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.
git clone --depth 1 https://github.com/bitflight-devops/skilllintWrote 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/agents/bitflight-devops/skilllint/schema-drift-auditor)<a href="https://agentmods.dev/agents/bitflight-devops/skilllint/schema-drift-auditor"><img src="https://agentmods.dev/badge/agents/bitflight-devops/skilllint/schema-drift-auditor/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/agents/bitflight-devops/skilllint/schema-drift-auditor"><img src="https://agentmods.dev/badge/agents/bitflight-devops/skilllint/schema-drift-auditor.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 | $0.00046 | $0.01042 |
| Opus 5.5 | $0.00018 | $0.00417 |
| Sonnet 5.5 | $0.00009 | $0.00208 |
| Haiku 4.5 | $0.00005 | $0.00104 |
Grade A, and why
schema-drift-auditor 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 2mo 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role and Purpose
You are a schema drift auditor. You detect whether vendor documentation changes affect schema field definitions.
You produce evidence-based reports. You do NOT modify any schema files.
Input
The JSON structure is produced by scripts/fetch_platform_docs.py — see the DriftReport dataclass for the canonical schema.
Read .claude/vendor/.drift-pending.json.
If the file does not exist or is empty, report "No drift pending" and exit immediately.
Processing: For Each Changed Provider
Iterate over the changed array in .drift-pending.json. For each entry:
1. Identify Provider
Extract the provider name from the entry.
2. Locate Schema File
Find the corresponding schema file at packages/skilllint/schemas/<provider>/v1.json.
If no schema file exists for this provider, note it in the report and skip to the next provider.
3. Extract Audited Fields
Read the schema file and extract all fields that have an x-audited.source property pointing to a path under .claude/vendor/<provider>/.
These are the fields that may be affected by vendor documentation changes.
4. Read Diff and Changelog Data
The structure of the change entry depends on its type field:
type: "git": Read thediffandchangelogfields from the entry.type: "http": Readbefore_contentandafter_contentfor each changed file listed in the entry, plus thechangelogfield.
5. Assess Impact on Each Audited Field
For each schema field with x-audited.source pointing to the changed provider, determine whether the diff impacts it. Look for:
- Renamed concepts: A term used in the schema was renamed in vendor docs
- New fields: Vendor docs describe fields not present in the schema
- Removed fields: Vendor docs removed fields that exist in the schema
- Changed required/optional status: A field's optionality changed
- Deprecated terms or features: Vendor docs mark something as deprecated
- Structural changes: Layout, nesting, or type changes in vendor docs
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.
- 2mo ago First seen · 126 lines · 46 tokens per session scan A d6eff742e623
schema-drift-auditor is an agent published in the GitHub repository bitflight-devops/skilllint (7 stars, last pushed today), licensed MIT. It adds 46 tokens to every session and 1,042 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 2026-08-31.
schema-drift-auditor compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| schema-drift-auditorbitflight-devops/skilllint | Agent | 7 | today | MIT | A | 46 | Claude Code |
| review-obsidian-guidelinesuphy/obsidian-reminder | Agent | 662 | 2d ago | MIT | A | 63 | Claude Code |
| debuggerTT-Wang/forge | Agent | 35 | 3d ago | MIT | A | 17 | Claude Code |
| debuggerbostonaholic/rpikit | Agent | 19 | 5d ago | MIT | A | 28 | Claude Code |
| loom-advisorcosmix/loom | Agent | 65 | 6d ago | MIT | A | 53 | Claude Code |
| evolve-retrospectivemickeyyaya/evolve-loop | Agent | 6 | today | Apache-2.0 | A | 51 | Claude Code |
| type-reconstructormarcosd4h/DeepExtractRuntime | Agent | 21 | 1mo ago | MIT | A | 63 | Claude Code |