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 ahmedawan-oracle/claude-code-plugins --skill fusion-drift-doctorgit clone --depth 1 https://github.com/ahmedawan-oracle/claude-code-pluginsWrote 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/ahmedawan-oracle/claude-code-plugins/fusion-drift-doctor)<a href="https://agentmods.dev/skills/ahmedawan-oracle/claude-code-plugins/fusion-drift-doctor"><img src="https://agentmods.dev/badge/skills/ahmedawan-oracle/claude-code-plugins/fusion-drift-doctor/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/ahmedawan-oracle/claude-code-plugins/fusion-drift-doctor"><img src="https://agentmods.dev/badge/skills/ahmedawan-oracle/claude-code-plugins/fusion-drift-doctor.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 | $0.00196 | $0.02198 |
| Opus 5 | $0.00098 | $0.01099 |
| Sonnet 5 | $0.00039 | $0.00440 |
| Haiku 4.5 | $0.00020 | $0.00220 |
Grade A, and why
fusion-drift-doctor 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 9d 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
fusion-drift-doctor — what drifted, and how to fix it
The runtime gates DETECT drift and fail the run; they don't tell you which fix. This skill closes that: read the failure, probe the live Fusion PVO, classify each affected column, and route to the right remediation. Read-only — it diagnoses and hands off; it never edits packs/profiles or runs the pipeline.
When to use
- A
seed/incrementalrun failed withAIDPF-2072/4070/4071/2012/4040, or the summary says "schema drift" / "PVO drift". - "The Fusion PVO column got renamed", "bronze schema changed", "why does my incremental keep failing the gate?"
- As a precheck inside
/aidp-fusion-incrementalbefore dispatch.
The gate codes it triages
| Code | What it means | Route |
|---|---|---|
| AIDPF-2072 | Live Fusion PVO schema drifted vs the bootstrap-pinned snapshot (a source column renamed/removed). | classify → bootstrap --refresh or /medallion-author |
| AIDPF-4071 | A declared outputSchema column is missing from the live PVO. |
classify (same as 2072) |
| AIDPF-4070 | A live PVO column's type changed vs declared. | /medallion-author — draft a bronze type-overlay (retype outputSchema to the live type) from the persisted AIDPF-4070__<node>.json |
| AIDPF-2012 | Bronze table fingerprint drifted vs the pinned profile fingerprint. | confirm the change is legit → bootstrap --refresh to re-pin |
| AIDPF-4040 | Plan-hash drift — the node's plan-hash differs from the seed-pinned one. | classify the cause (below) — re-seed only fixes a genuine plan-shape change |
Note the distinction: PVO source drift (2072/4070/4071) is detected by a metadata-only BICC probe of the live PVO — it catches a renamed source column even when the bronze Delta table still holds the old one. Bronze-table drift (2012) is a
DESCRIBEof the materialized table. Different layers.
Helper
| File | Role | Invoked via |
|---|---|---|
drift_classify.py |
Classify each columnAlias against the live PVO columns → present / renamed_resolvable (→ bootstrap --refresh) / needs_overlay (→ medallion-author) / missing_literal (→ investigate if it should exist, OR — if legitimately absent for this tenant — relax the requiredColumns assertion via a relaxRequiredColumns overlay through /medallion-author; AIDPF-2062/2063 guard it). |
Bash, JSON in/out |
What ships with it
1 file 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.
- 9d ago First seen · 115 lines · 196 tokens per session scan A b75cc652908f
fusion-drift-doctor is a skill published in the GitHub repository ahmedawan-oracle/claude-code-plugins (2 stars, last pushed 1mo ago), licensed MIT. It adds 196 tokens to every session and 2,198 once invoked, about $0.0010 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
fix-failing-tests
Diagnose a failing test in the googleapis/mcp-toolbox repo and land a fix by reasoning from the actual error: read the failure, reproduce it, shrink it until the cause is forced into the open, then fix the cause. Use this whenever a test or CI job is red, a build breaks after a change, many packages fail at once, or a…
triage-issues
Triage GitHub issues in the googleapis/mcp-toolbox repo: propose the correct labels (type / priority / product / status), check for duplicates, verify a bug has enough info to act on, and draft a triage comment. Use whenever a maintainer asks you to triage, label, categorize, prioritize, or "look at" an issue (or a…
postgresql-indexing
PostgreSQL indexing best practices for Prowler: index design, partial indexes, partitioned table indexing, EXPLAIN ANALYZE validation, concurrent operations, monitoring, and maintenance. Trigger: When creating or modifying PostgreSQL indexes, analyzing query performance with EXPLAIN, debugging slow queries, reviewing…
graphjin-eval
Create, extend, run, baseline, and diagnose GraphJin agent evaluations through the graphjin eval CLI.
axiom-audit-grdb-performance
Use when the user mentions GRDB performance review, slow GRDB queries, app-group database setup audit, a ValueObservation that stopped updating, or pre-release GRDB scan.
django-perf-review
Django performance code review. Use when asked to "review Django performance", "find N+1 queries", "optimize Django", "check queryset performance", "database performance", "Django ORM issues", or audit Django code for performance problems.