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 ViryaZheng/promptly-prompt --skill skillgit clone --depth 1 https://github.com/ViryaZheng/promptly-promptWrote 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/viryazheng/promptly-prompt/skill)<a href="https://agentmods.dev/skills/viryazheng/promptly-prompt/skill"><img src="https://agentmods.dev/badge/skills/viryazheng/promptly-prompt/skill/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/viryazheng/promptly-prompt/skill"><img src="https://agentmods.dev/badge/skills/viryazheng/promptly-prompt/skill.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 | $0.00059 | $0.00418 |
| Opus 5 | $0.00030 | $0.00209 |
| Sonnet 5 | $0.00012 | $0.00084 |
| Haiku 4.5 | $0.00006 | $0.00042 |
Grade A, and why
promptly-prompt 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.
What it actually says
promptly-prompt
AI answer quality depends on input clarity, not prompt tricks — and nobody writes perfectly clear prompts all the time. This skill catches the unclear ones at submission and repairs them through alignment.
It operates via a UserPromptSubmit hook that injects two disciplines
into unclear requests, both at once:
-
Restate to align — echo the user's request in your own words and state your understanding, so a misread surfaces before any work happens. If the restatement reveals a mismatch, raise it before acting.
-
Diagnose, then reuse prior art — don't solve from memory. Diagnose the root cause of the problem, search for the domain's mature, established practices — methodologies, frameworks, libraries, prior art — and only then proceed. If nothing fits, say so and explain why.
The hook script at scripts/intercept.py scores prompt unclarity using
rule-based signals: vague verbs without success criteria, hedging, and
dangling referents add points; concrete anchors (paths, errors, code),
structure, and explicit criteria subtract them. Length never adds points —
a long, well-specified prompt is the clearest kind and passes untouched.
Unclear requests (score >= 3) get the full injection, in the prompt's own
language (Chinese or English) — both disciplines, every time.
Explicit Invocation
When invoked directly (e.g., user says "optimize this prompt"), apply the two disciplines manually: restate the user's intent with implicit needs surfaced, then locate the domain and the existing methods that belong to it. Rewrite the prompt with that context filled in.
What ships with it
1 file 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 · 42 lines · 59 tokens per session scan A b9b2925c954d
promptly-prompt is a skill published in the GitHub repository ViryaZheng/promptly-prompt (37 stars, last pushed 2mo ago), licensed MIT. It adds 59 tokens to every session and 418 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 2026-08-30.
Other skills, from other repositories
cloudflare-workers-ai
Cloudflare Workers AI for serverless GPU inference. Use for LLMs, text/image generation, embeddings, or encountering AIERROR, rate limits, token exceeded errors.
ai-llm-engineering
Design, integrate, evaluate, and operate AI/LLM systems using model- and framework-agnostic engineering principles.
omh-llm-app-dev
This is a Hermes-native llm-app-dev workflow skill.
omh-model-setup
This is a Hermes-native model-setup workflow skill.
omh-model-optimization
This is a Hermes-native model-optimization workflow skill.
model-onboarding
Onboard a new model generation or sibling into oh-my-hermes: probe router recognition, research the official contract, write trait-to-counter calibration, place routing in both lanes, price from documented list only, gate machine config on a served route, prove with the gates, close with a benchmark pair. Use when a…