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/flow-statusnpx skills add Andyduck-ops/omp-flow --skill flow-statusgit clone --depth 1 https://github.com/Andyduck-ops/omp-flowWhat 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 | $0.00024 | $0.00886 |
| Opus 5 | $0.00012 | $0.00443 |
| Sonnet 5 | $0.00005 | $0.00177 |
| Haiku 4.5 | $0.00002 | $0.00089 |
Grade A, and why
flow-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 3d 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
Flow Status
Use this Skill only for read-only Flow Status inspection.
-
Resolve the repository root containing
.omp-flow. -
Resolve one exact host and session only from the Harness currently executing this Skill and current-process runtime evidence. Treat empty or whitespace-only variables as absent.
Host Current-host evidence Exact session evidence claudeNative Claude Skill execution, optionally confirmed by OMP_FLOW_HOST=claudeOMP_FLOW_CONTEXT_IDbridged from Claude'ssession_idcodexCODEX_THREAD_ID, optionally confirmed by native Codex execution orOMP_FLOW_HOST=codexThe same CODEX_THREAD_ID; ifOMP_FLOW_CONTEXT_IDis also present, it must matchoh-my-piNative Oh My Pi Skill execution, OMP_SESSION_ID, orPI_SESSION_ID, optionally confirmed byOMP_FLOW_HOST=oh-my-piOMP_FLOW_CONTEXT_ID,OMP_SESSION_ID, orPI_SESSION_ID; every present value must matchsnowSNOW_SESSION_ID, optionally confirmed by native Snow execution orOMP_FLOW_HOST=snowThe same SNOW_SESSION_ID; ifOMP_FLOW_CONTEXT_IDis also present, it must matchcursorHook-injected OMP_FLOW_HOST=cursor, optionally confirmed by native Cursor executionThe matching Hook-injected OMP_FLOW_CONTEXT_IDcarrying Cursor'sconversation_id- A non-empty
OMP_FLOW_HOSTis valid only when it is exactlyclaude,codex,oh-my-pi,snow, orcursor. A valid value is authoritative explicit evidence; any other value makes Flow Status unavailable. Cursor never falls back to an implicit or configured host. - Native Harness identity means the Harness actually executing this Skill. It is runtime
evidence, not a configured Harness name.
OMP_FLOW_CONTEXT_IDalone does not identify a host; it supplies a session only after the current host is established by the table. CODEX_THREAD_ID,OMP_SESSION_IDorPI_SESSION_ID, andSNOW_SESSION_IDalso claim hostscodex,oh-my-pi, andsnow, respectively. If explicit, native, or variable-based evidence claims more than one host, report ambiguous evidence and stop. If multiple session variables apply to the selected host, every non-empty value must be identical.- Missing host evidence, missing matching session evidence, invalid explicit evidence, or any
host/session conflict makes Flow Status unavailable. Never read
.omp-flow/config.json,.omp-flow/config.yaml, configured Harness order, cache recency, task counts, or Markdown to choose the current host or session.
- A non-empty
-
Run the project-local supported inspect surface with those exact values:
python -X utf8 .omp-flow/scripts/omp_flow.py --cwd <repository-root> status inspect --host <host> --session <host-session-id> --jsonUse
python3instead ofpythonwhere that is the platform command. Never fall back to another host or session cache entry. Do not call another status renderer, inspect transcripts, or infer task facts from Markdown. -
Report the task-set source and freshness, current task, literal assignment role and mapped position, task-local progress, and attention exactly when present.
-
If the response is unavailable, stale, clock-uncertain, malformed, disconnected, or scope-mismatched, say so. Do not preserve old counts, role, progress, approval, or current-task claims as current.
This surface is read-only. Do not use cached status to select or archive a task, start or finish an
operation, approve work, attach to or interrupt an agent, stop a process, edit tui.status_line,
or claim that Codex has a persistent third-party footer.
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.
- 3d ago First seen · 55 lines · 24 tokens per session scan A cec4319fc8b2
flow-status is a skill published in the GitHub repository Andyduck-ops/omp-flow (5 stars, last pushed 7d ago), licensed MIT. It adds 24 tokens to every session and 886 once invoked, about $0.0001 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…