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/mizukaizen/hive-doctrine-mcpWrote 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/commands/mizukaizen/hive-doctrine-mcp/regression)<a href="https://agentmods.dev/commands/mizukaizen/hive-doctrine-mcp/regression"><img src="https://agentmods.dev/badge/commands/mizukaizen/hive-doctrine-mcp/regression/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/commands/mizukaizen/hive-doctrine-mcp/regression"><img src="https://agentmods.dev/badge/commands/mizukaizen/hive-doctrine-mcp/regression.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 | $0.00578 |
| Opus 5 | $0.00000 | $0.00289 |
| Sonnet 5 | $0.00000 | $0.00116 |
| Haiku 4.5 | $0.00000 | $0.00058 |
Grade A, and why
regression 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/regression
Check for regressions by comparing test results against a baseline.
Usage
/regression [--baseline "main|<branch>|<commit>"] [--compare "<branch>|HEAD"] [--suite "unit|integration|e2e|all"]
Behaviour
1. Establish Baseline
- Identify the baseline reference (default: main branch)
- Record the test results from the baseline (or retrieve cached results)
- Note the total tests, pass count, fail count, skip count
2. Run Current Tests
- Run the test suite on the comparison branch/commit
- Capture results: pass, fail, skip, duration for each test
3. Compare Results
Identify:
- New failures — Tests that passed on baseline but fail now. These are potential regressions.
- Fixed tests — Tests that failed on baseline but pass now. Confirm these are intentional fixes.
- New tests — Tests that exist now but not on baseline. Verify they pass.
- Removed tests — Tests that existed on baseline but are missing now. Verify removal was intentional.
- Performance changes — Tests that take significantly longer (>50% increase in duration).
4. Analyse Regressions
For each new failure:
- Identify the most recent commit that could have caused it
- Check what code the failing test covers
- Assess whether the failure indicates a real bug or a test that needs updating
- Classify as: regression (real bug), intentional change (test needs update), or flaky test
5. Generate Report
# Regression Report
## Summary
| Metric | Baseline | Current | Delta |
|--------|----------|---------|-------|
| Total tests | N | N | +/-N |
| Passing | N | N | +/-N |
| Failing | N | N | +/-N |
| Skipped | N | N | +/-N |
| Duration | Xs | Xs | +/-Xs |
## Regressions (New Failures)
| Test | File | Likely Cause | Classification |
|------|------|-------------|----------------|
| [test name] | [file] | [commit/change] | Regression / Intentional / Flaky |
## Fixed (Previously Failing)
| Test | File |
|------|------|
| [test name] | [file] |
## New Tests
| Test | File | Status |
|------|------|--------|
| [test name] | [file] | Pass/Fail |
## Verdict
[PASS: No regressions detected / FAIL: N regressions require investigation]
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 · 78 lines · 0 tokens per session scan A e710c20a65f2
regression is a command published in the GitHub repository mizukaizen/hive-doctrine-mcp (0 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 578 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 2026-08-31.
Other commands, from other repositories
ui-aqa-flow-test-report-analysis
Phase 7 Test Report Analysis of ui-aqa-flow.
ui-aqa-flow-code-analysis
Phase 3 Code Analysis of ui-aqa-flow.
ng-red-team
Portable command prompt generated from skills/stress-testing-agent-changes/SKILL.md. Edit the skill, then run python tools/ng.py gen-commands; do not edit this file by hand.
develop
Implement skill development issues with TDD-governed workflow.
mega-edit
Edit the mega-plan interactively. Add, remove, or modify features. Usage: /plan-cascade:mega-edit.
hybrid-manual
Load an existing PRD file and enter review mode. Supports JSON format with stories, priorities, dependencies, and acceptance criteria.