hyper-clear

A session-reset tool that clears the current conversation context while preserving selected project documents. It is designed for starting a fresh feature cycle without old discussion affecting the work.

In plain words
What is it for?
Use it between feature cycles or after an audit when you want a clean conversation. It can also be called repeatedly without changing the result.
Why use it?
It reduces confusion caused by earlier feature work, decisions, or instructions carrying into a new 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/tjmustard/hypergraph-coding-agent-framework/hyper-clear
Any agent
npx skills add tjmustard/Hypergraph-Coding-Agent-Framework --skill hyper-clear
Clone the repo
git clone --depth 1 https://github.com/tjmustard/Hypergraph-Coding-Agent-Framework

Made for: Claude Code, Codex.

Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,038 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 $0.00025 $0.01038
Opus 5 $0.00013 $0.00519
Sonnet 5 $0.00005 $0.00208
Haiku 4.5 $0.00003 $0.00104

Measured yesterday against content hash 4bcf76b9b46a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

hyper-clear 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.

.agents/skills/hyper-clear/SKILL.md · 147 lines

How it starts

The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Clear Context

This skill clears session context to prevent cross-feature bleed and allow fresh feature cycles. It is idempotent and safe to invoke at any time.

When to use this skill

  • Automatically after /hyper-audit completes (post-audit hook).
  • Manually at any time to reset session context between feature cycles.
  • Whenever you want to guarantee a fresh session without old conversation history contaminating the next phase.

How to use it

Step 1: Check Idempotency State

Read .agents/memory/activeContext.md:

  • If the session_cleared flag is true: /hyper-clear has already been called in this session. Return OK (idempotent, no action needed).
  • If the session_cleared flag is false or missing: Proceed to Step 2.

Step 2: Flush Conversation History

Clear conversation history by starting a new conversation in Claude Code:

  1. Inform the user: "Context cleared. Starting fresh session for next feature cycle."
  2. The user manually starts a new conversation thread (or you can suggest: "You may now /hyper-clear by opening a new chat window").

Specification Retained:

  • spec/compiled/architecture.yml — preserved
  • spec/compiled/SuperPRD.md — preserved
  • spec/compiled/MiniPRD_*.md — preserved
  • .agents/ framework code — preserved
  • Performance metrics (heuristics, model overrides) — preserved

Session State Flushed:

  • Conversation history from this context window — cleared
  • Temporary working memory — cleared

Step 3: Update Idempotency Tracker

Edit .agents/memory/activeContext.md:

## Session State
- session_cleared: true
- cleared_at: [CURRENT_TIMESTAMP]
- cleared_by: /hyper-clear command

Step 4: Log Result

Output to user:

========================================
✅ CONTEXT CLEARED
========================================
Session context flushed.
Architecture.yml and spec/compiled/ retained.
Ready for next feature cycle.

Idempotency: This is a fresh clear.
(Calling /hyper-clear again will be a no-op.)
========================================

Read the full file on GitHub · 147 lines

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. yesterday First seen · 147 lines · 25 tokens per session scan A 4bcf76b9b46a

Subscribe to this mod's changes

hyper-clear is a skill published in the GitHub repository tjmustard/Hypergraph-Coding-Agent-Framework (2 stars, last pushed 1mo ago), licensed MIT. It adds 25 tokens to every session and 1,038 once invoked, about $0.0001 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens