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 bostonaholic/team --skill writing-prosegit clone --depth 1 https://github.com/bostonaholic/teamWrote 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/bostonaholic/team/writing-prose)<a href="https://agentmods.dev/skills/bostonaholic/team/writing-prose"><img src="https://agentmods.dev/badge/skills/bostonaholic/team/writing-prose/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/bostonaholic/team/writing-prose"><img src="https://agentmods.dev/badge/skills/bostonaholic/team/writing-prose.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 | $0.00024 | $0.00710 |
| Opus 5 | $0.00012 | $0.00355 |
| Sonnet 5 | $0.00005 | $0.00142 |
| Haiku 4.5 | $0.00002 | $0.00071 |
Grade A, and why
writing-prose 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 4d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing Prose
Apply plain language and Simplified Technical English (ASD-STE100) to documentation. Read references/style-guide.md first. It carries the word table, examples, score command, and review criteria.
One busy reader
Kenneth Roman and Joel Raphaelson wrote Writing That Works for memos and proposals. A PR description is the same job: one busy reader, one decision, no time. Lead with the recommendation, name the action you want, and cut every sentence that describes the document. The style guide carries the rest.
Plain language
- Write at a seventh-grade reading level with common words.
- Define each acronym, domain term, or jargon term at first use.
- One idea per sentence. Prefer one plain verb to a nominalization.
- Use American spelling and one consistent name for each thing.
Two modes
Choose per sentence:
- Strict: instructions, numbered steps, warnings, errors, and runbook
commands. Cap at 20 words. Use imperative form, one instruction per sentence,
and condition before command. Ban
would,could, andmight. - STE-flavored: design documents, ADRs, PRDs, changelogs, commit bodies, and
review comments. Cap at 25 words. Declarative prose is allowed. Use
wouldorcouldonly for an actual alternative or consequence. Banmight.
A consuming skill's format contract wins. These modes govern sentence prose.
Mechanical invariants
- Use simple tenses and active voice unless the actor is unknown, irrelevant, or deliberately omitted.
- Keep noun clusters to three words. Do not omit subjects, verbs, or articles.
- Use lists for complex text. Never use semicolons. Keep paragraphs to six sentences and one topic.
- Put warnings and cautions before the protected step.
- Name concrete files, commands, paths, identifiers, and components.
- Use the substitutions, restricted meanings, and exceptions in the style guide.
Words and phrases to delete
Delete marketing adjectives, modal prefaces, filler, and false-ease words such
as simply, just, of course, and obviously. Preserve them only in verbatim
quotes, code or proper nouns, or established technical terms whose meaning would
change. State measurable properties instead of evaluative adjectives.
What ships with it
3 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.
- 4d ago Changed · -194 lines · -20 tokens per session ecbb4d4e110e
- 5d ago First seen · 275 lines · 44 tokens per session scan A 5801c1def506
writing-prose is a skill published in the GitHub repository bostonaholic/team (11 stars, last pushed today), licensed MIT. It adds 24 tokens to every session and 710 once invoked, about $0.0001 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
continuous-learning
Pattern extraction, confidence-scored evaluation, skill creation, organization, versioning, and cross-project export pipeline.
goga-discover
Interview the user relentlessly about a decision until every branch of the design tree is resolved, then record the result as a short ADR.
tutti-agent-workspace-app
Build or evolve a complex agent-enabled Tutti workspace app repository. Use for Tutti apps with web/server/shared monorepos, @tutti-os/agent-acp-kit local agent runtimes, kit-owned TUTTICLI agent/composer discovery, dynamic agent catalogs, run-scoped MCP tool gateways, app-owned package builders, web-first debugging…
assimilate-popular-workflows
This skill should be used when the user asks to "find skills in the wild", "assimilate popular workflows", "discover SKILL.md files in repos", "research external skills", "find workflow patterns", "survey the skill landscape", "what skills exist out there", or wants to investigate public repositories for extractable…
mcp-app-verification
Comprehensive verification checklists for MCP Apps. Tests with basic-host reference, validates handler-before-connect, text fallback, resource URI linking, single-file bundling, host styling, CSP, and legacy pattern detection.
mcp-host-styling-integration
Integrates MCP App UI with host theming system. Applies host CSS variables, handles onhostcontextchanged, safe area insets, display mode detection, and fullscreen configuration.