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/primeline-ai/claude-code-starter-system/project-statusgit clone --depth 1 https://github.com/primeline-ai/claude-code-starter-systemWrote 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/primeline-ai/claude-code-starter-system/project-status)<a href="https://agentmods.dev/commands/primeline-ai/claude-code-starter-system/project-status"><img src="https://agentmods.dev/badge/commands/primeline-ai/claude-code-starter-system/project-status.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 5.1 | $0.00009 | $0.00514 |
| Opus 5 | $0.00005 | $0.00257 |
| Sonnet 5 | $0.00002 | $0.00103 |
| Haiku 4.5 | $0.00001 | $0.00051 |
Grade A, and why
project-status 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.
What it actually says
/project-status
Show the current project status, or set up project memory for the first time.
Workflow
Step 1: Check for Existing Memory
Read .claude/memory/index.json.
Path A: Memory Exists
Read .claude/memory/projects/{active}.json where {active} is the project name from the index.
Display the project status:
Project: {name}
Phase: {phase}
Goal: {primary goal from the goals array}
Recent Progress:
- {most recent progress entry - date + summary}
- {second most recent}
- {third most recent}
(show up to 3 entries, most recent first)
Blockers: {blockers field, or "None"}
Then ask: "What would you like to work on?"
Path B: No Memory Found - Initialize
If .claude/memory/index.json does not exist, start the initialization flow.
Ask these questions one at a time:
- "What project are you working on? (This will be the project name)"
- "What is the primary goal for this project?"
- "What phase are you in? (planning / building / testing / launching)"
After all three answers, create the memory files:
.claude/memory/index.json:
{
"active": "{name-slug}",
"updated": "{YYYY-MM-DD}"
}
Where {name-slug} is the project name in lowercase kebab-case (e.g., "My App" becomes "my-app").
.claude/memory/projects/{name-slug}.json:
{
"name": "{project name as given}",
"phase": "{phase}",
"goals": ["{primary goal}"],
"progress": [],
"blockers": []
}
Create the .claude/memory/projects/ directory path as needed.
Confirm with:
Project initialized! Memory will persist across sessions.
Project: {name}
Phase: {phase}
Goal: {goal}
Use /handoff at the end of each session to save your progress.
Use /remember to save solutions, patterns, and decisions as you work.
Plain Text Triggers
- "project status"
- "what project are we on"
- "show project"
- "initialize project"
- "set up memory"
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 · 98 lines · 9 tokens per session scan A e7a526857a7a
project-status is a command published in the GitHub repository primeline-ai/claude-code-starter-system (5 stars, last pushed 21d ago), licensed MIT. It adds 9 tokens to every session and 514 once invoked, about $0.0000 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 2026-08-31.
Other commands, from other repositories
memstack-search
Search MemStack memory for past sessions, insights, and project context.
prune
Delete pending instincts older than 30 days that were never promoted.
instinct-status
Show learned instincts (project + global) with confidence.
consolidate
Dream cycle -- promote patterns, prune stale, reconcile contradictions, optionally promote to global.
memory-why
Show why a memory recall returned what it did -- BM25 vs vector vs hybrid provenance.
context-stats
Display context window usage and token statistics.