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 Kastalien-Research/thoughtbox --skill improving-promptsgit clone --depth 1 https://github.com/Kastalien-Research/thoughtboxWrote 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/kastalien-research/thoughtbox/improving-prompts)<a href="https://agentmods.dev/skills/kastalien-research/thoughtbox/improving-prompts"><img src="https://agentmods.dev/badge/skills/kastalien-research/thoughtbox/improving-prompts/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/kastalien-research/thoughtbox/improving-prompts"><img src="https://agentmods.dev/badge/skills/kastalien-research/thoughtbox/improving-prompts.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 | $0.00044 | $0.01255 |
| Opus 5.5 | $0.00018 | $0.00502 |
| Sonnet 5.5 | $0.00009 | $0.00251 |
| Haiku 4.5 | $0.00004 | $0.00126 |
Grade A, and why
improving-prompts 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 1mo 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Improving Prompts
Overview
Apply documented Claude 4.5 best practices to existing prompts. Do not invent "improvements" - use the actual guidance from Anthropic.
When to Use
- Optimizing CLAUDE.md or AGENTS.md files
- Improving custom command prompts
- Refining skill instructions
- Migrating prompts from older Claude models to 4.5
When NOT to Use
- Writing new prompts from scratch (just follow best practices directly)
- The prompt is working well and user hasn't identified issues
The Core Problem
Without this skill, agents:
- Invent "best practices" from general knowledge
- Make structural changes without asking what's broken
- Add complexity assuming more structure = better
- Change things to demonstrate value rather than solve problems
Common Rationalizations (Do Not Fall For These)
| Rationalization | Reality |
|---|---|
| "The user said it's too vague" | "Too vague" isn't actionable. What specific behavior fails? |
| "I'm the expert, trust me" | Authority doesn't bypass the need for concrete issues |
| "Time pressure - demo tomorrow" | Pressure is when agents make the worst decisions |
| "The spirit of the skill is to help" | Violating the letter IS violating the spirit |
| "I have enough context" | If you can't name the specific failure, you don't |
| "Structure is always better" | Structure solves structure problems, not all problems |
| "This is obviously an improvement" | Obvious to you ≠ solving the user's actual problem |
Required Process
Step 1: Understand Before Changing
Before ANY modifications:
- Ask what specific behaviors are underperforming
- Ask what the prompt should achieve that it currently doesn't
- If user says "just improve it generally" - ask for at least one concrete issue
What counts as a "concrete issue":
- "Claude ignores my instruction to be concise" ✓
- "The examples I provide don't match the output format" ✓
- "Claude suggests changes but doesn't implement them" ✓
What does NOT count:
- "It's too vague" ✗ (vague about what?)
- "It doesn't follow best practices" ✗ (which practice? what fails?)
- "It's inconsistent" ✗ (inconsistent how? show examples)
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.
- 1mo ago First seen · 141 lines · 44 tokens per session scan A 224421d301e5
improving-prompts is a skill published in the GitHub repository Kastalien-Research/thoughtbox (65 stars, last pushed 3mo ago), licensed MIT. It adds 44 tokens to every session and 1,255 once invoked, about $0.0002 per session on Opus 5.5. 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
matlab
Builds, reviews, migrates, and plans MATLAB or GNU Octave numerical workflows. Use for arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
phylogenetics
Builds and analyzes phylogenetic trees using MAFFT multiple sequence alignment, IQ-TREE maximum likelihood with ModelFinder and branch support, and FastTree approximate inference. Uses ETE3 for tree summaries and visualization. Applies to homologous nucleotide or protein sequences, microbial gene trees, protein…
unity-yaml-editing
Last-resort guidance for safely hand-editing Unity YAML.
ad-policy-check
Checks paid ads against the ad platform's rules (Meta, TikTok, Google, LinkedIn and others) and the brand's category rules: the copy, on-image or on-screen text, pictures and people. Rewrites what can be fixed honestly, adds the disclosures that are needed, and flags anything that needs a human or legal review, with…
render-3d-product-showcase
Assemble a premium 3D product-showcase ad from a config — four beat clips (an orbiting hero rotation, a macro push-in, a physics reveal, a typographic close) normalized to the chosen backdrop colour, hard-concatenated in order, closed on a deterministic Playwright brand end card, and mixed under one instrumental bed…
render-airdrop-carousel
Assemble a viral iOS "AirDrop" notification-carousel video ad (≈6–8s, 9:16) from a brand line plus 6–16 real product photos — a native AirDrop share-sheet card ("Brand would like to share a · Decline / Accept") springs up and its preview window CYCLES through the products, landing on a range/lineup payoff with an…