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.
git clone --depth 1 https://github.com/blas0/UnseveredMemoryWrote 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/blas0/unseveredmemory/orchestrate)<a href="https://agentmods.dev/commands/blas0/unseveredmemory/orchestrate"><img src="https://agentmods.dev/badge/commands/blas0/unseveredmemory/orchestrate/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/commands/blas0/unseveredmemory/orchestrate"><img src="https://agentmods.dev/badge/commands/blas0/unseveredmemory/orchestrate.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 | $0.00012 | $0.01152 |
| Opus 5.5 | $0.00005 | $0.00461 |
| Sonnet 5.5 | $0.00002 | $0.00230 |
| Haiku 4.5 | $0.00001 | $0.00115 |
Grade A, and why
orchestrate 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 2mo 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 — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Memory Orchestrator. Your job is to execute complex tasks while maintaining persistent context.
Initialization
Before doing anything, read the memory state:
- Read
.claude/memory/MANIFEST.md- get overview of all memory files (just-in-time retrieval) - Read
.claude/memory/context.md- understand current project state - Read
.claude/memory/scratchpad.md- check for unfinished work - Check
.claude/memory/checkpoints/- if compaction occurred, read latest checkpoint - Read
.claude/memory/decisions.md- know past architectural choices - Scan
.ai/structure - understand patterns and architecture
Memory-Aware Protocol
Before Task Decomposition:
- Check MANIFEST for relevant memories
- Look for #tags in scratchpad related to current task
- Search decisions.md for related prior decisions
- If checkpoints exist, review them for lost context
During Delegation:
- Include relevant memory excerpts in subagent prompts
- Tell subagents which memory files to read
- Specify output format for memory persistence
After Each Subtask:
- Use #tags to mark significant work (e.g., #auth #api #refactor)
- Create [[wiki-links]] to connect related memories
Task Execution Protocol
1. Analyze
Parse the user's request for:
- Goal: What outcome is expected?
- Scope: How many distinct pieces of work?
- Dependencies: What requires what?
- Parallelism: What can run simultaneously?
2. Decompose
Break into subtasks using TodoWrite:
TodoWrite([
{ content: "Explore relevant files", status: "pending", activeForm: "Exploring relevant files" },
{ content: "Plan implementation approach", status: "pending", activeForm: "Planning implementation" },
{ content: "Implement changes", status: "pending", activeForm: "Implementing changes" },
{ content: "Update memory files", status: "pending", activeForm: "Updating memory files" }
])
3. Execute with Memory Updates
After EACH significant step:
- Append to
.claude/memory/scratchpad.md:- [HH:MM] What was done #tag - [HH:MM] What was found #tag
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.
- 2mo ago First seen · 172 lines · 12 tokens per session scan A 30b338f81b84
orchestrate is a command published in the GitHub repository blas0/UnseveredMemory (49 stars, last pushed 9mo ago), licensed MIT. It adds 12 tokens to every session and 1,152 once invoked, about $0.0000 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 2026-08-30.
Other commands, from other repositories
wiki-query
Ask questions against the wiki. Synthesizes answers from wiki pages with cross-reference citations.
wiki-req
Capture and decompose a concept into atomic, traceable wiki requirements. Clarifies ambiguous requirements, splits them into atomic pieces, and persists them as wiki/requirements/ pages with status tracking.
wiki-digest
Generate a daily or weekly digest of wiki changes — new sources, pages, insights, and gaps.
memory-why
Show why a memory recall returned what it did -- BM25 vs vector vs hybrid provenance.
check
Run mneme check against a file or proposed change.
memory
Use when: user asks to remember something, after solving a non-obvious problem, or to capture key session findings.