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/anettodev/github-plannerWrote 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/anettodev/github-planner/plan-preview)<a href="https://agentmods.dev/commands/anettodev/github-planner/plan-preview"><img src="https://agentmods.dev/badge/commands/anettodev/github-planner/plan-preview/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/anettodev/github-planner/plan-preview"><img src="https://agentmods.dev/badge/commands/anettodev/github-planner/plan-preview.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 | $0.00485 |
| Opus 5.5 | $0.00000 | $0.00194 |
| Sonnet 5.5 | $0.00000 | $0.00097 |
| Haiku 4.5 | $0.00000 | $0.00049 |
Grade A, and why
plan-preview 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 1mo 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
Preview Issues from Planning Document
Parse a planning document and show the issues that would be created, without creating anything. This is a safe, read-only operation.
Arguments: $ARGUMENTS (required — path to planning document, optional: --repo owner/repo)
Steps
1. Load Document
- Read the file at the provided path
- Detect document type: refactoring plan, migration plan, epic, tech debt inventory, or generic task list
2. Extract Tasks
Use the plan-to-issues skill to parse the document:
- Identify each phase, priority item, or numbered task
- Map task signals to labels
- Group by phase/priority → milestones
- Track dependencies between items
3. Display Each Issue
For each extracted issue, show:
---
### Issue: {title}
**Labels**: `refactor`, `priority: high`
**Milestone**: Phase 2: Config Cleanup
**Risk**: MEDIUM — touches build configuration
**Depends on**: Issue "Delete Supabase files"
#### Body Preview:
> ## Summary
> Remove Supabase SPM package and all environment variable references...
>
> ## Tasks
> - [ ] Delete `.remote(url: "...supabase-swift.git"...)` from packages array
> - [ ] Remove NUTRIA_SUPABASE_URL build settings
> ...
>
> ## Files Affected
> | Action | File |
> |---|---|
> | EDIT | `Project.swift` |
---
4. Show Summary Stats
## Summary
- **Total issues**: N
- **By priority**: X critical, Y high, Z medium, W low
- **Milestones**: Phase 1 (N issues), Phase 2 (N), ...
- **Labels used**: cleanup (N), refactor (N), ...
- **Estimated duplicates**: N (will be skipped)
Ready to create? Run: /plan-issues <same-path>
5. Suggest Improvements
If the source document has issues that would produce poor GitHub Issues, flag them:
- Tasks that are too vague (no concrete steps)
- Tasks that are too large (> 8 checklist items → suggest splitting)
- Missing risk assessment
- Missing file paths
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.
- 1mo ago First seen · 70 lines · 0 tokens per session scan A 4f8e2fbe126e
plan-preview is a command published in the GitHub repository anettodev/github-planner (2 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 485 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.
Other commands, from other repositories
task-hunter.skeleton
The user's input is resolved according to the following rules.
task-conductor.skeleton
/task-conductor top 5 -> /task-conductor plan top 5 /task-conductor all -> /task-conductor plan all /task-conductor 3,5,8 -> /task-conductor plan 3,5,8.
task-master.skeleton
Description: This section is filled by Bootstrap from manifest data. Required manifest fields: project.description, stack.primary Example output.
session-status.skeleton
This command reads session-.json files under .claude/tracking/sessions/ and summarizes which agent is on which task, in which phase, and what it is waiting on.
task-plan-review.skeleton
Purpose: Review plans created by /task-plan before /task-hunter implements them. Do not write product code. Correct plan quality, file references, acceptance checks, and scope.
deps
A command that analyzes the upstream and downstream relationships of a workflow record or local draft. It creates a list of direct links, dependency chains, blockers, evidence, and confidence levels.