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 anilcancakir/claude-code-plugin --skill prompt-writergit clone --depth 1 https://github.com/anilcancakir/claude-code-pluginWrote 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/anilcancakir/claude-code-plugin/prompt-writer)<a href="https://agentmods.dev/skills/anilcancakir/claude-code-plugin/prompt-writer"><img src="https://agentmods.dev/badge/skills/anilcancakir/claude-code-plugin/prompt-writer.svg" alt="Measured on agentmods" 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 | $0.00045 | $0.01672 |
| Opus 5 | $0.00023 | $0.00836 |
| Sonnet 5 | $0.00009 | $0.00334 |
| Haiku 4.5 | $0.00005 | $0.00167 |
Grade A, and why
prompt-writer 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 6d 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 — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Write prompts optimized for Claude Code's model architecture. Every sentence earns its tokens — Claude already knows general concepts.
Core Principles
Progressive disclosure drives all component design. CC loads content in three tiers:
- Metadata (~100 tokens per skill in
<system-reminder>listing) — description only, 250 char cap - Body (loaded on invocation, compacted to 5k tokens) — SKILL.md content
- References (loaded on demand, unlimited) —
references/files read explicitly
Total invoked skills budget: 25k tokens. Challenge every token.
Dedup awareness — CC auto-injects identity, safety rules, tool schemas, permission system, CLAUDE.md cascade, memory instructions, and output formatting. Components must NOT repeat these. Read references/cc-dedup-guide.md for the complete dedup reference before drafting.
Golden rule: Infrastructure instructions = CC provides. Business logic = your component.
Token budget targets:
| Level | Budget |
|---|---|
| Skill listing description | 250 chars hard cap |
| SKILL.md body | <500 lines, compacted to 5k tokens |
| Total invoked skills | 25k tokens |
| Agent body | 40-80 lines, max 120 |
| Command body | 50-200 lines |
| Rule body | 10-40 lines |
Sentence Structure
Use imperative mood: "Extract", "Launch", "Run", "Identify", "Verify".
One sentence = one instruction. Keep under 25 words.
Active voice: "Analyze files" not "Files are analyzed".
Replace vague words with concrete rules:
| Vague | Concrete |
|---|---|
| "good code" | "typed, tested, lint-clean" |
| "proper error handling" | "catch at boundary, rethrow typed" |
| "appropriate naming" | "camelCase methods, PascalCase classes" |
| "consider performance" | "lazy-load collections over 100 items" |
Avoid hedging: "Consider", "Try to", "You should", "You might want to", "Be careful with". These waste tokens and weaken instructions.
Section Patterns
Each component type follows a distinct structural pattern. Read references/writing-patterns.md for complete templates with examples.
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.
- 6d ago First seen · 177 lines · 45 tokens per session scan A 97fb7b52b49d
prompt-writer is a skill published in the GitHub repository anilcancakir/claude-code-plugin (2 stars, last pushed 4mo ago), licensed MIT. It adds 45 tokens to every session and 1,672 once invoked, about $0.0002 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
sparc-methodology
SPARC (Specification, Pseudocode, Architecture, Refinement, Completion) comprehensive development methodology with multi-agent orchestration.
agent-framework-py-release
Use when cutting a Python release for the microsoft/agent-framework monorepo. Triggers on "bump py versions", "cut a python release", "prepare release PR for python", "release py packages", "bump python to X.Y.Z", or similar requests to bump Python package versions and prepare a release PR. Handles all four lifecycle…
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
python-feature-lifecycle
Guidance for package and feature lifecycle in the Agent Framework Python codebase, including stage meanings, feature-stage decorators, feature enums, and how to move APIs from one stage to the next.
build-and-test
How to build and test .NET projects in the Agent Framework repository. Use this when verifying or testing changes.
python-code-quality
Code quality checks, linting, formatting, and type checking commands for the Agent Framework Python codebase. Use this when running checks, fixing lint errors, or troubleshooting CI failures.