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/phuoctrung-ppt/ai-sdlc-workflow/workflow-evalgit clone --depth 1 https://github.com/phuoctrung-ppt/ai-sdlc-workflowWhat 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 | $0.00018 | $0.00351 |
| Opus 5 | $0.00009 | $0.00176 |
| Sonnet 5 | $0.00004 | $0.00070 |
| Haiku 4.5 | $0.00002 | $0.00035 |
Grade A, and why
workflow-eval 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.
What it actually says
Act as Judge Agent with the workflow integrity checklist. Always write a durable artifact under docs/reviews/, whether this command was invoked manually or by a protected-change hook.
Evaluate: {plan_or_diff_or_feature}
Inputs to inspect:
AGENTS.md- Standards docs from
.cursor/config/workflow-policy.json, usuallyAGENTS.md - Relevant
docs/plans/*ordocs/adr/* - Relevant
.cursor/agents/*,.cursor/rules/*,.cursor/commands/* - Git diff or specified implementation files
Process:
- Run context-builder for review:
python3 .cursor/context/context-builder.py --phase review --task "{plan_or_diff_or_feature}" --agent judge-agent --keywords "workflow,judge,security,tenant,test" --budget 5000 - Verify the result against acceptance criteria and the handoff packet.
- Check the shared protected classifier in
.cursor/config/protected-paths.json; do not accept agent self-classification. - Check role boundaries: planner planned, workers implemented, judge stayed read-only.
- Check evidence quality: commands, tests, docs, ADRs, security/privacy/data/AI/infrastructure/domain gates.
- Write findings to
docs/reviews/YYYY-MM-DD-workflow-eval-{slug}.md.
Output:
Status: GOOD | NEEDS_OPTIMIZATION | BLOCKED
## What Works
## Gaps
- [severity] file:line — issue
## Required Optimizations
## Evidence Reviewed
## Recommended Cursor Config Changes
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 · 42 lines · 18 tokens per session scan A 44acf2e9e794
workflow-eval is a command published in the GitHub repository phuoctrung-ppt/ai-sdlc-workflow (2 stars, last pushed 17d ago), licensed MIT. It adds 18 tokens to every session and 351 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 2026-08-31.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.