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 JeonJe/claude-plugins --skill ma-plangit 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-plan)<a href="https://agentmods.dev/skills/jeonje/claude-plugins/ma-plan"><img src="https://agentmods.dev/badge/skills/jeonje/claude-plugins/ma-plan.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 | $0.00125 | $0.01268 |
| Opus 5 | $0.00063 | $0.00634 |
| Sonnet 5 | $0.00025 | $0.00254 |
| Haiku 4.5 | $0.00013 | $0.00127 |
Grade A, and why
ma-plan 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 7d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ma-plan
Generate one executable implementation PLAN per target project. Keep product code read-only; this skill writes only temporary PLAN files for later review and handoff. Each PLAN also decides whether the runtime E2E gate is required, so later phases do not invent verification scope after implementation.
Invocation
/ma-plan <issue-key> [--projects=project-a,project-b] [--auto]
| Input | Action | Output |
|---|---|---|
/ma-plan PROJ-123 |
Derive projects, confirm, dispatch Plan Agents | One PLAN per project |
/ma-plan PROJ-123 --projects=example-frontend,example-backend |
Use the explicit registered projects | Two validated PLAN files |
/ma-plan PROJ-123 --auto |
Skip confirmation only when inputs and targets are unambiguous | Validated PLANs or [BLOCKED] evidence |
Preconditions
- Read the ma skill's scope gate (
../ma/references/scope-gate.md) and retain a terminal scope ofplan. Do not enter handoff or implementation. - Require PRD, design, and diagrams at their canonical
{contextRoot}/{domain}/paths. - Scan PRD/design open-decision sections. If an unresolved
[Blocking]product or contract decision remains, return[BLOCKED]; Important/Deferrable items may continue as PLAN risks. - Resolve projects from explicit
--projects, otherwise from the PRD affected-project list and designCross-repo Impactrows markedYes. - Validate every project against the workspace config
projectsregistry. If PRD and design disagree, ask for reconciliation;--autodoes not guess the project set. - If a target PLAN already exists, update it as a resume only when its key/project identity matches. Do not create duplicate variants or silently overwrite a different target.
Adaptive planning
Resolve Small, Medium, or Large from the design and affected surface. Apply the evidence budgets in config/inputs.md and step ranges in templates/plan.md; treat them as targets rather than quotas and never add filler.
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.
- 7d ago First seen · 84 lines · 125 tokens per session scan A 31ac327dbb70
ma-plan is a skill published in the GitHub repository JeonJe/claude-plugins (3 stars, last pushed 1mo ago), licensed MIT. It adds 125 tokens to every session and 1,268 once invoked, about $0.0006 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
solr-extending
To build Solr plugins: SearchComponent, QParser, URP, DocTransformer.
doctor
Check ryk installation, policy status, host integration status, and plugin readiness.
init
Create or repair an ryk policy for the current repository.
protect
Explain how to run the current Claude Code workflow under ryk protection.
redteam
Run ryk red-team fixtures and summarize results.
ryk-doctor
Check ryk installation, policy status, host integration status, and plugin readiness.