What is project-rules-drift-auditor?

A drift checker for GitHub Projects that compares live automation rules with a saved baseline. Drift means the current setup no longer matches the intended configuration.

Use it for scheduled or on-demand audits, severity-based drift reports, and issue-ready remediation guidance.

It makes unexpected, missing, or extra project rules visible and classifies how serious each difference is.

project-rules-drift-auditor — Agent for Claude Code by ivegamsft

Install

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.

Clone the repo

git clone --depth 1 https://github.com/ivegamsft/basecoat

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/ivegamsft/basecoat/basecoat-50-security-project-rules-drift-auditor.svg)](https://agentmods.dev/agents/ivegamsft/basecoat/basecoat-50-security-project-rules-drift-auditor)

Your own site

<a href="https://agentmods.dev/agents/ivegamsft/basecoat/basecoat-50-security-project-rules-drift-auditor"><img src="https://agentmods.dev/badge/agents/ivegamsft/basecoat/basecoat-50-security-project-rules-drift-auditor.svg" alt="Measured on agentmods" height="20"></a>

Per session 92 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 786 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00092	$0.00786
Opus 5	$0.00046	$0.00393
Sonnet 5	$0.00018	$0.00157
Haiku 4.5	$0.00009	$0.00079

Measured 4d ago against content hash 6948f9106cb1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

project-rules-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 4d 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.

agents/basecoat-50-security-project-rules-drift-auditor.agent.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Rules Drift Auditor Agent

Purpose: compare live GitHub Project automation rules against the canonical AIDL guardrail baseline and produce a severity-classified, issue-ready drift report.

Inputs

repo — target repository in owner/repo format
project_id or project_url — GitHub Project (v2) to audit
baseline_path (optional) — path to baseline manifest JSON; defaults to scripts/project-rules-baseline.json
mode — advisory (report only) or enforce (open remediation issues on drift)
severity_threshold (optional) — minimum severity to include in report (critical | high | medium | low); defaults to low

Workflow

Preflight (enforce mode only) — confirm the opt-in drift-audit workflow exists (-InstallClass templates). If missing, stop and report install guidance; enforcement cannot run without this optional downstream workflow.
Load baseline — read from baseline_path; reject if absent/unparseable.
Fetch live rules — via gh api graphql.
Diff against baseline — classify each delta as missing, modified, or extra.
Classify severity — critical/high/medium/low.
Generate remediation rubric — a concrete fix per finding.
Emit report — deterministic JSON + Markdown summary.
Open issues (enforce mode only) — for findings at/above severity_threshold.

Full severity model, remediation rubric fields, baseline manifest contract, output format examples, and determinism requirements are in agents/references/project-rules-drift-auditor-detail.md.

Output

JSON report — deterministic, one entry per finding with severity and remediation
Markdown summary — human-readable table of findings
GitHub issues (enforce mode) — one per finding at/above severity_threshold

Model

Recommended: gpt-5.4 Minimum: gpt-5.4-mini

skills/project-rules-drift-audit/SKILL.md, skills/governance-audit/SKILL.md, skills/flow-suggest/SKILL.md
scripts/project-rules-drift-audit.ps1, scripts/project-rules-baseline.json
.github/workflows/project-rules-drift-audit.yml, docs/reference/project-rules-drift-auditor.md
agents/basecoat-50-security-policy-as-code-compliance.agent.md, agents/governance-auditor.agent.md

Read the full file on GitHub · 73 lines

Changes

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.

4d ago First seen · 73 lines · 92 tokens per session scan A 6948f9106cb1

Subscribe to this mod's changes

project-rules-drift-auditor is an agent published in the GitHub repository ivegamsft/basecoat (4 stars, last pushed today), licensed MIT. It adds 92 tokens to every session and 786 once invoked, about $0.0005 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 2026-09-03.

Debugging Project management

ijfw-debug-session-manager

Use when managing a multi-cycle debug session that needs checkpoint/continuation across context resets.

FerroxLabs/ijfw · 24 tokens

incident-responder

Production incident response agent'i. Severity classification (P0-P3), runbook execution, root cause analysis, impact assessment, communication template'leri, post-incident review ve remediation tracking.

vibeeval/vibecosystem · 42 tokens

Compliance Auditor

Perform non-destructive cross-artifact consistency and quality analysis across spec, plan, and tasks.

attilaszasz/sdd-pilot · 22 tokens

linear-ticket-investigator

Extract evidence from a single Linear ticket — read the ticket, locate affected code, and return an Evidence Record matching the /fix-bug Phase 2 schema. Returns structured evidence only — no root-cause analysis, no fix proposal, no confidence scoring (those are /fix-bug's job via holistic-analysis). Used by…

mthines/agent-skills · 88 tokens

evolve-scout-scan

MAP-step slice scanner for the scout map-reduce decomposition. Scans ONE codebase slice (a package group) and emits a structured ScanDigest. Does NOT select tasks or write evals — the scout synthesizer (REDUCE) does that from the merged digests.

mickeyyaya/evolve-loop · 62 tokens

jira-ops

Inspect JIRA-side cache + project context discovery via the jira-as CLI wrapper. Diagnostic surface: cache-status, cache-clear, discover-project. Routed by mk:jira-ops skill. NOT for issue CRUD; NOT for project admin (jira-admin).

ngocsangyem/MeowKit · 54 tokens