superplan-guard

A small regression-checking workflow for protecting an important software behavior after a fix or change. A regression is when previously working behavior breaks again.

In plain words
What is it for?
It is for choosing and adding a focused test or verification check after fixing a bug or changing a workflow contract. It helps ensure the guard checks user-visible behavior rather than implementation details.
Why use it?
It focuses attention on the smallest test or proof that would expose the same failure in the future. This avoids broad, noisy tests that do not protect the actual contract.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/superplan-md/superplan-plugin/superplan-guard
Any agent
npx skills add superplan-md/superplan-plugin --skill superplan-guard
Clone the repo
git clone --depth 1 https://github.com/superplan-md/superplan-plugin

Made for: Claude Code, Codex.

Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 258 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00033 $0.00258
Opus 5 $0.00016 $0.00129
Sonnet 5 $0.00007 $0.00052
Haiku 4.5 $0.00003 $0.00026

Measured 2d ago against content hash 041661740e08, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

superplan-guard 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.

output/skills/superplan-guard/SKILL.md · 42 lines

What it actually says

Regression Guarding

Overview

Every important fix or behavior change should leave behind a guard.

Trigger

Use when:

  • a bug was fixed
  • a workflow contract changed
  • the agent asks "what test should protect this?"
  • a failure revealed a missing proof path

Core Rules

  • identify the exact behavior worth protecting
  • add the smallest credible guard that would fail before the bug returns
  • prefer the repo's existing test or verification style
  • guard the contract, not the incidental implementation
  • keep the guard close to the changed behavior when possible

Forbidden Behavior

  • adding broad noisy tests when one focused check would do
  • testing implementation trivia instead of user-visible or contract-visible behavior
  • skipping the guard because the fix feels obvious

Handoff

Likely follow-ons:

  • superplan-tdd when the guard should be written before the full fix
  • superplan-verify when the new guard becomes part of the proof path
  • superplan-postmortem when the missing guard revealed a broader process gap
Changes

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.

  1. 2d ago First seen · 42 lines · 33 tokens per session scan A 041661740e08

Subscribe to this mod's changes

superplan-guard is a skill published in the GitHub repository superplan-md/superplan-plugin (72 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 33 tokens to every session and 258 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.

Related

Other skills, from other repositories

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.

SethGammon/Citadel · 48 tokens

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.

SethGammon/Citadel · 69 tokens

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…

SethGammon/Citadel · 60 tokens

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…

SethGammon/Citadel · 67 tokens

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.

SethGammon/Citadel · 43 tokens

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…

SethGammon/Citadel · 71 tokens