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/audit-workflowgit clone --depth 1 https://github.com/marcusgoll/Spec-FlowWhat 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 | $0.00014 | $0.02853 |
| Opus 5 | $0.00007 | $0.01426 |
| Sonnet 5 | $0.00003 | $0.00571 |
| Haiku 4.5 | $0.00001 | $0.00285 |
Grade A, and why
audit-workflow scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 455 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/audit-workflow — Workflow Effectiveness Analysis
Purpose: Analyze completed epic workflow to identify bottlenecks, quality issues, and improvement opportunities. Auto-runs after /implement and /finalize phases.
Command: /audit-workflow [epic-slug | auto]
When to use:
- Auto-triggered after
/implementcompletes - Auto-triggered during
/optimizephase - Auto-triggered after
/finalizefor post-mortem - Manual invocation to analyze current epic
Workflow Audit Process
Step 1: Locate Epic Workspace
If epic-slug provided:
EPIC_DIR="epics/$ARGUMENTS"
If "auto" or no argument:
# Find most recent epic
EPIC_DIR=$(ls -td epics/*/ | head -1)
Validate workspace exists:
test -d "$EPIC_DIR" && echo "found" || echo "not found"
If not found, error: "No epic workspace found. Run /epic first."
Step 2: Read Epic Artifacts
Load all epic data for analysis:
# Core artifacts
- epic-spec.md (requirements)
- state.yaml (phase tracking)
- sprint-plan.md (dependencies, execution plan)
- tasks.md (task breakdown)
- research.md (research findings)
- plan.md (architecture plan)
# Execution artifacts
- NOTES.md (implementation notes)
- sprints/*/implementation logs
- optimization-report.xml (quality gates)
Extract key metrics:
- Total phases completed
- Time spent per phase
- Tasks completed vs total
- Quality gate pass/fail rates
- Sprint execution times
- Parallel execution efficiency
Step 3: Analyze Workflow Effectiveness
Analysis focus areas (execute inline - no agent delegation):
- Phase efficiency - time vs value delivered per phase
- Bottleneck detection - which phases took longest
- Quality gate effectiveness - caught issues early?
- Sprint parallelization - actual vs potential speedup
- Documentation quality - XML artifacts complete?
- Process adherence - skipped phases, manual overrides
Output target: audit-report.xml with findings and recommendations
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.
- 2d ago First seen · 455 lines · 14 tokens per session scan A 8731c0456efb
audit-workflow is a command published in the GitHub repository marcusgoll/Spec-Flow (91 stars, last pushed 4mo ago), licensed MIT. It adds 14 tokens to every session and 2,853 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
quick-fix
Fast-track workflow for small bug fixes.
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.
usage-add
PitWay: Accumulate measured planning or qa token usage onto a milestone.
pi-code-review
Adversarial code review via Codex — break confidence in changes, not validate them.
milestone-list
PitWay: List every milestone with a concise one-line status.
setup
Install the claude-pace statusline bundled with this plugin.