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-entrynpx skills add superplan-md/superplan-plugin --skill superplan-entrygit 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 | $0.00038 | $0.05585 |
| Opus 5 | $0.00019 | $0.02792 |
| Sonnet 5 | $0.00008 | $0.01117 |
| Haiku 4.5 | $0.00004 | $0.00558 |
Grade A, and why
superplan-entry 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 — 461 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Using Superplan
Overview
Universal outer workflow layer for Superplan.
Internal category: workflow-control / execution-orchestration.
This skill replaces the entry discipline that using-superpowers used to provide.
Keep it small, but not permissive. Its job is to decide whether Superplan should meaningfully participate, whether readiness is missing, and which workflow phase owns the next responsibility.
If there is a meaningful chance that the request is repo work, use this skill before implementation, broad repo exploration, or clarifying questions.
Fast Trigger Rule
Treat this as an early trigger, not a late fallback.
- if there is even a modest chance the request is repo work, load this skill first
- do not wait for "proof" that the work is complex before routing
- do not keep the work inside
superplan-entryonce a narrower phase owner is clear
The value of this skill is early discrimination, not broad control.
Subagent Guard
If you were dispatched as a bounded subagent to execute, investigate, or verify a specific task, skip this skill.
Do not rerun top-level Superplan entry routing from inside a task-owned subagent unless the assignment explicitly says to reevaluate engagement.
Instruction Priority
Follow this order:
- direct user instructions and repo instructions such as
AGENTS.md,CLAUDE.md, or equivalent host guidance superplan-entryentry discipline- generic default behavior
If a repo instruction conflicts with a default Superplan habit, obey the user or repo instruction.
Mandatory Discipline
Treat entry routing as mandatory first-contact discipline, not optional advice.
- do not start implementing first and promise to structure later
- do not start broad repo exploration first and claim routing can happen after
- do not ask clarifying questions first when the real first question is whether Superplan should engage
- do not rationalize that a dense request is "probably just one task" without checking
- do not let "smallest useful depth" become a reason to skip an explicit route result
- do not begin execution for newly requested repo work until the route and shape chain is complete
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.
- evals/01-fresh-request-active-task.md 928 B
- evals/02-interrupted-session-different-request.md 882 B
- evals/03-unrelated-dirty-worktree.md 979 B
- evals/README.md 3.8 KB
- references/entry-discipline.md 2.6 KB
- references/gotchas.md 1.1 KB
- references/memory-and-measurement.md 1.8 KB
- references/readiness.md 3.6 KB
- references/routing-boundaries.md 2.8 KB
- references/setup-config.md 1.8 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 · 461 lines · 38 tokens per session scan A 879bbb152572
superplan-entry is a skill published in the GitHub repository superplan-md/superplan-plugin (72 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 38 tokens to every session and 5,585 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…