Context Decays Faster Than Code
Two open-source skills for fewer "haven't we already discussed this?" moments.
Over the past few months I’ve been using a coding agent - Claude - to build and maintain a few software projects. Working with the tool daily, I noticed that context - documentation, architectural decisions, even the agent’s internal memories - is critical, and decays very quickly. Mistakes repeated themselves; old decisions would magically resurface. Where a senior developer would notice a stale document and think “that’s probably out of date”, an agent would read the same content and act on it.
These are familiar culprits, now with bigger impact:
Code drifts from declared architecture — codebases have guidelines, rules, and principles that are described in documentation. These can become obsolete if they’re not kept up to date. With the increased velocity of AI, this happens much more quickly.
Context drifts from code — in order to guide agent behaviour, users define context files like CLAUDE.md, cursorrules, etc. Agents also store internal memory files with key information. Agents can and do read all of this, so if they’re not up to date, you get undesirable behaviour.
To slow the decay I built a couple of skills.
architecture-drift-review
I run this after major feature work, before a release, and as a weekly job. It audits the codebase against its described architecture and verifies claims against code.
Three rules make it work:
Deterministic evidence first — “Seventeen modules open the database directly; the doc says one” is a finding. “Coupling seems high” is not.
No finding without an exit — every finding leaves with a fix, a new automated guard, or an explicit dated acceptance. A finding that ends as “should be looked at” will regress — that’s a failure of the review.
The doc is a byproduct — keeping ARCHITECTURE.md accurate happens in passing. If a review produces only an updated document, it described the system instead of making it more robust.
If the project has no architecture doc at all, the skill inverts: it scans the system and creates a baseline document, so the next run has something to audit.
agent-context-audit
I run this every time I’m getting unexpected behaviour from agents - the “haven’t we already discussed this?” moment. It’s tool-agnostic so Claude memories, CLAUDE.md, AGENTS.md, Cursor rules, Copilot instructions, decision-record statuses, skill files, permission and MCP configs are all checked.
If you run more than one tool, it also diffs their instruction files against each other, because CLAUDE.md and .cursorrules can drift too.
Two principles worth sharing:
The false-OK — when you verify a claim with a grep and get nothing back, that can be read as OK. But what if the file was moved? Empty is not necessarily OK, it can also mean unverified.
The graduation pass — a number of findings from my audits have graduated into deterministic checks that I run locally. By doing that, they evolve from “instructions the agent must remember” to “checks that can’t be ignored.” Bonus: they’re cheap, run without a network connection, and support both agents and human teams.
Give them a try
Both skills are MIT-licensed and easy to install:
npx skills add ken-talltree-io/agent-skills@architecture-drift-review
npx skills add ken-talltree-io/agent-skills@agent-context-auditThe repo is here: github.com/ken-talltree-io/agent-skills. The skills are extracted from real production use, so they’re likely biased to my work. Issues and PRs are welcome.