Borrowing it
Nothing to install: this file belongs to tomdwipo/claude-soul. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/tomdwipo/claude-soul/main/.claude/commands/plan-first.mdgit clone --depth 1 https://github.com/tomdwipo/claude-soulWrote 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/commands/tomdwipo/claude-soul/plan-first)<a href="https://agentmods.dev/commands/tomdwipo/claude-soul/plan-first"><img src="https://agentmods.dev/badge/commands/tomdwipo/claude-soul/plan-first.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 | $0.00000 | $0.00578 |
| Opus 5 | $0.00000 | $0.00289 |
| Sonnet 5 | $0.00000 | $0.00116 |
| Haiku 4.5 | $0.00000 | $0.00058 |
Grade A, and why
plan-first 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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Feature Planning First Command
Think Hard and Give me a few options for a $ARGUMENTS, starting with the simplest first. Don't code yet - just outline the approach and ask me which direction to take.
Investigate the codebase. Diagnose before prescribing. Before proposing options, read the relevant files, trace call sites, and confirm the actual current behavior. Never propose a fix based on assumptions — ground every option in what the code actually does today. State your diagnosis (root cause + evidence) before listing options.
add Philosophy behind with max 15 words. add pros and cons. add comparison matrix with other approaches. add expectation cost token generation. if from jira task get all information by using mcp atlassian, jira-attachment, video-to-image frame per second, include comments if have. if have link jira get detail all description and all comments if any. if the option can use the ascii diagram, do it.
Ticket Reality Check (when chat includes a Jira link)
Before proposing options, verify whether the ticket's issue still applies to the current codebase:
- Reproduce the issue against the current code. Read the relevant files / trace the code path described in the ticket and confirm whether the bug/gap is still present.
- Check for existing mitigation. Search for any guard, feature flag, defensive code, or recent commit that already addresses the issue (use
git log, grep, and the.docs/common-issues/catalog). - Decide one of three outcomes:
- Still broken, no mitigation → proceed with the normal
/plan-firstflow (options, diagnosis, etc.) — the plan should include the fix. - Already fixed or mitigated in the current codebase → do NOT propose options. Instead:
- State this finding in chat with evidence (file paths + line numbers + commit SHA if relevant).
- Use
mcp__atlassian__transitionJiraIssueto move the ticket to Done (or the equivalent closed state). - Use
mcp__atlassian__addCommentToJiraIssue(withcontentFormat: "adf") to add a comment summarising what mitigates it, with file/line evidence.
- Partial mitigation → call this out explicitly, then propose options only for the uncovered gap.
- Still broken, no mitigation → proceed with the normal
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 · 43 lines · 0 tokens per session scan A 10177918cdda
plan-first is a command published in the GitHub repository tomdwipo/claude-soul (24 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 578 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 2026-08-30.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.