Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add bengous/claude-code-plugins/plugin install context-managementWrote 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.
[](https://agentmods.dev/skills/bengous/claude-code-plugins/agent-docs-drift)<a href="https://agentmods.dev/skills/bengous/claude-code-plugins/agent-docs-drift"><img src="https://agentmods.dev/badge/skills/bengous/claude-code-plugins/agent-docs-drift/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.
<a href="https://agentmods.dev/skills/bengous/claude-code-plugins/agent-docs-drift"><img src="https://agentmods.dev/badge/skills/bengous/claude-code-plugins/agent-docs-drift.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00044 | $0.00314 |
| Opus 5.5 | $0.00018 | $0.00126 |
| Sonnet 5.5 | $0.00009 | $0.00063 |
| Haiku 4.5 | $0.00004 | $0.00031 |
Grade A, and why
agent-docs-drift scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Agent Docs Drift
Audits CLAUDE.md, AGENTS.md and .claude/rules/ against the commits since any of them last changed. Never commits: the user commits.
-
Run the report:
"${CLAUDE_PLUGIN_ROOT}/scripts/agent-docs-drift.ts"A non-zero exit prints the reason on stderr: relay it and stop. When no doc file is tracked, point the user to
/init. An empty window: relay the report's result and stop. -
Follow the report's protocol. In Claude Code:
- a subagent is an Agent tool call with
subagent_type: Explore, briefed with the baseline, protocol step 3, the audit set and its share of commits; - the approval question is an AskUserQuestion (apply all / cherry-pick / reject);
- general quality improvement of the docs belongs to
/context-audit.
- a subagent is an Agent tool call with
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.
- 1mo ago First seen · 33 lines · 44 tokens per session scan A 7a8c3d047b4e
agent-docs-drift is a skill published in the GitHub repository bengous/claude-code-plugins (5 stars, last pushed today), licensed MIT. It adds 44 tokens to every session and 314 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-16.
Other skills, from other repositories
development-workflow
Detailed development workflow with modular patterns for git, review, testing, and deployment.
git-workflow
Git operations: commits, branches, PRs, and conflict resolution.
stepwise-task-execution
Master workflow for an implementation task. Use when you pick up any task or bug that changes product code, including a needrevision bounce.
incremental-commits
Commit boundaries and messages on a task branch. Use when deciding where to cut a commit or how to word one while implementing.
ship-it
A GitHub workflow for finishing an implemented issue: commit the relevant changes, push a branch, create a pull request, merge it, and close the issue. GitHub is a service for hosting code and reviewing changes, and a pull request is a proposed change for review.
git-expert
Expert-level Git version control with advanced workflows, branching strategies, and best practices for team collaboration. Use when the user mentions version control, collaboration, or workflow, or when the task involves Essential Git Commands, Advanced Git Techniques, Branching Strategies, or Conflict Resolution.