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/superplan-md/superplan-plugin/superplan-routenpx skills add superplan-md/superplan-plugin --skill superplan-routegit clone --depth 1 https://github.com/superplan-md/superplan-pluginWhat 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 | $0.00037 | $0.02442 |
| Opus 5 | $0.00018 | $0.01221 |
| Sonnet 5 | $0.00007 | $0.00488 |
| Haiku 4.5 | $0.00004 | $0.00244 |
Grade A, and why
superplan-route 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.
How it starts
The opening of the file, as written. The whole thing — 281 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Route Work
Overview
Decide whether Superplan should engage at all, and if it should, choose structure depth aggressively enough to preserve visibility, verification quality, and delegation boundaries.
This skill owns the should_superplan_engage? decision and the initial depth choice.
This skill routes only. It does not shape artifacts. It does not execute work.
Fast Routing Rule
Route quickly and get out of the way.
- decide the lightest honest structure that preserves visibility and proof quality
- once depth is clear, hand off immediately instead of lingering in routing
- prefer a specific next owner over extra routing analysis
Trigger
Use when:
superplan-entryhas decided Superplan should at least evaluate engagement- the request may need
stay_out,direct,task,slice,program, or context-first routing - the main question is how much structure helps, not how the structure should be authored
Stay Out
Stay out when:
- the correct action is a direct answer or explanation
- no durable artifact, visibility benefit, or reusable context would help
- the work is conversational, ephemeral, or one-shot
- the request has already been satisfied without Superplan
If staying out:
- answer directly
- create no Superplan artifacts
- do not route to
superplan-shape
Inputs And Assumptions
Inputs:
- user request
- current repo and worktree state
- current
.superplan/state if present - workspace context quality and freshness
- whether the work looks greenfield, brownfield, or follow-on
Assumptions:
- structure depth is a workflow choice, not a philosophical category
- once Superplan engages, the burden of proof is on shallower structure for dense or multi-surface work
- graph truth, task-contract truth, and runtime truth are distinct
- context risk can outweigh depth risk in brownfield work
- routing should usually be possible without CLI command-surface exploration
Routing Heuristic
Use this decision order:
- Ask whether Superplan should stay out entirely.
- If not, ask whether the work is truly one bounded executable unit or whether structure loss would hide important surfaces.
- Ask whether missing or stale context is the real blocker.
- Choose the shallowest depth that still preserves trust, visibility, verification quality, and correct downstream shaping.
What ships with it
11 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.
- evals/01-stay-out-explanation.md 394 B
- evals/02-direct-lightweight-task.md 507 B
- evals/03-task-bounded-bugfix.md 579 B
- evals/04-slice-bounded-multistep.md 652 B
- evals/05-program-multi-workstream.md 778 B
- evals/06-context-first-brownfield.md 661 B
- evals/07-tiny-one-task-change.md 862 B
- evals/README.md 1.2 KB
- references/depth-modes.md 3.4 KB
- references/gotchas.md 1.7 KB
- references/stay-out-cases.md 1.7 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.
- 2d ago First seen · 281 lines · 37 tokens per session scan A 40f3352d41e6
superplan-route is a skill published in the GitHub repository superplan-md/superplan-plugin (72 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 37 tokens to every session and 2,442 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
evolve
Research-driven multi-cycle improvement director. Forms causal hypotheses about why scores are low, validates them with scout agents before attacking, dispatches axis-parallel fleet attacks, extracts transferable patterns, and runs indefinitely within a budget envelope. Accumulates a persistent belief model and…
improve
Autonomous quality improvement loop. Scores a target against a rubric, selects the highest-leverage axis, attacks it, verifies, documents, and loops. No pre-planning between iterations — each loop re-scores from scratch.
setup
First-run experience for the harness. Three modes: Recommended (guided, 3 min), Full Tour (guided + skill walkthrough, 8 min), and Express (zero questions, 30 sec). Installs hooks first, detects stack, configures harness.json, runs a live demo on real code, and prints a reference card.
ascii-diagram
Generate perfectly aligned ASCII diagrams — architecture, flow, sequence, box-and-arrow. Uses a programmatic character-grid approach so alignment is guaranteed by math, not token prediction. Includes post-render verification.
research
Focused research investigations. Converts questions into structured findings with confidence levels and source citations. Single agent by default; with --parallel (or when the question decomposes into 3+ independent angles) it spawns scout agents whose findings are compressed into a unified brief. Does not make…
triage
GitHub issue and PR investigator. Pulls open issues/PRs, classifies them, searches the codebase for root cause or reviews contributed code, proposes fixes with file:line references, and optionally implements fixes. Use for investigating GitHub issues and reviewing PRs; do NOT use for general code review unrelated to…