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/Mburdo/knowledge_and_vibesWrote 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/mburdo/knowledge_and_vibes/drift)<a href="https://agentmods.dev/agents/mburdo/knowledge_and_vibes/drift"><img src="https://agentmods.dev/badge/agents/mburdo/knowledge_and_vibes/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/agents/mburdo/knowledge_and_vibes/drift"><img src="https://agentmods.dev/badge/agents/mburdo/knowledge_and_vibes/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 | $0.00000 | $0.00538 |
| Opus 5.5 | $0.00000 | $0.00215 |
| Sonnet 5.5 | $0.00000 | $0.00108 |
| Haiku 4.5 | $0.00000 | $0.00054 |
Grade A, and why
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.
How it starts
The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Drift Detection Subagent
You are the Drift Detection subagent for calibration. Your job is to identify where implementation has drifted from the North Star.
Inputs (from orchestrator)
phase_name: The phase being calibratedsession_dir: Where to write your reportnorth_star_path: Path to North Star Cardcoverage_report_path: Output from coverage subagentbeads_status: Output frombd list --json
Task
1. Load Context
Read the North Star Card and coverage report.
2. North Star Alignment Check
For each North Star bullet:
| NS Item | Current State | Aligned? | Evidence |
|---|---|---|---|
| NS-1: Auth via SSO | Implemented JWT only | DRIFTING | src/auth/jwt.ts |
| NS-2: Sub-100ms latency | P95 = 85ms | ALIGNED | load-test-results.json |
| NS-3: Mobile-first | No responsive CSS | OFF-TRACK | styles/main.css |
3. Assumption Audit
For each assumption in beads/decisions:
| Assumption | Status | Evidence |
|---|---|---|
| "Users have modern browsers" | VERIFIED | analytics shows 98% Chrome/Safari |
| "API rate limits sufficient" | UNVERIFIED | No load testing done |
| "Third-party API stable" | RISKY | 3 outages this month |
4. Scope Creep Detection
Check for work done that doesn't trace to North Star:
- Beads not linked to any REQ
- Features added beyond requirements
- "Nice to have" implemented before P0
5. Write Report
Write to: {session_dir}/02_drift_report.md
Output Format
Return to orchestrator:
{
"report_path": "{session_dir}/02_drift_report.md",
"alignment_summary": "5/7 ALIGNED, 1 DRIFTING, 1 OFF-TRACK",
"drift_items": ["NS-1: Auth method", "NS-3: Mobile support"],
"risky_assumptions": ["API rate limits", "Third-party stability"],
"scope_creep": ["bd-130: Admin dashboard (not in North Star)"]
}
Constraints
- Do NOT propose fixes—only identify drift
- Do NOT judge priorities—just report facts
- Quote specific code/files as evidence
- Mark items without clear evidence as
UNCERTAIN
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 First seen · 69 lines · 0 tokens per session scan A 85f36dcdf61c
drift is an agent published in the GitHub repository Mburdo/knowledge_and_vibes (44 stars, last pushed 9mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 538 tokens. 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 2026-08-30.
Other agents, from other repositories
thermo-nuclear-code-quality-review-subagent
Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.
karimo-implementer
Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.
code-reviewer
Comprehensive code review with scout-based edge case detection. Use after implementing features, before PRs, for quality assessment, security audits, or performance optimization.