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/gxfn/wakeflow/initgit clone --depth 1 https://github.com/GxFn/WakeflowWhat 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 | $0.00011 | $0.00451 |
| Opus 5 | $0.00005 | $0.00226 |
| Sonnet 5 | $0.00002 | $0.00090 |
| Haiku 4.5 | $0.00001 | $0.00045 |
Grade A, and why
init 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 yesterday.
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
Initialize the current workspace with the public v3 maintenance owner.
- Build one explicit closed
selectioncoveringprogram,topology,storage,governance, andhosts. Repository/support/window entries link with request-localselectionKey; do not invent durable IDs or infer Design/Test from similar directory names. - Call
wakeflow_maintain_workspacewithaction: "fresh-initialize",mode: "preview", the workspace root, the complete selection, and the user's language. Preview is read-only. - Show the user the exact managed surfaces, blockers,
launchIntents, and confirmed plan boundary. Wait for explicit confirmation. - Apply with the same root/action,
mode: "apply", and the exactconfirmedActionPlanplusconfirmedActionPlanDigestreturned by preview. Never reconstruct or edit the plan. - If apply reports recovery-required, call the same action with
mode: "recover", the exact plan/digest, and namedoperationId. - Report created/verified surfaces and retained launch intents. Do not dispatch work from initialization.
An existing strict v3 workspace uses reconfigure for an intentional desired
model change or reconcile to restore managed bytes/projections. There is no
reset/discovery/useDiscovered alias. A recognized legacy workspace requires the
explicit unregistered bootstrap path and separate user authorization; /init
must not import or delete legacy state.
launchIntents are host-neutral authority. Route them through the packaged v3
Claude host facade's exact launch-window command, then register the final
real session with wakeflow_register_window operation=register. Retired
public-v2 window-host/thread-registry commands are not aliases. If the exact
host effect or receipt is unavailable, report the intents and stop without
writing substitute runtime.
If the Wakeflow MCP surface is unavailable, stop for plugin reload/reinstall; do not invoke backend scripts or cache paths directly.
$ARGUMENTS
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.
- yesterday First seen · 41 lines · 11 tokens per session scan A 4dd0be23b555
init is a command published in the GitHub repository GxFn/Wakeflow (5 stars, last pushed 8d ago), licensed MIT. It adds 11 tokens to every session and 451 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 commands, from other repositories
release-flow
Portable gated release flow — deterministic gate + vendor-agnostic independent reviewer, runnable from any harness.
release
Prepare a release (step 1 of 2) — version bump and PR. Cutting the tag is a separate operator-only step.
fieldtheory
Explain and drive the Field Theory CLI — bookmark-sourced seeds, repo-aware possibility runs that score ideas onto a 2x2 grid, and the interconnected .md files they leave behind. Trigger when the user asks about ft, bookmarks, seeds, ft possible (or the older name ft ideas), grids, dots/nodes, or how to turn saved…
lians-recall
Recall current (non-stale) facts from Lians memory, optionally as-of a past date.
scorecard
Run a repeatable weekly health check. Score Brain OS out of 100. Compare week-over-week.
review
Comprehensive code review for blz changes.