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 gyanranjan/polyagent-skills --skill agent-writergit clone --depth 1 https://github.com/gyanranjan/polyagent-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/skills/gyanranjan/polyagent-skills/agent-writer)<a href="https://agentmods.dev/skills/gyanranjan/polyagent-skills/agent-writer"><img src="https://agentmods.dev/badge/skills/gyanranjan/polyagent-skills/agent-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/skills/gyanranjan/polyagent-skills/agent-writer"><img src="https://agentmods.dev/badge/skills/gyanranjan/polyagent-skills/agent-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 | $0.00069 | $0.00733 |
| Opus 5 | $0.00034 | $0.00367 |
| Sonnet 5 | $0.00014 | $0.00147 |
| Haiku 4.5 | $0.00007 | $0.00073 |
Grade A, and why
agent-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 9d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Writer
Purpose
Create new agent definitions and skill files that conform to the polyagent-skills portable format. This is the meta-skill — it creates other skills.
When to Use
- User wants to create a new skill for the polyagent-skills library
- User wants to define a new agent persona or workflow
- User asks "write me a skill for X"
- User wants to convert agent-specific instructions into portable format
When NOT to Use
- User wants to execute a task using an existing skill (use that domain skill directly)
- User only needs a minor edit to an existing skill file (perform targeted editing instead)
Inputs
Required:
- What the skill/agent should do
- When it should trigger
Optional:
- Example inputs and expected outputs
- Common skills it should reference
- Agents it needs to work with
Process
Step 1: Understand Intent
Clarify what the skill should accomplish, who uses it, and what triggers it.
Step 2: Design the Skill
Plan the process steps, inputs, outputs, and edge cases.
Step 3: Write SKILL.md
Follow the Skill Format Spec exactly:
- YAML frontmatter with name, description, tags, version
- All required sections: Purpose, When to Use, When NOT to Use, Inputs, Process, Output Format, Quality Checks, Common Skills Used, Edge Cases
- References to common-skills where appropriate
Step 4: Create Supporting Files
Add references/, examples/, and templates/ as needed.
Step 5: Validate Portability
Check against the portability rules:
- No agent-specific syntax
- Relative paths only
- Plain Markdown only
- Self-contained steps
Step 6: Update Adapters
Run polyagentctl sync-adapters to add the new skill to all adapter files.
Output Format
A complete skill directory: skills/<skill-name>/SKILL.md plus supporting files.
Quality Checks
- Frontmatter
namematchesskills/<name>/directory exactly - Trigger phrases in the description and "When to Use" are specific and testable
- Required sections from the skill format spec are present
- All referenced files and common-skills use valid relative paths
- Output format is explicit enough to produce deterministic results
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.
- 9d ago First seen · 92 lines · 69 tokens per session scan A 1ee4010a22e8
agent-writer is a skill published in the GitHub repository gyanranjan/polyagent-skills (2 stars, last pushed 6mo ago), licensed MIT. It adds 69 tokens to every session and 733 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 skills, from other repositories
create-skill
Wizard for creating new Agent Zero skills. Guides users through creating well-structured SKILL.md files. Use when users want to create custom skills.
skill-creator
A guide for creating and editing reusable instruction packages called skills. A skill gives an agent the knowledge and workflow needed for a particular kind of task.
create-agent
A guided skill for creating a specialized software agent with its own persona and working principles. It gathers requirements through conversation, shows a preview for confirmation, and then creates the agent.
design-taste-frontend
Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design systems when applicable, audit-first on redesigns, strict pre-flight check.
stitch-design-taste
Semantic Design System Skill for Google Stitch. Generates agent-friendly DESIGN.md files that enforce premium, anti-generic UI standards — strict typography, calibrated color, asymmetric layouts, perpetual micro-motion, and hardware-accelerated performance.
image-to-code
Elite website image-to-code skill for Codex. For visually important web tasks, it must first generate the design image(s) itself, deeply analyze them, then implement the website to match them as closely as possible. In Codex, it must prefer large, readable, section-specific images instead of tiny compressed boards…