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.
npx agentmods add skills/melodic-software/claude-code-plugins/plannpx skills add melodic-software/claude-code-plugins --skill plangit clone --depth 1 https://github.com/melodic-software/claude-code-pluginsWrote 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/skills/melodic-software/claude-code-plugins/plan)<a href="https://agentmods.dev/skills/melodic-software/claude-code-plugins/plan"><img src="https://agentmods.dev/badge/skills/melodic-software/claude-code-plugins/plan.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 | $0.00100 | $0.09091 |
| Opus 5 | $0.00050 | $0.04546 |
| Sonnet 5 | $0.00020 | $0.01818 |
| Haiku 4.5 | $0.00010 | $0.00909 |
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 yesterday.
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 — 303 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pre-computed context
Current branch: !git branch --show-current 2>/dev/null || echo "unknown"
Recent commits: !git log --oneline -5 2>/dev/null || echo "no commits"
Working tree status (empty = clean): !{ git status --porcelain 2>/dev/null || echo "(git status unavailable)"; } | head -10
Variables
Arguments: $ARGUMENTS
Purpose
Plans fail when they skip rationale, ignore blast radius, or rush past approval gates. This skill structures the planning step so that every implementation starts with a clear design, with evidence, test strategy, and user sign-off, before a single line of code is written.
This is not Claude Code's built-in plan mode (shift+tab). That is a permission mode: read-only exploration. This skill is a planning discipline: the intellectual work of designing an approach, assessing risks, and getting approval. The two complement each other: use plan mode for safe exploration during planning, and this skill for the structured process around it.
This skill takes the outputs of the earlier stages, exploration (local understanding), research (external evidence), and /planning:design (types, contracts, module boundaries, package topology), and produces a plan the user approves before execution begins.
Philosophy: a 2-minute plan prevents a 20-minute rework cycle. The depth of planning should match the blast radius. A one-file fix gets a brief plan; a cross-cutting architecture change gets a full plan with stress-testing and research-iterate loops.
Emit checklist
For multi-step planning sessions (almost always: steps 1-5 of this skill), copy templates/checklist.md into the topic's memory slice as <memory_dir>/<topic-slug>/plan-checklist.md (default .work/). Tick each - [ ] as the corresponding step completes. Step 3 (Plan stress-test via fresh-context sub-agent) and Step 5 (Present for approval) are non-negotiable ticks. Stress-test before presenting, always.
Skip when: mid-flight review replan only. Append a dated scope-change note and revise the PLAN phases instead; do not spawn a second checklist file.
What ships with it
10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- context/close-out.md 3.7 KB
- context/plan-reviewer.md 2.8 KB
- context/plan-template.md 18 KB
- context/research-iterate.md 3.5 KB
- context/review-mode.md 692 B
- context/stress-test-triggers.md 3.0 KB
- context/tag-decisions.md 3.5 KB
- evals/evals.json 9.0 KB
- templates/checklist.md 1.9 KB
- templates/plan-md-anatomy.md 2.2 KB
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.
- yesterday First seen · 303 lines · 100 tokens per session scan A f77c4e8b5d04
plan is a skill published in the GitHub repository melodic-software/claude-code-plugins (15 stars, last pushed today), licensed MIT. It adds 100 tokens to every session and 9,091 once invoked, about $0.0005 per session on Opus 5. 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 2026-09-03.
Other skills, from other repositories
parallel-orchestrator
Manage parallel Claude Code workstreams using git worktrees. Use when: splitting large tasks across multiple workers, coordinating parallel development, monitoring worker progress, integrating completed work, analyzing work item documents (code reviews, issue lists). Triggers: parallel, orchestrator, worktrees…
parallel-worker
Execute focused implementation tasks in a parallel workflow. Use when: working on assigned files in a worktree, making checkpoint commits, signaling dependencies or blockers, completing orchestrator-assigned tasks. Triggers: worker, checkpoint, worktree, assigned scope, commit prefix, parallel task.
generate-tree-structure
For tree/maze generation: spanning trees, random mazes, graph coverage. Uses frontier-based exploration with configurable traversal order.
optimize-local-search
For NP-hard optimization: TSP, scheduling, assignment problems. Uses greedy construction + local improvement (2-opt, hill climbing).
pass-function-as-arg
For generic algorithms: strategy pattern, callbacks, configurable behavior. Pass functions as parameters to customize algorithm behavior.
solve-constraint-puzzle
For constraint satisfaction: Sudoku, scheduling, N-queens, logic puzzles, SAT-like problems, assignment problems. Uses propagate-then-search pattern.