A codebase-aware planning tool that turns a feature specification into a detailed implementation plan. A feature specification is a written description of what should be built.

It reads the specification, investigates the codebase, decides how large the work is, writes a plan, and documents how the change should be tested.

It connects the requested feature to the existing code instead of relying only on a high-level description. It also records the plan and moves the specification into the next work stage.

plan — Skill for Claude Code by fledgeling-co/fledgeling-plugins

Install

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.

Any agent

npx skills add fledgeling-co/fledgeling-plugins --skill plan

Clone the repo

git clone --depth 1 https://github.com/fledgeling-co/fledgeling-plugins

Made for: Claude Code.

Or install shipyard, the plugin that ships this one along with the rest of its 8 skills.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/fledgeling-co/fledgeling-plugins/plan/github.svg)](https://agentmods.dev/skills/fledgeling-co/fledgeling-plugins/plan)

Your own site

<a href="https://agentmods.dev/skills/fledgeling-co/fledgeling-plugins/plan"><img src="https://agentmods.dev/badge/skills/fledgeling-co/fledgeling-plugins/plan/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/fledgeling-co/fledgeling-plugins/plan"><img src="https://agentmods.dev/badge/skills/fledgeling-co/fledgeling-plugins/plan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 202 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,576 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00202	$0.03576
Opus 5.5	$0.00081	$0.01430
Sonnet 5.5	$0.00040	$0.00715
Haiku 4.5	$0.00020	$0.00358

Measured 1mo ago against content hash 5000069c2c63, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

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 1mo 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.

plugins/shipyard/evals/baseline/plan-SKILL.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Feature Spec Planner (markdown specs)

Produce an implementation plan for a feature spec by investigating the actual codebase, write it to a local markdown file, then link it from the spec and move the spec to Ready for Work.

Runs in your current session with Read/Glob/Grep/Write/Edit, Bash, and the Workflow tool. It uses no issue-tracker MCP (Diolog Tasks or otherwise) and invokes no Agent SDK script. The spec markdown file replaces a tracker issue + comment thread.

Inputs

A spec id (DIO-0001). The plan reads docs/specs/spec-<ID>.md. Optional --dry-run intent: write the plan file locally but make no status/ledger updates.

Procedure

Read the spec at docs/specs/spec-<ID>.md. The ## Feature description section is the original intent; the latest ## Triage section carries the Assumptions (the defaults for anything the description didn't pin down) and any answers/edits the human added (authoritative). Summarize intent — don't transcribe the spec into the plan. If the spec status is Needs More Info, first try to resolve the open questions the way triage should have — from the codebase, the closest analogue, and the safer default — and plan on those documented assumptions. Decline to plan only when the core intent genuinely cannot be planned without a real external (non-internal) dependency — a product / policy / brand decision only the human can make, or an external contract / credential / system you lack. Even then, plan every part that dependency does not block and name only the blocked slice; reserve NEEDS TRIAGE for when the whole feature hinges on the missing external answer.
Classify the plan-size tier (Trivial / Small / Standard / Large) before writing — it sets the template and length budget. When in doubt, pick the smaller tier. See references/plan-tiers.md.
Investigate the codebase at the tier's depth — fan out with the Workflow tool ("ultracode"). For Standard/Large specs, spawn parallel reader subagents — one per element/subsystem the spec references — each returning: the exact files to create/modify, the closest existing analogue, the interfaces/contracts, and any naming ambiguity. Synthesize their findings into the plan. For Trivial/Small specs, investigate inline (a workflow is overkill). Trace data features UI → query/mutation → resolver → service → schema end-to-end. A plan grounded in real code is worth writing; a plan of assumptions is not.

Read the full file on GitHub · 80 lines

Changes

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.

1mo ago First seen · 80 lines · 202 tokens per session scan A 5000069c2c63

Subscribe to this mod's changes

plan is a skill published in the GitHub repository fledgeling-co/fledgeling-plugins (2 stars, last pushed 4d ago), licensed MIT. It adds 202 tokens to every session and 3,576 once invoked, about $0.0008 per session on Opus 5.5. 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 2026-09-04.

Planning

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens