decision change drift auditor
Detects unauthorized changes and material drift between approved baseline documents and revised plans or policies.
$5
Works with the AI Agents you already use
Claude Code
Cursor
Codex CLI
Muse
Dots+21 moreClaude CodeCursorCodex CLIMuseDots
Manus
Grok
Grok Bot+18 agentsdecision change drift auditor
Example session with this skill installed
Audit the attached revised project charter (v2.0) against the approved baseline charter (v1.0). The baseline was approved by the Board on 2024-01-15. Check for unauthorized drift.
- Read your context and instructions
- Compiled the decision change drift
The audit of the revised project charter (v2.0) against the approved baseline (v1.0) is complete. I have identified 3 instances of unauthorized drift, including one critical reversal of a board-approved commitment.
Drift Audit Report
Documents Audited
- Baseline: Project Charter v1.0, approved 2024-01-15 by Board of Directors
- Target: Project Charter v2.0, dated 2024-05-10, authored by PMO
Summary
- Total deltas found: 5
- Authorized evolution: 2
- Unauthorized drift: 3 (Critical: 1, Major: 1, Minor: 1, Negligible: 0)
- Systemic patterns: 0
Findings
| ID | Severity | Type | Baseline Clause | Target Clause | Delta Description |
|---|---|---|---|---|---|
| F-001 | CRITICAL | Reversal | "Project budget capped at $2.5M; any overage requires Board sign-off." | "Project budget managed by PMO; escalations to Finance if >$3.0M." | Budget ceiling increased by 20% and approval authority shifted from Board to Finance. |
| F-002 | MAJOR | Weakening | "Security audit shall be completed before Stage 2 deployment." | "Security audit should be initiated during Stage 2 deployment." | Changed 'shall' to 'should' and moved timing from a hard gate to a concurrent activity. |
| F-003 | MINOR | Ownership Shift | "QA Lead responsible for final sign-off." | "Technical Lead responsible for final sign-off." | Accountability moved from independent QA to the implementation team lead. |
Recommendations
- Immediate Freeze: Deployment to Stage 2 must be halted until the Security Audit timing (F-002) is rectified.
- Renewed Approval: Submit v2.0 to the Board for re-approval of the new $3.0M budget threshold (F-001).
- Documentation: Formally record the change in sign-off authority (F-003) in the project RACI matrix.
Next steps
- Review the specific delta rationale for F-001 with the Finance department.
- Prepare the Board briefing note for the budget threshold amendment.
- Update the v2.0 draft to restore 'shall' in the security audit clause.
Connects securely to your tools. The creator never sees your data.
About this skill
The problem
Policies and project plans often undergo silent revisions between formal approval and implementation. These subtle shifts in language, thresholds, or ownership can introduce unauthorized risk or regulatory non-compliance that manual reviews often miss.
What it does
- Extracts and categorizes commitments, thresholds, and constraints from approved baseline documents.
- Maps target documents against baselines to identify removals, reversals, or weakened commitments.
- Classifies deltas into categories like ownership shifts, approval drift, and stale evidence.
- Assesses materiality of each change to prioritize regulatory or financial risks.
- Flags specific triggers that require renewed approval from original authorities.
Why this beats prompting it yourself
General-purpose prompts often treat linguistic changes as stylistic improvements. This skill enforces a rigorous audit methodology that treats every deviation as a potential deletion or weakening. It maintains a strict side-by-side mapping to ensure no baseline commitment is lost in the noise of a document revision.
Use cases
- Auditing a final project proposal against the board-approved initial charter.
- Checking updated operational policies for unauthorized weakening of safety controls.
- Verifying that contract revisions haven't shifted ownership or liability without documented consent.
- Comparing multiple departmental plans to ensure consistent adherence to a central baseline.
Known limitations
Does not handle purely stylistic or formatting audits. Requires documents to have a direct baseline-to-target relationship.
Focuses on material drift; skips grammar and formatting. Requires documents with a clear baseline-derived relationship. Does not author replacement language.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 1 month ago
Permissions
No special permissions declared or detected