context-rot-prevention

A handoff tool for moving an overgrown coding-agent session into a fresh context. Context means the conversation and working information the agent can keep available while working.

In plain words
What is it for?
Use it during long tasks, when the context window is nearly full, or when continuing the work in a fresh session is preferable.
Why use it?
It helps prevent quality loss when a session has accumulated many turns, files, or repeated rereading. A new context can continue from a prepared handoff.

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/xyruscode/ai-sync/context-rot-prevention
Any agent
npx skills add XyrusCode/ai-sync --skill context-rot-prevention
Clone the repo
git clone --depth 1 https://github.com/XyrusCode/ai-sync

Made for: Claude Code, Codex.

Per session 83 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 667 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 $0.00083 $0.00667
Opus 5 $0.00042 $0.00333
Sonnet 5 $0.00017 $0.00133
Haiku 4.5 $0.00008 $0.00067

Measured 2d ago against content hash 7313a2e1b203, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

context-rot-prevention 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.

skills/context-rot-prevention/SKILL.md · 31 lines

How it starts

The opening of the file, as written. The whole thing — 31 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Context Rot Prevention

Prevents context rot: hands a session that has grown heavy off to a fresh, nested context (auto-spawn when the tool allows it, otherwise a self-contained handoff prompt) before output quality drops. Full procedure, rationale, and the handoff template live in docs/context-rot.md.

When to use

  • A session has many turns, many distinct files read or edited, or keeps re-reading files it already loaded.
  • You catch yourself re-deriving state you already settled earlier in the conversation.
  • Token-usage telemetry (where the tool exposes it) shows the context window is near the cap.
  • The user asks to split, continue in a fresh session, or hand the thread off.
  • A slice of work is done and the next slice is better done with a clean context.

Don't use for

  • Short or one-shot tasks that will finish in the current context. Splitting is overhead.
  • Near-complete work. A handoff costs more than seeing it through.
  • Parallel fan-out of subtasks into many agents. That is workflow-orchestration.md / the Workflow tool, not a continuity handoff.

Decision

  1. Assess the envelope. Weight the cumulative signals (turns, working-set size, re-deriving state, telemetry if present). No single number decides; read the shape.
  2. Checkpoint. Commit or otherwise leave the tree in a known state; write a memory note for non-obvious decisions.
  3. Split: use a native nested-session primitive when available and safe. This Copilot app: create_session / send_session_message. Claude Code: claude --continue or a typed subagent. Codex: codex resume. Cross-CLI read-only fan-out: agent orchestrator.
  4. Else: emit a self-contained handoff prompt. Write it so a fresh session with zero prior context can continue immediately, and tell the user where it goes. Use the template in the doc.

The handoff prompt must carry: goal, done-so-far, current state (branch, HEAD, key files), decisions already made, exact next step, and where to re-derive context.

Read the full file on GitHub · 31 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. 2d ago First seen · 31 lines · 83 tokens per session scan A 7313a2e1b203

Subscribe to this mod's changes

context-rot-prevention is a skill published in the GitHub repository XyrusCode/ai-sync (2 stars, last pushed 2d ago), licensed MIT. It adds 83 tokens to every session and 667 once invoked, about $0.0004 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

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 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