Project Starter is a workflow plugin that equips coding agents with specialized subagents, reusable skills, commands, hooks, and output styles for software projects. It is for developers who want structured assistance with tasks such as planning, debugging, code review, security, and automation across several coding-agent platforms. Catalogue add-ons are components of its own workflow.
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/cloudai-x/claude-workflow-v2/save-session-learningsgit clone --depth 1 https://github.com/CloudAI-X/claude-workflow-v2Wrote 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/commands/cloudai-x/claude-workflow-v2/save-session-learnings)<a href="https://agentmods.dev/commands/cloudai-x/claude-workflow-v2/save-session-learnings"><img src="https://agentmods.dev/badge/commands/cloudai-x/claude-workflow-v2/save-session-learnings.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 | $0.00028 | $0.00841 |
| Opus 5 | $0.00014 | $0.00420 |
| Sonnet 5 | $0.00006 | $0.00168 |
| Haiku 4.5 | $0.00003 | $0.00084 |
Grade A, and why
save-session-learnings 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 5d 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Save Session Learnings
Capture and persist significant discoveries from this session into project documentation so knowledge survives across sessions and agents.
Phase 1: Gather Session Context
Collect evidence of what was learned during this session:
git diff HEAD~5 --stat
git log --oneline -10
git diff --name-only HEAD~5
Also review the conversation history for:
- Bugs that were debugged (root cause + fix)
- Architecture decisions made
- Configuration or environment discoveries
- Patterns established or followed
- Commands that worked (or failed)
- Gotchas and edge cases encountered
Phase 2: Categorize Learnings
Sort each finding into one of these categories:
Architecture
- Key files, folders, data flow, component relationships
- Service boundaries, module dependencies
Patterns
- Naming conventions, code style, recurring design patterns
- File structure conventions, import ordering
Gotchas
- Things that break, common errors, non-obvious behavior
- Workarounds for known issues
Commands
- Build, test, deploy, dev server commands that work
- Tool-specific invocations with correct flags
Decisions
- Why something was done a certain way
- Trade-offs considered, alternatives rejected
Phase 3: Check Existing Documentation
Before writing, read both files to avoid duplicating entries:
- Use Glob to check if
CLAUDE.mdandAGENTS.mdexist in the project root - If they exist, Read them fully
- Compare gathered learnings against existing entries
- Skip anything already documented
- If existing entries are outdated, update them instead of adding duplicates
Phase 4: Write Learnings
Update both CLAUDE.md and AGENTS.md in the project root (create if missing).
Format for New Entries
Append to the ## Session Log section (create it if absent). Use this format:
## Session Log
- YYYY-MM-DD: [Category] Brief, actionable description of what was learned
For structured learnings, append to the relevant section (### Gotchas, ### Patterns, etc.) or create the section if it does not exist:
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.
- 5d ago First seen · 134 lines · 28 tokens per session scan A 275ca6bc9484
save-session-learnings is a command published in the GitHub repository CloudAI-X/claude-workflow-v2 (1,413 stars, last pushed 10d ago), licensed MIT. It adds 28 tokens to every session and 841 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 commands, from other repositories
context-save
An elite context engineering specialist focused on comprehensive, semantic, and dynamically adaptable context preservation across AI workflows. This tool orchestrates advanced context capture, serialization, and retrieval strategies to maintain institutional knowledge and enable seamless multi-session collaboration.
init-workspace-flow-discovery
Phase 3 Discovery of init-workspace-flow.
init-workspace-flow-questions
Phase 8 Questions of init-workspace-flow.
kiro-steering-custom
Command "kiro-steering-custom" from gotalab/cc-sdd, covering kiro custom steering creation, workflow, available templates, steering principles and tool guidance.
memory-why
Show why a memory recall returned what it did -- BM25 vs vector vs hybrid provenance.
review-code
Read ALL memory bank code rules + best practices, check the files that changed, and APPLY fixes so they adhere. The active counterpart to /scan (which is read-only). Use after an AI session, before commit, to make changed files compliant.