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 hoavdc/CodexKit --skill codexkit-safe-pi-planninggit clone --depth 1 https://github.com/hoavdc/CodexKitWrote 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/hoavdc/codexkit/codexkit-safe-pi-planning)<a href="https://agentmods.dev/skills/hoavdc/codexkit/codexkit-safe-pi-planning"><img src="https://agentmods.dev/badge/skills/hoavdc/codexkit/codexkit-safe-pi-planning/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/hoavdc/codexkit/codexkit-safe-pi-planning"><img src="https://agentmods.dev/badge/skills/hoavdc/codexkit/codexkit-safe-pi-planning.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 | $0.00063 | $0.01167 |
| Opus 5.5 | $0.00025 | $0.00467 |
| Sonnet 5.5 | $0.00013 | $0.00233 |
| Haiku 4.5 | $0.00006 | $0.00117 |
Grade A, and why
codexkit-safe-pi-planning 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 1mo 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SAFe PI Planning Facilitator
When to Use
- Before a new Program Increment (PI) starts
- When an Agile Release Train (ART) needs to align on the next 8–12 weeks
- When cross-team dependencies must be mapped and risks must be surfaced
- When PI Objectives need to be written with quantified Business Value
Procedure
Step 1 — Preparation (Pre-Event)
- Collect team capacity for each iteration (available story points or throughput)
- Pull the prioritized feature backlog from Product Management
- Identify known architectural and cross-team dependencies
- Prepare the blank Program Board (teams × iterations matrix)
Step 2 — Day 1: Draft Plan
- Business Context — Product Management presents vision and top features
- Architecture Vision — System Architect presents enablers and tech runway
- Team Breakout #1 — Each team drafts iteration plans, identifies dependencies
- Draft Plan Review — Teams present plans; stakeholders flag risks
- Management Q&A — Address impediments, resource conflicts, scope concerns
Step 3 — Day 2: Finalize
- Team Breakout #2 — Adjust plans based on feedback, resolve dependency conflicts
- Program Board Finalization — All dependencies mapped as strings on the board
- PI Objectives — Each team writes 5–8 objectives using SMART format
- Business Value — Product Management assigns BV score (1–10) to each objective
- Confidence Vote — Fist of five (1–5); reshuffle if average < 3
Step 4 — Output
- Compile PI Objectives table (Objective / BV / Committed vs Uncommitted)
- Generate Program Board visualization (dependency map)
- Document risks identified during planning
- Record Confidence Vote result
Inputs
| Input | Required | Format |
|---|---|---|
| Feature backlog | Yes | Priority-ordered list with descriptions |
| Team capacity per iteration | Yes | Story points or throughput number |
| Known dependencies | Recommended | From/To team + feature reference |
| ART roster | Yes | List of teams in the ART |
What ships with it
1 file 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.
- 1mo ago First seen · 130 lines · 63 tokens per session scan A 16e9d0c74c38
codexkit-safe-pi-planning is a skill published in the GitHub repository hoavdc/CodexKit (26 stars, last pushed 11d ago), licensed MIT. It adds 63 tokens to every session and 1,167 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
add-linear
Add Linear channel integration via Chat SDK. Issue comment threads as conversations.
sn-team-harness
Use when a user asks what SenseNova Team Harness is, wants an introduction or overview, is getting started, or is deciding whether it fits — a self-hosted workspace where people and local AI agents collaborate on conversations, projects, work items, and artifacts. Covers its core concepts (Workspace, Project…
product-brief
Extract a product idea through guided questions and generate a PRD. Use when the user says 'write a PRD', 'spec this feature', 'turn this idea into a brief'. Not for a non-product initiative like hiring or partnerships (use initiative-kickoff once shipped); not for checking existing projects' status (use…
triage
Route orphaned inbox files and pull scattered - [ ] tasks into the right project/person/goal using current priorities. Use when the user says 'clean up my inbox', 'triage', 'sort out these notes'. Also use proactively when 00-Inbox/ is piling up. Not for updating notes from meetings; use process-meetings.
feature-decision
Framework for making feature prioritization decisions.
things-setup
Connect Things 3 (macOS only) so Dex reads and updates your Things tasks. Use when the user says 'I use Things', 'sync my Things inbox', or pastes a things:// link. Not for Todoist (todoist-setup) or Trello (trello-setup).