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 agentmods add skills/yarlson/yarstack/text-improvenpx skills add yarlson/yarstack --skill text-improvegit clone --depth 1 https://github.com/yarlson/yarstackWhat 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 | $0.00061 | $0.00600 |
| Opus 5 | $0.00030 | $0.00300 |
| Sonnet 5 | $0.00012 | $0.00120 |
| Haiku 4.5 | $0.00006 | $0.00060 |
Grade A, and why
text-improve 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 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.
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 — 30 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Improve Text
Rewrite the supplied or scoped prose in plain, direct language so its intended reader can understand it on the first pass without losing meaning, facts, or technical precision.
Rules
- Rewrite the text; do not review it. Return improved prose, not a list of findings, unless the user asks for an explanation. Do not re-answer the underlying question, fact-check claims, or add new ideas.
- Use the same language as the source. Translate only when the user asks for translation.
- Simpler does not always mean shorter. Make the text hard to misunderstand. Cut words when that helps, but keep context the intended reader needs and use more space when a dense idea needs it.
- Facts survive unchanged. Preserve every path, command, filename, number, URL, identifier, name, decision, quotation, protocol term, legal phrase, and externally required wording. Flag a suspected problem instead of silently changing it.
- Use direct, natural language. Remove needless preamble, hedging, ceremony, stale phrases, jargon, corporate filler, repeated meaning, and unnecessary qualifiers. State concrete subjects, actions, and consequences. Keep formal language and necessary domain vocabulary when the audience or contract requires them; do not force slang or a generic casual voice.
- Simplify the structure when it helps. Break up dense sentences and flatten needless headings, tables, or nested lists. Keep structure that carries meaning or makes multiple parts easier to scan.
- Preserve intentional voice. Keep useful humor, emphasis, and conversational language. Do not replace a distinct voice with generic corporate prose.
- Make the smallest useful edit. Leave clear wording alone. If no wording materially harms clarity, return the original text unchanged.
Boundaries
Work directly on text supplied in the conversation or drafts created within the current authorized workflow. Edit a source file, pull request, issue, or other external content only when the current task authorizes that write.
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 First seen · 30 lines · 61 tokens per session scan A cefb0d32eaa0
text-improve is a skill published in the GitHub repository yarlson/yarstack (3 stars, last pushed 5d ago), licensed MIT. It adds 61 tokens to every session and 600 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
opensrc
Fetch dependency source code to give AI agents deeper implementation context. Use when the agent needs to understand how a library works internally, read source code for a package, fetch implementation details for a dependency, or explore how an npm/PyPI/crates.io package is built. Triggers include "fetch source for"…
release-cli
Release a new version of the tokenmaxxing CLI to npm. Use when explicitly asked to release or publish @851-labs/tokenmaxxing, including checking main, bumping apps/cli/package.json, updating CHANGELOG.md, committing, tagging cli-vX.Y.Z, pushing, monitoring generated native package publishing, and smoke testing the…
ship-mobile-app
Build, change, debug, and prepare production mobile apps across domain meaning, local and server state, lifecycle, platform, and release boundaries. Use for non-trivial Flutter, React Native, iOS, or Android work involving persistence, sync, auth, offline behavior, notifications, permissions, native integrations…
verify-regression-tests
Verify that a regression test actually detects the defect it claims to guard against. Use after adding or reviewing a bug-fix guard, reproducing the original failure after a fix, or investigating a suspiciously green regression test. Do not use for general TDD, broad test-suite audits, mutation-score optimization…
repository-bootstrap
Audit and establish or upgrade the canonical repository governance baseline. Use only when explicitly asked to bootstrap, standardize, or upgrade a repository; do not use for feature development or source-code restructuring.
repository-hygiene
Perform a read-only evidence-based audit of stale docs, agent files, scripts, generated artifacts, duplicate code, and optional tools. Use only when explicitly asked for cleanup or governance review; do not delete or refactor during the audit.