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 Angel45604/the-foreman --skill the-refinergit clone --depth 1 https://github.com/Angel45604/the-foremanWrote 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/angel45604/the-foreman/the-refiner)<a href="https://agentmods.dev/skills/angel45604/the-foreman/the-refiner"><img src="https://agentmods.dev/badge/skills/angel45604/the-foreman/the-refiner/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/angel45604/the-foreman/the-refiner"><img src="https://agentmods.dev/badge/skills/angel45604/the-foreman/the-refiner.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00060 | $0.00634 |
| Opus 5 | $0.00030 | $0.00317 |
| Sonnet 5 | $0.00012 | $0.00127 |
| Haiku 4.5 | $0.00006 | $0.00063 |
Grade A, and why
the-refiner 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 10d 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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Modes
Rewrite (default): output the rewritten text only. No preamble, no summary of changes.
Review (cue words: review, flag, diff, "what's wrong"): change nothing. Output a table with columns Span | Category | Why | Replacement. Output the table only. No preamble, no summary, no closing note. If nothing needs changing, output a single table row with Category none, the only value exempt from the rule below. Category must be one of the ten group names in references/ai-tells.md, or a group name from the core contract's Banned patterns or Voice sections. Prefer the ai-tells group name; use a core-contract group name only when no ai-tells group fits.
Process
All references/ paths below resolve under this skill's base directory (stated when this skill loads), never under the project working directory.
- Read the core contract at
references/core-contract.md(its Banned patterns, Truth, and Preserve verbatim when rewriting prose sections govern every mode). - Read the source text for meaning.
- Fast scan for quick smells: synonym rotation (the same idea renamed sentence to sentence), nominalization (writing "perform an analysis" where "analyze" works), marketing adjectives (ai-tells groups 3 and 7), run-on sentences (core contract: "Put one idea in each sentence"), filler connectives (ai-tells group 3), and notice-flag hedge filler (ai-tells group 4). Hedge words that carry real uncertainty are never removed or weakened.
- Walk the text against
references/ai-tells.md. - Read
references/before-after.mdbefore producing any output in either mode. - Rewrite or flag, depending on the mode.
- Run the self-check.
Self-check
Before returning, run this pass:
- Banned-word scan.
- Em-dash scan.
- Opener and closer scan.
- Hedge-strength diff against the source.
- Preserve-verbatim diff (identifiers byte-identical).
- Shape check: the output is the rewritten text only, or the table only; no preamble or closing note.
The rules themselves live in the core contract. This section names only the checks; it does not restate the lists.
What ships with it
4 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.
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.
- 10d ago First seen · 44 lines · 60 tokens per session scan A 45a2ae261805
the-refiner is a skill published in the GitHub repository Angel45604/the-foreman (2 stars, last pushed 11d ago), licensed MIT. It adds 60 tokens to every session and 634 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…