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.
npx skills add xiaohuxi/config-drift-guard-mcp --skill config-drift-remediationgit clone --depth 1 https://github.com/xiaohuxi/config-drift-guard-mcpWrote 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/xiaohuxi/config-drift-guard-mcp/config-drift-remediation)<a href="https://agentmods.dev/skills/xiaohuxi/config-drift-guard-mcp/config-drift-remediation"><img src="https://agentmods.dev/badge/skills/xiaohuxi/config-drift-guard-mcp/config-drift-remediation/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/xiaohuxi/config-drift-guard-mcp/config-drift-remediation"><img src="https://agentmods.dev/badge/skills/xiaohuxi/config-drift-guard-mcp/config-drift-remediation.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 | $0.00064 | $0.00608 |
| Opus 5 | $0.00032 | $0.00304 |
| Sonnet 5 | $0.00013 | $0.00122 |
| Haiku 4.5 | $0.00006 | $0.00061 |
Grade A, and why
config-drift-remediation 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Config Drift Remediation
Use config-drift-guard-mcp as the evidence source. Keep the workflow read-only and never write directly to production configuration.
Workflow
- Identify the baseline and target environments.
- Confirm the supplied files represent equivalent applications or components.
- Call
inspect_configfor both files. - Stop and report parsing errors, unsupported formats, duplicate keys, or inaccessible paths.
- Call
compare_configswith the baseline and target files. - Call
scan_secretsfor both files even when their secret fingerprints are identical; configuration drift and plaintext-secret exposure are separate risks. - Classify every difference:
- Expected environment difference: hostnames, endpoints, replicas, feature switches, or capacities that intentionally vary.
- Missing configuration: required key absent from the target.
- Type drift: equivalent key changes type, such as number to string.
- Structure drift: renamed, moved, or split key paths.
- Sensitive configuration risk: plaintext secret, private key, credential-bearing URL, or unexpected secret fingerprint change.
- Rank remediation work:
- Critical: exposed credentials or unexpected secret changes.
- High: missing required keys, type drift, or incompatible structure.
- Medium: non-sensitive value changes needing confirmation.
- Low: documented expected differences.
- Produce the report using references/report-template.md.
- End with a verification checklist and unresolved decisions.
Guardrails
- Never reveal secret plaintext or attempt to recover it; use only MCP-provided masks and fingerprints.
- Never copy a secret from one environment into another.
- Never assume every difference is an error.
- Never modify remote configuration, commit files, or deploy changes without an explicit separate request.
- Prefer key-level patch guidance over rewriting whole files.
- Preserve target-environment values that are documented as intentional.
- Recommend secret rotation when plaintext credentials are detected.
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.
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.
- 12d ago First seen · 64 lines · 64 tokens per session scan A 810569a5c9ef
config-drift-remediation is a skill published in the GitHub repository xiaohuxi/config-drift-guard-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 64 tokens to every session and 608 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 2026-08-31.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.