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 agentmods add skills/jeonje/claude-plugins/ma-writenpx skills add JeonJe/claude-plugins --skill ma-writegit clone --depth 1 https://github.com/JeonJe/claude-pluginsWrote 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/jeonje/claude-plugins/ma-write)<a href="https://agentmods.dev/skills/jeonje/claude-plugins/ma-write"><img src="https://agentmods.dev/badge/skills/jeonje/claude-plugins/ma-write.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 | $0.00134 | $0.01010 |
| Opus 5 | $0.00067 | $0.00505 |
| Sonnet 5 | $0.00027 | $0.00202 |
| Haiku 4.5 | $0.00013 | $0.00101 |
Grade A, and why
ma-write 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 4d 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ma-write
Create workspace-owned PRD or technical-design contracts. Stay within the docs scope; never hand off, implement, commit, push, or open an MR from this skill.
Invocation
/ma-write <issue-key> [prd|design] [--auto] [--no-interview]
| Input | Action | Output |
|---|---|---|
/ma-write PROJ-123 prd |
Run the PRD workflow and conditional gates | PRD plus optional blueprint/brief |
/ma-write PROJ-123 design |
Validate the PRD, then run the design workflow | Design plus diagrams |
/ma-write PROJ-123 prd --no-interview |
Draft from available evidence without Phase 0 Q&A | Ready PRD or [BLOCKED] draft with decisions |
Resolve the mode
- Use an explicit
prdordesignargument when provided. - Without a mode, inspect the canonical paths:
- PRD missing →
prd - PRD exists and design missing →
design - Both exist → resume the artifact containing unresolved work; if neither is clearly in progress, ask whether to update PRD or design.
- PRD missing →
- Require the issue key. Resolve the domain through the workspace config (
projects.{name}.domain) before reading project code.
Load only the selected workflow
prd: readreferences/modes/prd.md. Loadchecklists/prd-scenario-edge-cases.mdandreferences/modes/blueprint.mdonly when their gates match.design: readreferences/modes/design.md.
Do not load the other mode's reference; this is the primary context-budget boundary.
References index
| File | When to read |
|---|---|
| references/modes/prd.md | PRD mode — full workflow |
| references/modes/design.md | Design mode — full workflow |
| references/modes/blueprint.md | PRD mode — only when the blueprint gate matches (UI/flow/stakeholder-visible change) |
| references/diagram-choice.md | Design docs — which diagram type fits which content |
| checklists/prd-scenario-edge-cases.md | PRD mode — high-risk-domain features such as auth/payment/scheduling (gate list inside) |
What ships with it
5 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.
- 4d ago First seen · 70 lines · 134 tokens per session scan A 143b78d521b4
ma-write is a skill published in the GitHub repository JeonJe/claude-plugins (3 stars, last pushed 1mo ago), licensed MIT. It adds 134 tokens to every session and 1,010 once invoked, about $0.0007 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
execution-grounded-review
Execution-grounded review: run tests first, trace each acceptance criterion to execution evidence. Use when verifying an implementation meets spec.
multi-model-delegation
Multi-model design consults via PAL (kimi, glm, gemini, gpt). Use when asking other models to brainstorm a design or reconciling their split answers.
api-testing
HTTP API testing with Supertest (TS) and httpx/pytest (Python). Use when the user mentions API testing, Supertest, httpx, REST/GraphQL validation, or HTTP response errors.
dev-environment-bootstrapping
Use this skill when the user asks to bootstrap, set up, create, or initialize a Shopware development environment from scratch — phrases like "set up a Shopware dev environment", "clone and install Shopware", "initialize a Shopware plugin project", "bootstrap Shopware and a new plugin called X", "get a fresh Shopware…
phpunit-integration-to-unit-migrating
Use this skill ONLY when the user explicitly requests an audit, migration, or evaluation of whether a Shopware integration test belongs in the unit suite — trigger phrases like "audit integration tests", "migrate integration tests to unit", "is this an integration test or a unit test", "evaluate integration tests for…
expose-tunable-knob
Expose a live-adjustable control instead of guessing a magic constant for a parameter the agent cannot itself perceive. Use when tuning visual, audio, or UX output (color, size, position, timing, volume) that only the user can judge.