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 mattgierhart/PRD-driven-context-engineering --skill ghm-status-syncgit clone --depth 1 https://github.com/mattgierhart/PRD-driven-context-engineeringWrote 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/mattgierhart/prd-driven-context-engineering/ghm-status-sync)<a href="https://agentmods.dev/skills/mattgierhart/prd-driven-context-engineering/ghm-status-sync"><img src="https://agentmods.dev/badge/skills/mattgierhart/prd-driven-context-engineering/ghm-status-sync.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00052 | $0.00912 |
| Opus 5 | $0.00026 | $0.00456 |
| Sonnet 5 | $0.00010 | $0.00182 |
| Haiku 4.5 | $0.00005 | $0.00091 |
Grade A, and why
ghm-status-sync 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 8d 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Status Sync
Synchronize the README.md Command Center with the current project state after gate advancement or EPIC status changes.
Workflow Overview
- Load Context → Read README.md, PRD.md metadata, Active EPIC Session State section
- Extract State → Pull lifecycle stage, blockers, metrics
- Update Dashboard → Sync README sections with current truth
Core Output Template
| Element | Definition | Evidence |
|---|---|---|
| Lifecycle Stage | Current PRD version from PRD.md | Current Lifecycle Gate: v0.X |
| Gate Status | Visual progress indicators | 🟢 Complete / 🟡 In Progress / ⚪ Pending |
| Active EPIC | Current work from EPIC header | EPIC-XX: Title |
| Blockers | Open blockers from EPIC Session State section | List with severity |
Step 1: Load Context
Read these files in order:
README.md(current state)PRD.md(metadata block for lifecycle stage)- Active EPIC Session State section (blockers, progress)
Checklist
- README.md loaded
- PRD.md metadata extracted
- Active EPIC identified and Session State section read
Step 2: Extract Current State
Pull authoritative values:
| Field | Source |
|---|---|
| Lifecycle Stage | PRD.md Current Lifecycle Gate |
| Gate Progress | PRD.md gate table |
| Active EPIC | README.md Active Work section |
| Blockers | EPIC Session State section |
| Metrics | README.md Truth Table |
Step 3: Update README Dashboard
Apply synchronization rules:
- Lifecycle Stage: Update header to match PRD.md
- Gate Table:
- 🟢 = Passed gates (all criteria met)
- 🟡 = Current gate (in progress)
- ⚪ = Future gates (not started)
- Active EPIC: Update metadata in Active Work section
- Blockers: Sync from EPIC Session State section
- Squad Status (Section:
squad-status): Update agent and EPIC tables:- For each agent in
.claude/agents/: check MEMORY.md mtime for "Last Active", grep EPICs for agent name for "Current EPIC" - For each EPIC in
epics/: read State field, Epic Lead, and Change Log last date - Status values:
active(session <2h old),idle(no recent activity),blocked(blocker in session state)
- For each agent in
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 8d ago First seen · 113 lines · 52 tokens per session scan A 5a7e4a523537
ghm-status-sync is a skill published in the GitHub repository mattgierhart/PRD-driven-context-engineering (182 stars, last pushed 8d ago), licensed MIT. It adds 52 tokens to every session and 912 once invoked, about $0.0003 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 skills, from other repositories
omc-plan
Strategic planning with optional interview workflow.
project-session-manager
Worktree-first dev environment manager for issues, PRs, and features with optional tmux sessions.
ultragoal
Durable multi-goal workflow that persists plan/ledger artifacts under .omc/ultragoal and prints Claude /goal handoff text for the active session.
speckit-workflow
Comprehensive understanding of the spec-kit methodology. Constitution-driven feature development with specify, plan, tasks, and implement phases.
sdlc-accelerate
End-to-end SDLC ramp-up from idea to construction-ready with automated phase transitions.
project-awareness
Detect project type, AIWG framework state, team configuration, and active work to summarize status and recommend next actions.