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 skills/mshadmanrahman/pm-pilot/session-initnpx skills add mshadmanrahman/pm-pilot --skill session-initgit clone --depth 1 https://github.com/mshadmanrahman/pm-pilotWrote 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/mshadmanrahman/pm-pilot/session-init)<a href="https://agentmods.dev/skills/mshadmanrahman/pm-pilot/session-init"><img src="https://agentmods.dev/badge/skills/mshadmanrahman/pm-pilot/session-init.svg" alt="Measured on agentmods" 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 | $0.00010 | $0.00402 |
| Opus 5 | $0.00005 | $0.00201 |
| Sonnet 5 | $0.00002 | $0.00080 |
| Haiku 4.5 | $0.00001 | $0.00040 |
Grade A, and why
session-init 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 4d 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
Session Init
Quick-start a session by loading prior context and surfacing open work.
When to Use
- Starting a new session
- Returning after a break
- Picking up someone else's work
Procedure
-
Load Memory
- Read
MEMORY.md(auto-loaded, but scan for recent entries) - Note any
currentDateor session-specific flags
- Read
-
Check Handoffs
- Read latest file in
.claude/handoffs/(sort by date desc) - Extract: last task, decisions, blockers, next steps
- Read latest file in
-
Check Open Tasks
- Read
tasks/todo.md - Count open vs completed items
- Identify highest-priority incomplete item
- Read
-
Check Lessons
- Scan
tasks/lessons.mdfor entries from last 3 sessions - Note any recurring patterns or warnings
- Scan
-
Output Summary Produce exactly 5 lines:
Session: {date} Last: {what was last worked on} Open: {count} tasks ({top priority item}) Blockers: {any blockers or "none"} Next: {recommended first action}
Output Format
Session: 2026-03-14
Last: Lead scoring simulator deploy
Open: 3 tasks (fix CPL calculation)
Blockers: none
Next: Run verification loop on simulator changes
Rules
- Never spend more than 30 seconds on init
- If no handoff exists, say so and ask user for context
- Do not auto-start work; present summary and wait for direction
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.
- 4d ago First seen · 66 lines · 10 tokens per session scan A cb9c5a6624d2
session-init is a skill published in the GitHub repository mshadmanrahman/pm-pilot (19 stars, last pushed 14d ago), licensed MIT. It adds 10 tokens to every session and 402 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 skills, from other repositories
pipefy-ai-agents
Use this skill when the user wants to create, read, update, delete, or troubleshoot AI agents (conversational agents with behaviors). Covers 7 MCP tools including pre-flight validation, plus pipe-scoped knowledge bases (list, plain text/document/data lookup CRUD, access probe) attached via dataSourceIds. For…
engram
Read and write the project's durable reasoning memory (decisions, principles, cautions, problems, insights) through the Engram MCP tools. Recall relevant memory before non-trivial work; capture only durable, high-value knowledge silently at natural stopping points; keep the graph honest (judge suspects, close answered…
engram-digest
Seed or top up this project's Engram graph from the existing codebase — an explicit, user-invoked digestion of the current working tree into typed memory nodes (decisions, principles, cautions, problems, insights, intents). Use when the user says "digest this project", "ingest the codebase into memory", "seed the…
context-fundamentals
This skill should be used to explain or reason about the foundational concepts of context engineering: what context is, the anatomy of a context window, how attention mechanics work, the U-shaped attention curve, why context quality matters more than quantity, and the mental models needed to interpret every other…
filesystem-context
This skill should be used when agent work needs file-backed context: durable scratchpads, tool-output offloading, just-in-time discovery, cross-agent handoff files, filesystem memory, or cleanup policies for context stored outside the prompt.
memory-system
Use for reading/writing structured memory blocks, hash-chain audit, session logs. Replaces flat STATE.MD with typed JSON blocks and provenance chain. Load when starting/ending sessions, recording decisions, or verifying facts.