A task-list review command that checks a JSON file containing planned coding tasks before implementation begins. It reports whether the list is complete and suitable for coding.

Use it to validate the task list produced during planning. It is also used as a required check before the coding phase.

It catches invalid structure, missing fields, duplicate task identifiers, and unsupported values before developers rely on the list. This prevents coding from starting with an unusable plan.

plan-check — Command by Caspian-Sun

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.

agentmods

npx agentmods add commands/caspian-sun/claude-code-workflow/plan-check

Clone the repo

git clone --depth 1 https://github.com/Caspian-Sun/claude-code-workflow

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 2,072 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. 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.

Model	Per session	Once invoked
Fable 5	$0.00000	$0.02072
Opus 5	$0.00000	$0.01036
Sonnet 5	$0.00000	$0.00414
Haiku 4.5	$0.00000	$0.00207

Measured 2d ago against content hash 66c82e1d3108, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

plan-check 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.

.claude/commands/plan-check.md · 150 lines

How it starts

The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are now a task list completeness checker. Run hard-gate checks against the input tasks.json and output whether it can proceed to the /code coding phase.

Applicable Scenarios

User wants to verify if a task list is executable — quick health check after /plan generates it
Mandatory pre-check for /code — /code must run this command first; if it fails, coding is refused

Input

@docs/tasks/tasks-xxx.json path → read directly
No path → stop and ask: "Please specify the task list path, e.g.: /plan-check @docs/tasks/tasks-login-2026-04-15.json"

Checks (run in order, no short-circuit — report all issues at once)

Check 1: Valid Structure (P0)

Validate JSON structure:

Required fields: moduleCode / prdRef / tasks[] / createdAt
Each item in tasks[] must contain: taskId / type / name / filePath / description / prdRef / businessRules / acceptanceCriteria / status
type must be one of: precondition | gen-api | api | mock | constants | utils | locale | config | model | store | hook | wrapper | component | page
status must be one of: pending | in-progress | done | blocked
taskId must be globally unique (no duplicates)

Note: Infrastructure types (precondition / constants / utils / locale / config / model / wrapper) are for i18n, route guards, access config, constants, utilities, runtime config, and other non-api/component/page engineering files.

On failure: list the violating taskIds and specific field issues

Check 2: Valid Dependency Graph (P0)

Perform graph-theory validation on tasks[].dependencies arrays:

No dangling references: every taskId in dependencies must actually exist
No circular dependencies: detect cycles via topological sort
No forward references: dependent taskId must appear before the current taskId in array order

On failure: list problematic edges (A → B does not exist / A → B → A cycle / A appears before B but depends on B)

Read the full file on GitHub · 150 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.

2d ago First seen · 150 lines · 0 tokens per session scan A 66c82e1d3108

Subscribe to this mod's changes

plan-check is a command published in the GitHub repository Caspian-Sun/claude-code-workflow (10 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,072 tokens. 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.

Planning agent-sdk ai-agent ai-workflow claude-code forward-deployed-engineering methodology

plan-check

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Applicable Scenarios

Input

Checks (run in order, no short-circuit — report all issues at once)

Check 1: Valid Structure (P0)

Check 2: Valid Dependency Graph (P0)

What this file has done since we first saw it

Other commands, from other repositories

vibe-agents

mass-line

sync-linear

ship

fest-show

generate-rules