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/kestral-team/kestral-plugins/multiphase-plannpx skills add Kestral-Team/kestral-plugins --skill multiphase-plangit clone --depth 1 https://github.com/Kestral-Team/kestral-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/kestral-team/kestral-plugins/multiphase-plan)<a href="https://agentmods.dev/skills/kestral-team/kestral-plugins/multiphase-plan"><img src="https://agentmods.dev/badge/skills/kestral-team/kestral-plugins/multiphase-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 | $0.00109 | $0.02597 |
| Opus 5 | $0.00055 | $0.01299 |
| Sonnet 5 | $0.00022 | $0.00519 |
| Haiku 4.5 | $0.00011 | $0.00260 |
Grade A, and why
multiphase-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 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 — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Multi-Phase Plan
Produce a correct phased plan and store it on Kestral as the shared source of truth so any coding agent can pick it up
and continue. Where the work genuinely allows it, mark phases into lanes that can run concurrently in separate git
worktrees (Conductor, git worktree, or your host's worktree UI). Pairs with kestral-pickup (start a lane in a fresh
worktree) and kestral-handoff (reconcile progress and repush the plan).
Correctness before parallelism. The job is a plan that reflects the real shape of the work. Parallelism is an observation about that plan (some phases happen to be independent), never a goal you bend the plan toward. A fully sequential, single-lane plan is a normal, expected, good outcome — most plans are mostly sequential. More lanes is not better.
Prerequisites
The Kestral MCP server must be in this session (/mcp). Authentication is handled by the MCP connection — proceed
directly. If any call returns auth failure (401, unauthorized, or Not authenticated), ask the user to reconnect or
authenticate the Kestral MCP server through their app's UI (Cowork: Customize → Connectors; Codex: authenticate
then start a new thread using /new — CLI: codex mcp login Kestral; app: Plugins → Kestral → MCP servers gear; Claude Code:
/mcp → reconnect; Cursor: Settings → Tools & MCPs → Connect).
Human-readable references
Keep Kestral IDs internal unless the user asks for them. In user-facing output:
- Tasks: show
slug - titlewhen a slug is available, linked withurlwhen the host can render links. - Projects, documents, and other Kestral entities: show the readable name first, linked with
urlwhen possible. - People: show display names; if unresolved, write
Unknown member (id: <rawId>).
Entrypoint
Expected invocations include:
/kestral:multiphase-plan$multiphase-plan- "Break this into a multi-phase plan and put it on Kestral."
- "Plan this out so another worktree can pick up a lane."
What ships with it
2 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 · 178 lines · 109 tokens per session scan A 71c8d5e9f851
multiphase-plan is a skill published in the GitHub repository Kestral-Team/kestral-plugins (4 stars, last pushed 17d ago), licensed Apache-2.0. It adds 109 tokens to every session and 2,597 once invoked, about $0.0005 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
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
monorepo-management
Master monorepo management with Turborepo, Nx, and pnpm workspaces to build efficient, scalable multi-package repositories with optimized builds and dependency management. Use when setting up monorepos, optimizing builds, or managing shared dependencies.