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/wallneradam/project-mem-mcp/dreamgit clone --depth 1 https://github.com/wallneradam/project-mem-mcpWrote 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/wallneradam/project-mem-mcp/dream)<a href="https://agentmods.dev/commands/wallneradam/project-mem-mcp/dream"><img src="https://agentmods.dev/badge/commands/wallneradam/project-mem-mcp/dream.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 | $0.00008 | $0.00257 |
| Opus 5 | $0.00004 | $0.00129 |
| Sonnet 5 | $0.00002 | $0.00051 |
| Haiku 4.5 | $0.00001 | $0.00026 |
Grade A, and why
dream 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
Run the project-mem:dream skill (use the full plugin-namespaced name, not bare dream) to consolidate the project's MEMORY.md file.
This can be triggered manually at any time, regardless of file size or last consolidation time.
Follow the skill's subagent prompt template EXACTLY:
- No
model:parameter on the Agent call — it overrides the pinnedclaude-sonnet-5and runs consolidation on expensive Opus. - No extra instructions of your own. Do not add "be conservative", "preserve in full", "don't drop anything" or a restatement of the consolidation rules — the subagent already has them, and your prose outranks them, which is exactly how dreams end up compressing ~5% instead of doing their job.
- If this session wrote something into MEMORY.md that must survive untouched, list it as pointers in the template's
## Preserve verbatim — added or revised in this session:field. That field is the only sanctioned place for it.
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 · 14 lines · 8 tokens per session scan A 3cb97350c82d
dream is a command published in the GitHub repository wallneradam/project-mem-mcp (2 stars, last pushed 17d ago), licensed MIT. It adds 8 tokens to every session and 257 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
checkpoint
Full memory flush — refresh state.md, append to activity log, route any new decisions/insights, then commit and push.
memory-gc
Inspect or rotate hunt-memory JSONL files (audit.jsonl, patterns.jsonl, journal.jsonl). Caps file size and keeps N rotated backups so memory does not grow unbounded.
iai-directive
Record a standing order the user typed themselves, as an explicit memory directive.
init-workspace-flow-questions
Phase 8 Questions of init-workspace-flow.
session-end
I'll summarize this coding session and update the memory system with our accomplishments.
weekly
Weekly memory report — facts learned, procedures, repeated mistakes prevented.