plan

plan is a skill for Claude Code from chan4lk/specclaw. It costs 56 tokens per session (2,416 once invoked), scanned A, original, MIT.

A planning step that turns an approved software proposal into a detailed specification, technical design, and ordered task list. It examines the existing codebase before writing these documents.

In plain words
What is it for?
Use it after approving a proposal and before building the change. It creates spec.md, design.md, and tasks.md for the work.
Why use it?
It gives developers a shared, concrete plan before implementation begins and checks that the required proposal and project setup exist.

Skill for Claude Code

Written for Claude Code: $CLAUDE_PLUGIN_ROOT variable. Also seen: mentions subagents.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the specclaw plugin — 32 skills, 21 agents shipped together

Good fit Use it after approving a proposal and before building the change. It creates spec.md, design.md, and tasks.md for the work.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add chan4lk/specclaw
Claude Code
/plugin install specclaw

Made for: Claude Code.

Or install specclaw, the plugin that ships this one along with the rest of its 32 skills, 21 agents.

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.

agentmods badge for plan

README.md
[![agentmods](https://agentmods.dev/badge/skills/chan4lk/specclaw/plan.svg)](https://agentmods.dev/skills/chan4lk/specclaw/plan)
Your own site
<a href="https://agentmods.dev/skills/chan4lk/specclaw/plan"><img src="https://agentmods.dev/badge/skills/chan4lk/specclaw/plan.svg" alt="Measured on agentmods" height="20"></a>
Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,416 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00056 $0.02416
Opus 5 $0.00028 $0.01208
Sonnet 5 $0.00011 $0.00483
Haiku 4.5 $0.00006 $0.00242

Measured 2d ago against content hash cab0c8a58b8a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, 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 2d 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/specclaw/skills/plan/SKILL.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

specclaw plan

First, run specclaw-ensure-init .specclaw — idempotently creates .specclaw/ if it doesn't exist (silent if already initialized; auto-inits using the current directory's basename as the project name).

Turn an approved proposal into an executable plan.

Flags

  • --author-spec — delegate spec authoring to the spec-author subagent for an interactive, technique-driven dialogue (5 Whys, Jobs-to-be-Done, Inversion, Pre-mortem, MoSCoW). When this flag is present, pause for explicit user approval of spec.md before generating design.md and tasks.md. Without the flag, behavior is unchanged (single-shot generation, no dialogue) so /specclaw:auto remains non-interactive.

    Detect the flag as a whitespace-delimited token anywhere in ARGUMENTS (positional-agnostic), and strip it before using the rest of ARGUMENTS as <change>.

  1. Validate: run specclaw-validate-change .specclaw <change> plan. If it fails, report missing prerequisites and stop.
  2. Read .specclaw/changes/<change>/proposal.md.
  3. Analyze the existing codebase (file structure, patterns, dependencies relevant to the change). Also read .specclaw/context.md if it exists — it contains project-level coding rules, patterns, architecture decisions, and constraints; apply them throughout spec, design, and tasks generation.
    • Codebase survey: build a structured survey and keep it in your working context for spec/design/tasks generation: top-two-level directory summary (e.g. from git ls-files | cut -d/ -f1-2 | sort -u), detected manifests (package.json, pyproject.toml, go.mod, Cargo.toml, *.csproj, pom.xml, Makefile, ...) and the languages/tooling they imply, and where tests live.
    • Discovered project docs: run specclaw-discover-context .specclaw list to see ranked candidate docs (rank, line count, path), then specclaw-discover-context .specclaw emit for the budget-capped digest. Read the digest and apply the project's documented conventions, constraints, and non-goals throughout planning. Prefer docs most relevant to this change when deciding what to read in depth. Cite your evidence: when a spec requirement, design decision, or task constraint comes from a discovered doc, name the doc path and quote the exact line(s) it rests on — never attribute a claim to a doc without a quote. If discovery is disabled or finds nothing, both commands print nothing — skip this step silently.
    • Promoted spec knowledge: read .specclaw/knowledge/spec-guidelines.md if it exists — it holds spec/design guidance promoted from earlier build learnings; apply it when writing spec.md and design.md. 3b. Dependency bypass carry-through. If proposal.md has a ## Dependency Bypass section, read .specclaw/analysis/module-stubs.md for each cited ST-### and read $CLAUDE_PLUGIN_ROOT/references/stub-discipline.md. The spec is where a bypass stops being a scheduling decision and becomes build obligations — carry it forward explicitly in all three files:

Read the full file on GitHub · 74 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.

  1. 2d ago Changed · +29 lines cab0c8a58b8a
  2. 7d ago First seen · 45 lines · 56 tokens per session scan A eadcd8b04fd1

Subscribe to this mod's changes

plan is a skill published in the GitHub repository chan4lk/specclaw (12 stars, last pushed 3d ago), licensed MIT. It adds 56 tokens to every session and 2,416 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 2026-08-30.

Related

Other skills, from other repositories