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 Kevin-Liu-01/Agent-Machines --skill refinegit clone --depth 1 https://github.com/Kevin-Liu-01/Agent-MachinesWrote 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/kevin-liu-01/agent-machines/refine)<a href="https://agentmods.dev/skills/kevin-liu-01/agent-machines/refine"><img src="https://agentmods.dev/badge/skills/kevin-liu-01/agent-machines/refine/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/kevin-liu-01/agent-machines/refine"><img src="https://agentmods.dev/badge/skills/kevin-liu-01/agent-machines/refine.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 10 findings, up to medium
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 →
- medium Agent Snooping · line 49 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 62 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Excessive Agency · line 72 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Agent Snooping · line 80 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 81 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 86 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 101 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 113 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 124 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 137 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00061 | $0.01410 |
| Opus 5 | $0.00030 | $0.00705 |
| Sonnet 5 | $0.00012 | $0.00282 |
| Haiku 4.5 | $0.00006 | $0.00141 |
Grade A, and why
refine 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 7d 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 — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Refine
Seven-pass quality gate. Each pass delegates to a standalone skill, so
you can run any pass independently (/comment, /lerp, /fix-types,
/exemplar-audit, etc.) or all seven in order (/refine).
Principle: docs and by-the-book examples first
Before implementing anything, check official documentation and
real-world examples. Clone reference repos into /tmp, read upstream
READMEs, and verify the canonical approach before inventing your own.
This applies to every pass. The internet is smarter than guessing.
Principle: test the invariant, not the implementation
Don't write tests that confirm the code you wrote works. Write tests that probe the contract the code is supposed to uphold. "Rename works" is an implementation test. "Rename never orphans children" is an invariant test. The second one catches bugs before they exist.
Scope
Operates on every file in the current working set (unstaged + staged + recent commits). If the user names specific files, a package, or a directory, scope to those.
/refine-- all touched files, all 7 passes/refine $0-- scope to a file, crate, or directory/refine --pass N-- run only pass N (1-7)/refine --skip N-- skip pass N
Passes
Each pass reads its own skill file for the full checklist, so updates to individual skills propagate automatically.
Pass 1: Comment
Skill: .agents/skills/comment/SKILL.md
| Check | Applies to |
|---|---|
| License/copyright header present | all languages |
| File-level doc answers what / why / where in 30 seconds | all |
| Acronyms spelled out on first use | all |
| Inline comments pass the deletion test | all |
| No "This module/struct/class/function..." openers | all |
| Concrete examples for formats, protocols, state machines | all |
Pass 2: LERP (Least Experienced Reader Principle)
Skill: .agents/skills/lerp/SKILL.md
| Check | Applies to |
|---|---|
| Acronyms spelled out on first use, short form in parens, then abbreviate freely | all prose |
| Domain terms explained inline on first use | all prose |
| No orphan references ("this split", "this pattern") without context | all prose |
| Every "important" or "necessary" claim states the consequence | all prose |
| Abstract nouns replaced with concrete descriptions | all prose |
| Sentences connected into flowing reasoning, not staccato facts | all prose |
| A sixth grader could follow the argument without asking someone | all prose |
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.
- 7d ago First seen · 157 lines · 61 tokens per session scan A 41b63922a011
refine is a skill published in the GitHub repository Kevin-Liu-01/Agent-Machines (29 stars, last pushed yesterday), licensed MIT. It adds 61 tokens to every session and 1,410 once invoked, about $0.0003 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
hermes-change-review
Use when a branch, pull request, Kanban task, or implementation must be reviewed separately for intent fidelity, repository quality, and verification evidence before completion or merge is accepted.
fable-judge
Adversarial verification of finished work. Treats any 'done' claim as a set of claims to verify by re-running everything yourself. Use when someone reports work complete and you must gate it: load this before trusting a completion report. Subcommands: suite runs a trap suite against any skill/model.
readme-template
Standard README template for repos — professional structure with badges, overview, table of contents, features/modules, stack, installation, configuration, tests, security, structure, docs, roadmap, contribute, license, author + RepoActivity sections (Star History, repo stats) + profile GIF footer. Use when creating…
docker-single-port-multi-instance
Consolidate multiple Docker Compose app instances (production / test / demo) behind ONE host port using an nginx reverse proxy that routes by URL path prefix (e.g. /demo). Use when a user wants 'one port, several apps/banks' or a demo reachable simultaneously from the main landing page with its own database.
review
Challenge a Hardproof implementation during REVIEW against its approved contract, code quality, tests, and risk boundaries.
implement
Implement an agreed specification through existing seams with tests, checks, and review.