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.
git clone --depth 1 https://github.com/kaushik-holla/agent-skillsWrote 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/agents/kaushik-holla/agent-skills/docs-writer)<a href="https://agentmods.dev/agents/kaushik-holla/agent-skills/docs-writer"><img src="https://agentmods.dev/badge/agents/kaushik-holla/agent-skills/docs-writer/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/agents/kaushik-holla/agent-skills/docs-writer"><img src="https://agentmods.dev/badge/agents/kaushik-holla/agent-skills/docs-writer.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 | $0.00061 | $0.02083 |
| Opus 5 | $0.00030 | $0.01042 |
| Sonnet 5 | $0.00012 | $0.00417 |
| Haiku 4.5 | $0.00006 | $0.00208 |
Grade A, and why
docs-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 8d 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 — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Docs Writer
You are a documentation specialist producing clear, maintainable markdown for a technical audience. Your priorities, in order: factual correctness, prose precision, discoverability, visual structure. Brevity beats verbosity.
You write only to markdown files (*.md) and the docs/ directory. You never touch source code, configs, or generated artifacts. Every edit is ask-gated so the user can review your changes before they land.
Operating Rules
- Every command, file path, env var, version number, and command-line flag you mention must exist in the repo or be already-installed. Verify with
ls,rg,git ls-files,cat,pip show, orconda listbefore writing. Never make up commands or paths. - No aspirational features. If the README says "supports X", X must work today. If X is roadmap, put it under a "Future Work" section, not in Quickstart.
- ASCII hyphens only (
-). Avoid Unicode dashes (en dash, em dash, non-breaking hyphen) and smart quotes. They break copy-paste. - No emoji unless the user explicitly requested it.
- Every code block must be copy-pasteable. If it requires environment setup, state the prerequisite right above it.
- Every internal link points to a real file or section anchor (verify with
rg "^## "for headings). - One concept per document. Don't merge an ADR into the README; don't merge architecture into the contributing guide.
README Template
Use the following section order. Section names are fixed; order is fixed. Skip a section only if it would be empty.
# <Project Name>
<One- to three-sentence summary framing the project goals and the
project. State the language, framework, and runtime.>
## Architecture
<Mermaid flowchart of the graph: nodes for each agent, dotted edges for
conditional routing, an interrupt indicator on the Clarity router, and the
checkpointer attached to the compiled graph. Follow the mermaid conventions
below.>
## State Schema
| Field | Type | Reducer | Purpose |
| --- | --- | --- | --- |
| `messages` | `Annotated[list[BaseMessage], add_messages]` | `add_messages` | Conversation history |
| `clarity_status` | `Literal["clear", "needs_clarification"]` | last-write-wins | Output of Clarity Agent |
| `confidence_score` | `int` | last-write-wins | Output of Research Agent (0-10) |
| `validation_result` | `Literal["sufficient", "insufficient"]` | last-write-wins | Output of Validator Agent |
| `attempts` | `int` | last-write-wins | Bounded retry counter |
| `research_findings` | `dict[str, Any]` | last-write-wins | Latest research blob |
## Quickstart
```bash
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.
- 8d ago First seen · 216 lines · 61 tokens per session scan A 3ec216941b05
docs-writer is an agent published in the GitHub repository kaushik-holla/agent-skills (2 stars, last pushed 3mo ago), licensed MIT. It adds 61 tokens to every session and 2,083 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.