c-plan

c-plan is a skill for Claude Code from sentasity/cadence. It costs 83 tokens per session (5,175 once invoked), scanned A, original, MIT.

A planning guide that turns an approved software design into one exact, execution-ordered plan folder. The plan records file paths, changes, commands, and links back to the design.

In plain words
What is it for?
Preparing a code-change plan after design approval, including work divided into phases.
Why use it?
It gives an AI coding agent precise implementation instructions and prevents planning from starting with an unfinished or already-used design.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: mentions subagents; names the AskUserQuestion tool.

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 cadence plugin — 11 skills, 5 agents, 1 hook shipped together

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 sentasity/cadence
Claude Code
/plugin install cadence

Made for: Claude Code.

Or install cadence, the plugin that ships this one along with the rest of its 11 skills, 5 agents, 1 hook.

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 c-plan

README.md
[![agentmods](https://agentmods.dev/badge/skills/sentasity/cadence/c-plan.svg)](https://agentmods.dev/skills/sentasity/cadence/c-plan)
Your own site
<a href="https://agentmods.dev/skills/sentasity/cadence/c-plan"><img src="https://agentmods.dev/badge/skills/sentasity/cadence/c-plan.svg" alt="Measured on agentmods" height="20"></a>
Per session 83 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,175 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
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 $0.00083 $0.05175
Opus 5 $0.00042 $0.02587
Sonnet 5 $0.00017 $0.01035
Haiku 4.5 $0.00008 $0.00517

Measured 5d ago against content hash b1e1cf54d0f6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

c-plan scanned grade A with 1 finding 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 5d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- **A. Automated** — Claude runs each: `curl`, `psql`, `pytest`, etc. Expected value/shape; broken-if signal.
skills/c-plan/SKILL.md · 212 lines

How it starts

The opening of the file, as written. The whole thing — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/c-plan

You translate an approved design into an execution-ordered plan folder. Plans are written for AI, not humans — terse, exact, no padding.

Entry contract

Requires: the design artifact for {yyyy-mm-dd-slug} with status: approved. Read the entire design (overview + every child + 99-OOS) via skills/_shared/storage-resolution.md (read_artifact) before drafting; do not assume a <paths.designs>/… folder path. When the design carries a 95-visual-contract slot, the read includes it, and the planner also fetches the frozen mockup via skills/_shared/storage-resolution.md (read_mockup).

Refuses when: design status is draft or in-review (tell user to finish/approve the design first); or when the design's 95-visual-contract freeze record still reads frozen: none (malformed approved design; point the user back to /c-design's approval step); or when a plan artifact with the same slug already exists at non-draft status — check via skills/_shared/storage-resolution.md (artifact_exists) — which would overwrite.

One design → one plan

A design always becomes exactly one plan folder. Work that would once have been separate plans becomes phase docs (01-<phase>.md, 02-<phase>.md, …) inside that one plan. There is no split question and no linked_plans: array. After reading the design, confirm the phase decomposition with the user (writing-flow step 3); do not ask about splitting into multiple plans.

Size is handled by phase decomposition, not by spawning sibling plans — /c-execute's DAG engine already parallelizes across phase docs.

Phase file sizing — fewer, coherent files

Each phase file becomes the unit of worktree dispatch and the unit of per-lane review under /c-execute's lane = phase file rule (docs/designs/2026-05-28-lane-by-phase-file/01-execution-engine-change.md). Consolidate related work into fewer, larger phase files:

  • One substantive topic per file. A topic is a coherent slice the reviewer can hold in their head — closely-related codebase slice (one skill, one service, one feature surface), shared Reads: core across tasks, a one-sentence reviewer headline with no "and also" clauses, and an internal DAG shape (chain, fan-out, fan-in — not fully disconnected).
  • Target 5–10+ tasks per file. Below 5 is too thin to amortize worktree spin-up + per-lane review. 10+ is fine as long as topical coherence holds. The 5–10+ figure is a target, not a threshold — a genuinely 3-task plan still ships as a 3-task phase file.
  • Task size inside a phase file is unchanged. The per-task contract (Reads:/Touches:/Depends:/Steps, every step one action, every code step shows the FULL code) is exactly today's rule. Consolidation is at the file level, not the task level.

Read the full file on GitHub · 212 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. 5d ago First seen · 212 lines · 0 tokens per session scan A b1e1cf54d0f6

Subscribe to this mod's changes

c-plan is a skill published in the GitHub repository sentasity/cadence (1 stars, last pushed 11d ago), licensed MIT. It adds 83 tokens to every session and 5,175 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

self-improve

Self-improve this skills repo — surface and (safely) apply quality improvements across four parallel read-only lenses (Clarity, Leanness, Coverage, Ergonomics). Sibling of /self-audit — audit fixes rule violations, improve raises quality where no rule is broken. Local meta-skill, independent of the /task: pipeline.

SpaiR/task-pipeline · 76 tokens

architect

Answer build-or-adopt honestly, then design one committed architecture from your own understanding of the problem — driven by ranked quality attributes, stress-tested against the field and against change, proven by a walking skeleton, its consequences confirmed by the user, committed to ARCHITECTURE.md. A command the…

donald-ada/workinggenius · 80 tokens

self-audit

Self-audit this skills repo against CLAUDE.md invariants, the artifact contract, and README/CLAUDE.md/docs sync via three parallel read-only subagents. Local meta-skill — independent of the /task: pipeline.

SpaiR/task-pipeline · 52 tokens

grill

Interrogate a plan or decision one question at a time before capture, keeping a decision-plus-rationale ledger, then route to the right capture skill.

SpaiR/task-pipeline · 33 tokens

designer

Settle the look before the pixels — audience and context first, then the base and the delta, taste settled by looking at real states, accessibility as the floor, one design language committed to DESIGN.md as tokens with roles. A command the user types, for work with an interface someone will see; standalone, no other…

donald-ada/workinggenius · 69 tokens

setup-working-genius

Per-repo configuration — pin the work-file directory, verify commands, and issue tracking, seed the project docs, and leave the pointer that tells every future session this project works this way.

donald-ada/workinggenius · 43 tokens