Borrowing it
Nothing to install: this file belongs to suuus/ape-context. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/suuus/ape-context/main/.github/skills/context-drift/SKILL.mdgit clone --depth 1 https://github.com/suuus/ape-contextWrote 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/suuus/ape-context/context-drift)<a href="https://agentmods.dev/skills/suuus/ape-context/context-drift"><img src="https://agentmods.dev/badge/skills/suuus/ape-context/context-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/suuus/ape-context/context-drift"><img src="https://agentmods.dev/badge/skills/suuus/ape-context/context-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 | $0.00071 | $0.00423 |
| Opus 5.5 | $0.00028 | $0.00169 |
| Sonnet 5.5 | $0.00014 | $0.00085 |
| Haiku 4.5 | $0.00007 | $0.00042 |
Grade A, and why
context-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
- Load stack, MCP, instructions, ADRP decisions/imports, ASRP Structure, execution manifest, ratification, and AERP Evidence. Missing required state is drift.
- Flag uncovered/removed tools, stale references, health/auth failures, and instruction bloat above 80 lines or 25% growth.
- Run
context_artifacts.py fingerprint; mismatch or material source, authority, autonomy, trust, or scope change invalidates ratification. - Use ADRP to validate decisions, imports, sidecars, lifecycle, source drift, supersession, contradiction, and tampering. Never overwrite imports.
- Use ASRP to validate Structure and manifest fingerprints. Changed ownership, responsibility, interfaces, boundaries, gates, entry points, or Evidence duties is action-required.
- Use AERP to validate required Evidence, exact ADRP/ASRP bindings, and artifact bytes. Missing Evidence, mismatch, or unverifiable artifacts is action-required.
Return exactly:
{"drift_report":{"action_required":[],"warnings":[],"info":[],"intent_affecting":[]}}
Items contain title, source, evidence, severity, and fix. Material changes are
both action_required and intent_affecting. Clean means all arrays are empty.
Use ask_user before any fix. Never edit or claim re-ratification. Route fixes through context-distill → Decisions →
Structure → Instructions → Quality → Ratify → Evidence/Feedback.
What ships with it
8 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.
- evals/eval.yaml 741 B
- evals/tasks/auth-failure-health.yaml 866 B
- evals/tasks/clean-report.yaml 1.0 KB
- evals/tasks/intent-affecting-change.yaml 1.3 KB
- evals/tasks/new-terraform-tool.yaml 1.0 KB
- evals/tasks/ratification-fingerprint.yaml 651 B
- evals/tasks/removed-tool-configured.yaml 1.0 KB
- evals/tasks/stale-instructions.yaml 905 B
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 Changed · -62 lines · +53 tokens per session 8c7f5f691175
- 2mo ago First seen · 102 lines · 18 tokens per session scan A 36666f315489
context-drift is a skill published in the GitHub repository suuus/ape-context (2 stars, last pushed 1mo ago), licensed MIT. It adds 71 tokens to every session and 423 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
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.
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…
cwv-optimizer
Diagnose and fix Core Web Vitals issues on AEM Edge Delivery Services pages. Goes deeper than generic CWV advice by understanding EDS-specific performance patterns including the 100KB LCP budget, E-L-D loading phases, block rendering behavior, and third-party script impact. Produces specific fixes for LCP, CLS, and…
ci-fixer
CI failures - read error, minimal fix, verify.
incident-response-incident-response
Coordinate production incident triage, mitigation, investigation, recovery, and follow-up. Use when responding to outages or other incidents that require structured operational coordination.
diagnosing-missing-recordings
Diagnoses why a session recording is missing or was not captured. Use when a user asks why a session has no replay, why recordings aren't appearing, or wants to troubleshoot session replay capture issues for a specific session ID or across their project. Covers SDK diagnostic signals, project settings, sampling…