superplan-context

A workflow for recording stable information about a software project, such as its architecture, conventions, and recurring problems.

In plain words
What is it for?
Use it to create or update reusable project context for long-running or older codebases.
Why use it?
It prevents developers and coding agents from having to rediscover important project knowledge during every task.

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

Made for: Claude Code, Codex.

Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 757 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 $0.00032 $0.00757
Opus 5 $0.00016 $0.00378
Sonnet 5 $0.00006 $0.00151
Haiku 4.5 $0.00003 $0.00076

Measured 2d ago against content hash 7d9ab16816fa, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

superplan-context 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-context/SKILL.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Context Bootstrap Sync

Overview

Create or update durable workspace context that should persist beyond the current task.

This skill owns Superplan's durable context layer, not active task state.

Trigger

Use when:

  • serious work begins and useful workspace context is missing
  • brownfield work would otherwise start cold
  • meaningful durable context drift is discovered

Stay Out

Do not run when:

  • the work is tiny
  • the observation is transient and task-specific
  • the information is unlikely to matter again
  • the request is purely conversational

Inputs And Assumptions

Inputs:

  • current repo structure
  • existing .superplan/context/ if present
  • current task or request
  • stable findings gathered during repo exploration

Assumptions:

  • context should contain stable reusable truth
  • transient task, graph, and runtime state belong elsewhere

Stable Layer Model

Keep these layers distinct:

  • stable context: reusable architecture, conventions, workflows, and non-obvious repo truths
  • active work: plans, specs, tasks, and current trajectory decisions
  • live runtime: in-progress execution state, blockers, and review movement

Use .superplan/context/README.md as the entrypoint and .superplan/context/INDEX.md as the routing layer into deeper context docs.

See references/context-indexing.md and references/durable-context-rules.md.

Allowed Actions

  • create initial durable workspace context
  • update stale context when important drift is found
  • summarize what changed in context
  • keep the context layer proportionate and reusable
  • use superplan context doc set <doc-slug> --stdin --json to write context docs
  • use superplan context log add --kind <decision|gotcha> --content "..." --json to append workspace logs

Forbidden Behavior

  • storing transient runtime state as durable context
  • rewriting the whole context layer casually
  • turning every observation into context
  • hijacking active task shaping or execution responsibilities
  • editing files under .superplan/ directly when a CLI command can own the write

Read the full file on GitHub · 122 lines

Files

What ships with it

4 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.

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 · 122 lines · 32 tokens per session scan A 7d9ab16816fa

Subscribe to this mod's changes

superplan-context is a skill published in the GitHub repository superplan-md/superplan-plugin (72 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 32 tokens to every session and 757 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

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

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

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

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

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