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/blas0/unseveredmemory/orchestratenpx skills add blas0/UnseveredMemory --skill orchestrategit 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/skills/blas0/unseveredmemory/orchestrate)<a href="https://agentmods.dev/skills/blas0/unseveredmemory/orchestrate"><img src="https://agentmods.dev/badge/skills/blas0/unseveredmemory/orchestrate.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 | $0.00000 | $0.01218 |
| Opus 5 | $0.00000 | $0.00609 |
| Sonnet 5 | $0.00000 | $0.00244 |
| Haiku 4.5 | $0.00000 | $0.00122 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Unsevered Memory - Workflow Skill
You are operating with persistent memory. This skill defines how to maintain context across sessions.
Memory Architecture
Two Sources of Truth
| Location | Type | Purpose | Update Frequency |
|---|---|---|---|
.claude/memory/ |
Dynamic | Session state, decisions | Every session |
.ai/ |
Static | Architecture, patterns | When patterns emerge |
File Purposes
| File | Content | When to Update |
|---|---|---|
context.md |
Current state, next steps | End of session |
scratchpad.md |
Live session operations | During session |
decisions.md |
Architectural choices | When decisions made |
.ai/core/ |
Tech stack, architecture | When they change |
.ai/patterns/ |
Reusable solutions | After 3+ uses |
Session Workflow
On Session Start
- Memory hook automatically loads
context.md - Review the current state and task
- Check
scratchpad.mdfor unfinished work - Reference
.ai/for patterns and architecture
During Session
Write to scratchpad.md as you work:
## Session: 2024-01-15 14:30
### Operations
- [14:31] Read context.md - last session worked on auth
- [14:32] User asked to fix login bug
- [14:35] Found issue in validateToken() at src/auth.ts:142
- [14:40] Fixed: was comparing wrong field
### Findings
- Token validation was checking user.id instead of user.uid
- Only affects users created after migration
### Decisions
- Keep backward compatibility by checking both fields
### Blockers
(none)
### Next Steps
- Add regression test for token validation
Update .ai/ when patterns emerge:
After implementing the same solution 3+ times, add it to .ai/patterns/.
On Session End
- Hook archives scratchpad to
sessions/YYYY-MM-DD.md - Update
context.mdwith:- What was accomplished
- Current state
- Next steps
- Append architectural decisions to
decisions.md
Live Documentation Updates
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 · 230 lines · 0 tokens per session scan A ed75627ae16b
orchestrate is a skill published in the GitHub repository blas0/UnseveredMemory (49 stars, last pushed 8mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,218 tokens. 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
throughline
Use when the user asks to use Throughline from Codex, continue or restore Throughline memory, export read-only handoff context for a local launcher, prepare a new Codex thread handoff, summarize a captured Codex session, or check whether the Throughline Codex Stop hook captured the current session. Hide long…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.
echo
Use when the user references past sessions, asks 'what did we do', 'do you remember', 'last session', 'recall', or 'continue from'.
durable-session-state
Persist plans, scope decisions, evidence, and reviewer/critic verdicts to durable files during long or multi-phase tasks so work survives context compaction, session resumes, and handoffs. Use for swarm-mode tasks, before context grows large, when recording approval gates, and when resuming after compaction or a…
mnemos
Task-scoped memory lifecycle — typed MnemoGraph prevents lossy context compaction by treating facts/decisions/code-refs/handoffs as distinct node types with per-type eviction policies.
wiki-sync
Synthesize a single source note into the vault's wiki/ folder — read the source, find or create the right wiki entry, write it back with proper frontmatter and source links. Used by Lumina's background wiki manager when a note changes.