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.
npx agentmods add commands/marcusgoll/spec-flow/workflow-healthgit clone --depth 1 https://github.com/marcusgoll/Spec-FlowWrote 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/marcusgoll/spec-flow/workflow-health)<a href="https://agentmods.dev/commands/marcusgoll/spec-flow/workflow-health"><img src="https://agentmods.dev/badge/commands/marcusgoll/spec-flow/workflow-health.svg" alt="Measured on agentmods" 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 | $0.00017 | $0.03552 |
| Opus 5 | $0.00009 | $0.01776 |
| Sonnet 5 | $0.00003 | $0.00710 |
| Haiku 4.5 | $0.00002 | $0.00355 |
Grade A, and why
workflow-health scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 505 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/workflow-health — Workflow Health Dashboard
Purpose: Aggregate metrics across all completed epics to show workflow system health, velocity trends, and continuous improvement effectiveness.
Command: /workflow-health [--detailed | --trends | --compare]
When to use:
- Check workflow system health across all epics
- Identify velocity trends over time
- Measure ROI of workflow improvements
- Compare epic performance
Workflow Health Analysis
Step 1: Discover Completed Epics
Scan for all epic workspaces:
EPIC_DIRS=$(find epics -maxdepth 1 -type d -name '[0-9]*' | sort)
EPIC_COUNT=$(echo "$EPIC_DIRS" | wc -l)
Filter for completed epics:
COMPLETED_EPICS=()
for dir in $EPIC_DIRS; do
if grep -q "status: completed" "$dir/state.yaml"; then
COMPLETED_EPICS+=("$dir")
fi
done
COMPLETED_COUNT=${#COMPLETED_EPICS[@]}
Step 2: Aggregate Core Metrics
For each completed epic, extract:
const epicMetrics = [];
for (const epicDir of completedEpics) {
const state = readYAML(`${epicDir}/state.yaml`);
const audit = readXML(`${epicDir}/audit-report.xml`); // if exists
const walkthrough = readXML(`${epicDir}/walkthrough.md`); // if exists
epicMetrics.push({
number: extractNumber(epicDir),
slug: extractSlug(epicDir),
start_date: state.created_at,
end_date: state.completed_at,
duration_hours: calculateDuration(state),
velocity_multiplier: audit?.velocity_impact?.actual_multiplier || "N/A",
sprint_count: state.sprints?.length || 0,
tasks_completed: state.tasks_completed || 0,
quality_score: audit?.overall_score || "N/A",
improvements_applied: countHealingReports(epicDir),
});
}
Step 3: Calculate Aggregate Statistics
Velocity trends:
const velocityStats = {
average: calculateAverage(epicMetrics.map((e) => e.velocity_multiplier)),
trend: calculateTrend(epicMetrics.map((e) => e.velocity_multiplier)),
best: Math.max(...epicMetrics.map((e) => e.velocity_multiplier)),
worst: Math.min(...epicMetrics.map((e) => e.velocity_multiplier)),
};
// Trend calculation
// Positive = improving over time
// Negative = degrading over time
const trend = linearRegression(
epicMetrics.map((e, i) => ({ x: i, y: e.velocity_multiplier }))
).slope;
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.
- 6d ago First seen · 505 lines · 17 tokens per session scan A d8dfc2ca0c97
workflow-health is a command published in the GitHub repository marcusgoll/Spec-Flow (92 stars, last pushed 4mo ago), licensed MIT. It adds 17 tokens to every session and 3,552 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
review
Review the current diff for violations of the conventions in AGENTS.md and .cursor/rules/. Report findings ordered by severity; do not fix anything unless asked.
organize-files
Organize and rename files based on content analysis.
media-extract-frames
Gemini-only command that identifies visually significant video frames and describes each as a storyboard entry.
task-verify
PitWay: Run an inprogress task's approved verification command and persist evidence.
milestone-list
PitWay: List every milestone with a concise one-line status.
amp-register
Register your agent with an external AMP provider for cross-provider messaging.