examples/calibration.md 1.0 KB
- examples/creation.md 1.1 KB
- examples/debugging.md 1.0 KB
- examples/decision.md 1.0 KB
- LICENSE 203 B
- LICENSE-APACHE 187 B
- LICENSE-MIT 328 B
- NOTICE 96 B
- README.md 20 KB
- README.zh-CN.md 19 KB
- references/business.md 3.0 KB
- references/distillation.md 1.9 KB
- references/execution.md 2.5 KB
- references/gates.md 3.6 KB
- references/master-lens.md 4.3 KB
- references/method.md 2.0 KB
- references/models.md 2.6 KB
- references/output.md 8.1 KB
- references/path.md 1.4 KB
- references/verification.md 3.0 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.
- 12d ago First seen · 579 lines · 148 tokens per session scan A b794d84d7a09
kim-decision is a skill published in the GitHub repository KimYx0207/Kim_Service (169 stars, last pushed 1mo ago), licensed MIT. It adds 148 tokens to every session and 5,964 once invoked, about $0.0007 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
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.
magpie-security-issue-import-from-md
Open one or more tracking issues from a markdown file containing a batch of security findings. Each finding becomes one tracker landing in the Needs triage board column. The file itself is the full report — there is no inbound reporter to reply to and no PR to inspect.