context-degradation-review

context-degradation-review is a skill for Codex from markoblogo/abvx-agent-skills. It costs 59 tokens per session (609 once invoked), scanned A, original, MIT.

A review guide for spotting problems caused by too much, stale, or conflicting context in an agent session. Context poisoning means incorrect or irrelevant information affects the agent's decisions.

In plain words
What is it for?
Use it before long-session handoffs, changes to skills or memory, or other work where accumulated context could degrade the agent's behavior.
Why use it?
It helps catch lost instructions, stale work carried over from an earlier task, distracting material, and conflicts between sources before they cause mistakes.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: mentions AGENTS.md.

Good fit Use it before long-session handoffs, changes to skills or memory, or other work where accumulated context could degrade the agent's behavior.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/markoblogo/abvx-agent-skills/context-degradation-review
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.

Any agent
npx skills add markoblogo/abvx-agent-skills --skill context-degradation-review
Clone the repo
git clone --depth 1 https://github.com/markoblogo/abvx-agent-skills

Made for: Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for context-degradation-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/markoblogo/abvx-agent-skills/context-degradation-review/github.svg)](https://agentmods.dev/skills/markoblogo/abvx-agent-skills/context-degradation-review)
Your own site
<a href="https://agentmods.dev/skills/markoblogo/abvx-agent-skills/context-degradation-review"><img src="https://agentmods.dev/badge/skills/markoblogo/abvx-agent-skills/context-degradation-review/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for context-degradation-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/markoblogo/abvx-agent-skills/context-degradation-review"><img src="https://agentmods.dev/badge/skills/markoblogo/abvx-agent-skills/context-degradation-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 609 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00059 $0.00609
Opus 5 $0.00030 $0.00304
Sonnet 5 $0.00012 $0.00122
Haiku 4.5 $0.00006 $0.00061

Measured 11d ago against content hash 46ae36224617, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

context-degradation-review 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 11d 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-degradation-review/SKILL.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Context Degradation Review

Use this skill to find when the context itself is making the agent worse.

Use When

  • a long session, handoff, or compaction summary may contain stale or conflicting instructions;
  • a SET bundle, AGENTS.md, SKILL.md, or memory write mixes useful facts with outdated task history;
  • the agent keeps optimizing for irrelevant prior work;
  • tool output, logs, or retrieved docs may bury the decisive evidence;
  • multiple sources disagree and the answer treats them as one coherent contract.

Failure Modes

  • lost-in-middle: key constraints are present but buried between low-signal material.
  • context-poisoning: incorrect, stale, or speculative text is treated as authority.
  • distraction: large but irrelevant context pulls work away from the current task.
  • context-clash: two instructions, docs, memories, or artifacts conflict.
  • stale-carryover: a prior goal continues after the user changed or stopped the task.

Workflow

  1. Identify the active task, current authority order, and expected output.
  2. List the context sources used: user message, repo files, memory, docs, tool output, web sources, generated summaries.
  3. Mark each source as authoritative, supporting, stale-risk, or irrelevant.
  4. Check for the five failure modes above.
  5. Propose the smallest context repair:
    • remove or ignore a stale source;
    • promote the decisive constraint near the active plan;
    • split task history from durable guidance;
    • ask for clarification only when the conflict blocks action;
    • rewrite a handoff or memory proposal with source boundaries.
  6. Continue only after the active context is narrow enough to act safely.

Output Shape

Use:

  • verdict: CONTEXT_OK, CONTEXT_DEGRADED, or CONTEXT_BLOCKED;
  • active task;
  • context sources reviewed;
  • degradation findings by mode;
  • smallest repair;
  • remaining risk.

Guardrails

  • Do not use this as a generic writing critique.
  • Do not remove context just because it is long; remove or demote it only when it is low-signal, stale, or conflicting.
  • Do not treat memory as higher authority than the current user message.
  • Do not let stale rollout context override an explicit stop, pause, or changed task.

Read the full file on GitHub · 65 lines

Files

What ships with it

2 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. 11d ago First seen · 65 lines · 59 tokens per session scan A 46ae36224617

Subscribe to this mod's changes

context-degradation-review is a skill published in the GitHub repository markoblogo/abvx-agent-skills (16 stars, last pushed 2d ago), licensed MIT. It adds 59 tokens to every session and 609 once invoked, about $0.0003 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.