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/andyduck-ops/omp-flow/omp-flow-sleepnpx skills add Andyduck-ops/omp-flow --skill omp-flow-sleepgit clone --depth 1 https://github.com/Andyduck-ops/omp-flowWrote 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/andyduck-ops/omp-flow/omp-flow-sleep)<a href="https://agentmods.dev/skills/andyduck-ops/omp-flow/omp-flow-sleep"><img src="https://agentmods.dev/badge/skills/andyduck-ops/omp-flow/omp-flow-sleep.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 | $0.00032 | $0.01004 |
| Opus 5 | $0.00016 | $0.00502 |
| Sonnet 5 | $0.00006 | $0.00201 |
| Haiku 4.5 | $0.00003 | $0.00100 |
Grade A, and why
omp-flow-sleep 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OMP-Flow Sleep
Use this Skill only with a complete assignment whose first non-blank line is an exact
{"ompFlowSleep":{...}} descriptor produced by .omp-flow/scripts/omp_flow.py sleep start.
Do not reconstruct, summarize, or guess a descriptor from an archived path.
Descriptor contract
Require version, sourceReceipt, sourceTask, sourceCommit, sourceTree, entry,
sleepIndex, runOutput, candidateRoot, actorId, receipt, and harvesterRevision.
Require version exactly 1, the assignment actor to match actorId, and every supplied path to
remain within the repository. Treat sourceReceipt, sourceCommit, sourceTree, receipt, and
harvesterRevision as opaque mechanical identity, not semantic evidence.
Method
- Read the archived Task
entryand follow only the Task Concepts needed to understand accepted outcomes, independent Review, verification, repeated findings, counterexamples, and expensive reasoning. Do not read raw Harness transcripts. - Read
sleepIndex. Use authored links, ordinary filenames, repository text search, and direct understanding of the smallest relevant Candidate/Wiki topics. Do not use embedding, vector retrieval, similarity thresholds, automatic taxonomy, a knowledge graph, or a fixed evidence schema. - Decide whether the Task supports zero, one, or several durable candidates. A Task-local fact, unverified explanation, generic lesson, or restatement of the Task is a valid zero-candidate result.
- For each useful topic, revise an existing Markdown Candidate beneath
candidateRootor create a self-contained one. Preserve ordinary links to the source Task and distinguish supporting evidence, contrary evidence, applicability boundaries, unresolved questions, and possible Wiki or Skill consequences. Never average a conflict into false consensus. - Write one OKF Run handoff at the exact
runOutput. State what was read, which Candidates were created or revised, why other observations were not promoted, and what review or experiment is still required. This handoff is authored knowledge; runtime state remains under.runtime. - Finish the mechanical run with:
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 · 89 lines · 32 tokens per session scan A 91634d092a52
omp-flow-sleep is a skill published in the GitHub repository Andyduck-ops/omp-flow (6 stars, last pushed 8d ago), licensed MIT. It adds 32 tokens to every session and 1,004 once invoked, about $0.0002 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 skills, from other repositories
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
auditing-subgroup-fairness
Audit an OpenMed NER or de-identification model for performance disparities across demographic subgroups (sex, age band, race/ethnicity when available) using openmed.eval.fairnessreport. Use when the user wants per-subgroup recall and leakage, wants to check whether de-identification under-protects a group, wants to…
agent-memory
../../../engineering/agent-memory/skills/agent-memory/SKILL.md.
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…