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 sawrus/agent-guides --skill drift-detectiongit clone --depth 1 https://github.com/sawrus/agent-guidesWrote 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/sawrus/agent-guides/drift-detection)<a href="https://agentmods.dev/skills/sawrus/agent-guides/drift-detection"><img src="https://agentmods.dev/badge/skills/sawrus/agent-guides/drift-detection/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/sawrus/agent-guides/drift-detection"><img src="https://agentmods.dev/badge/skills/sawrus/agent-guides/drift-detection.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Data Exfiltration · line 113 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00054 | $0.00681 |
| Opus 5.5 | $0.00022 | $0.00272 |
| Sonnet 5.5 | $0.00011 | $0.00136 |
| Haiku 4.5 | $0.00005 | $0.00068 |
Grade A, and why
drift-detection 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 today.
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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Terraform drift: detect and resolve
Drift means the real resources differ from the code. Resolve it in code; do not hide it.
1. Detect
terraform init -input=false
terraform plan -input=false -lock=false -detailed-exitcode -out=drift.tfplan
echo $? # 0 = no changes, 1 = error, 2 = changes (drift or unapplied code)
terraform show -no-color drift.tfplan > drift.txt
Use tofu instead of terraform if the project uses OpenTofu. Run against every environment directory or
workspace that the task names.
2. Classify each changed resource
Read drift.txt and sort every resource into one class:
- Unapplied code — the code changed on the default branch but nobody applied it. Check
git logfor the module. Resolution: apply through the normal pipeline. - Manual change — someone changed the resource in the console or with a CLI. Check the cloud audit log (CloudTrail, GCP Audit Logs, Azure Activity Log) for the actor and time.
- Provider-side default — the provider or service sets a value the code does not set, and the plan shows it
on every run. Resolution: set the value in code, or add the attribute to
lifecycle { ignore_changes = [...] }with a comment that names the reason. - Resource outside state — the resource exists but state does not track it.
3. Resolve
- Manual change that must stay: copy the value into the code, then run
planagain until it shows no change. - Manual change that must go: keep the code. The next apply reverts it. Ask the user first before that apply.
- Resource outside state: add an
importblock and plan:
import {
to = aws_s3_bucket.logs
id = "group-service-logs"
}
- Changed outputs or data sources only: run
terraform apply -refresh-onlyto update state. Ask the user first; it writes state. - Never run
terraform state rmto make drift disappear unless the user wants to stop managing the resource.
4. Verify
- Run step 1 again. The exit code must be
0, or every remaining change must be a planned code change. - Commit the code changes with the drift cause in the commit body.
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.
- today Changed · -116 lines · +25 tokens per session 4ada851fe7ad
- 1mo ago First seen · 179 lines · 29 tokens per session scan A d127289bb9f6
drift-detection is a skill published in the GitHub repository sawrus/agent-guides (19 stars, last pushed today), licensed MIT. It adds 54 tokens to every session and 681 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 2026-08-30.
Other skills, from other repositories
shipping-and-launch
Prepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy.
apify-actor-development
Create, modify and validate Apify Actors with scoped inputs, storage schemas, runtime logic and deployment review.
aws-serverless-eda
AWS serverless and event-driven architecture expert based on Well-Architected Framework. Use when building serverless APIs, Lambda functions, REST APIs, microservices, or async workflows.
ai-inference-service-mesh
Use verified service mesh patterns for AI inference traffic management, mTLS, canary releases, policy enforcement, and cross-cluster resilience.
ai-pipeline-orchestration
Orchestrate AI/ML pipelines for data ingestion, model training, batch inference, and RAG indexing using Prefect, Airflow, or Dagster.
ai-sre-incident-response
Build AI-focused SRE incident response practices for LLM outages, degraded quality, runaway cost events, and safety regressions.