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.
git clone --depth 1 https://github.com/hgahlot/claude-flowWrote 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/hgahlot/claude-flow/plan)<a href="https://agentmods.dev/commands/hgahlot/claude-flow/plan"><img src="https://agentmods.dev/badge/commands/hgahlot/claude-flow/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.
<a href="https://agentmods.dev/commands/hgahlot/claude-flow/plan"><img src="https://agentmods.dev/badge/commands/hgahlot/claude-flow/plan.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00499 |
| Opus 5.5 | $0.00000 | $0.00200 |
| Sonnet 5.5 | $0.00000 | $0.00100 |
| Haiku 4.5 | $0.00000 | $0.00050 |
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 2mo 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.
What it actually says
/plan — Spec-Driven Task Planning
Generate a structured task plan for the current work item using XML format optimized for Claude comprehension.
Instructions
- Clarify the goal — restate what needs to be built/fixed/changed in one sentence
- Identify constraints — review REQUIREMENTS.md for relevant constraints
- Break into tasks — 2–5 minute atomic tasks, each with explicit file paths
- Sequence by dependency — mark which tasks can run in parallel (wave-based)
- Add verification steps — each task ends with a verifiable check
Output Format
<plan>
<goal>One-sentence description of what this plan achieves</goal>
<context>
<files>List of files that will be created or modified</files>
<requirements>Relevant requirements from REQUIREMENTS.md</requirements>
<constraints>Key constraints to respect</constraints>
</context>
<wave id="1" description="Foundation — must complete before wave 2">
<task id="1.1">
<description>What to do</description>
<file>path/to/file.ext</file>
<action>create|edit|delete</action>
<verify>How to confirm this task is done correctly</verify>
</task>
</wave>
<wave id="2" description="Implementation — depends on wave 1">
<task id="2.1">
<description>What to do</description>
<file>path/to/file.ext</file>
<action>create|edit|delete</action>
<verify>Run: <command> — expected output: <output></verify>
</task>
</wave>
<wave id="3" description="Verification">
<task id="3.1">
<description>Run full test suite</description>
<verify>All tests pass. Zero failures.</verify>
</task>
</wave>
</plan>
Rules
- Each task must reference a specific file path
- Verification steps must be runnable (commands with expected output)
- No task should take more than 5 minutes
- Wave 1 tasks must be completable without any other task in the plan
- After outputting the plan, ask: "Shall I proceed with Wave 1?"
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.
- 2mo ago First seen · 58 lines · 0 tokens per session scan A 9d90655871f2
plan is a command published in the GitHub repository hgahlot/claude-flow (55 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 499 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.
plan compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| planhgahlot/claude-flow | Command | 55 | 7mo ago | MIT | A | 0 | Claude Code |
| checklistgithub/spec-kit | Command | 148k | yesterday | MIT | A | 13 | Claude Code |
| clarifygithub/spec-kit | Command | 148k | yesterday | MIT | A | 27 | Claude Code |
| specifygithub/spec-kit | Command | 148k | yesterday | MIT | A | 13 | Claude Code |
| analyzegithub/spec-kit | Command | 148k | yesterday | MIT | A | 26 | Claude Code |
| convergegithub/spec-kit | Command | 148k | yesterday | MIT | A | 35 | Claude Code |
| implementgithub/spec-kit | Command | 148k | yesterday | MIT | A | 14 | Claude Code |