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 skills add sjarmak/agent-workflows --skill prd-build-resumegit clone --depth 1 https://github.com/sjarmak/agent-workflowsWrote 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/skills/sjarmak/agent-workflows/prd-build-resume)<a href="https://agentmods.dev/skills/sjarmak/agent-workflows/prd-build-resume"><img src="https://agentmods.dev/badge/skills/sjarmak/agent-workflows/prd-build-resume/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/skills/sjarmak/agent-workflows/prd-build-resume"><img src="https://agentmods.dev/badge/skills/sjarmak/agent-workflows/prd-build-resume.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 | $0.00014 | $0.00466 |
| Opus 5 | $0.00007 | $0.00233 |
| Sonnet 5 | $0.00003 | $0.00093 |
| Haiku 4.5 | $0.00001 | $0.00047 |
Grade B, and why
prd-build-resume scanned grade B with 1 finding 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
cat .claude/prd-build.state.json What it actually says
PRD Build Resume
Load existing state:
if [ -f .claude/prd-build.state.json ]; then
cat .claude/prd-build.state.json
else
echo "NO_STATE_FILE"
fi
If NO_STATE_FILE: tell the user there's no run to resume. Suggest /prd-build <prd-path> to start one.
Otherwise, follow this recovery procedure:
1. Assess State
Read .claude/prd-build.state.json and .claude/prd-build-artifacts/dag.json. Determine:
- What phase was the run in? (decomposing, executing, landing, verifying, paused)
- Which units are landed, active, pending, evicted, failed?
- What pass number are we on?
2. Recover Interrupted Units
Any units with status "active" were interrupted mid-execution. Read dag.json, update those units' status to "pending" and clear their pipeline_stage to null, then write the file back.
3. Resume Execution
Update .claude/prd-build.state.json status to "executing". Append to .claude/prd-build.log.md: "Resumed from checkpoint".
4. Continue from Current Layer
Find the lowest layer number that still has non-landed units. Resume Phase 2 (EXECUTE) from that layer.
Follow the exact same orchestration logic as the main /prd-build command's Phase 2, 3, and 4. The key difference: you already have the work plan — skip decomposition and go straight to execution.
Read the PRD for context:
# The PRD path is stored in the state file — read it from the JSON printed above
cat "$(cat .claude/prd-build.state.json | python3 -c 'import sys,json; print(json.load(sys.stdin)["prd_path"])')"
Then read that file to understand what's being built, and continue orchestrating.
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 · 54 lines · 14 tokens per session scan B 0f183619451d
prd-build-resume is a skill published in the GitHub repository sjarmak/agent-workflows (9 stars, last pushed 1mo ago), licensed MIT. It adds 14 tokens to every session and 466 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
mission-control
Interact with Mission Control — AI agent orchestration dashboard. Use when registering agents, managing tasks, syncing skills, or querying agent/task status via MC APIs.
incident-postmortem-report
Produce a thorough incident post-mortem report after an outage or customer-impacting event. Covers executive summary, impact, detailed timeline, root cause, contributing factors, corrective and preventive actions, and lessons learned. Use when the user asks to write, draft, or complete a post-mortem, blameless review…
aws-cost-analysis
Analyze AWS costs by service, account, and time period. Identifies top spenders, cost anomalies, and optimization opportunities. Use when reviewing cloud spend, preparing cost reports, or investigating unexpected charges.
release-readiness-check
Verify all prerequisites are met before a release by checking PRs, CI/CD status, environment health, and blocking issues across GitHub, ArgoCD, and Jira. Use before cutting a release, deploying to production, or during release planning.
afrexai-compliance-engine
Your AI compliance officer. Guides startups and scale-ups through SOC 2, ISO 27001, GDPR, HIPAA, and PCI DSS — from zero to audit-ready. No consultants needed.
competitive-offer-architect
Design irresistible offer packages with real salary benchmarks, negotiation playbooks, and competitive counter-strategies. Co-designed with Siku (司库). Includes total compensation calculator, negotiation scripts, and BATNA analysis.