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/dispatchgit 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 | $0.00020 | $0.00389 |
| Opus 5 | $0.00010 | $0.00195 |
| Sonnet 5 | $0.00004 | $0.00078 |
| Haiku 4.5 | $0.00002 | $0.00039 |
Grade A, and why
dispatch 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
Run one controller dispatch step through the wakeflow-controller Skill.
- Confirm this is the demand's stamped Controller and select one eligible typed target task. Do not infer a Pod/controller from a title.
- Call
wakeflow_prepare_delivery operation=target-preview. Review the exact current state, binding, repository, TaskPackage, prompt, plan, and digest. Preview is zero-write. - After confirming it, call
operation=target-applywith the exact returned plan/digest. Apply writes immutable group/packet/envelope transport only. - Immediately before the host effect call
operation=target-claimwith the exact current binding/envelope tuple. A stale or conflicting lease stops the dispatch. - Route the effect through the packaged v3 Claude host facade's exact
target-deliverycommand. Its transport owner holds the stable-window operation mutex across validation, physical paste, and at most one bounded readback. Retired public-v2deliver/registry commands are not aliases; if exact host execution or its receipt is unavailable, stop and report the blocker. - Record the observed fact with
wakeflow_record_delivery operation=target-outcome. The recorder is not the host-effect fence. - End the turn. Accepted, ambiguous, or sent-unconfirmed transport is never
resent. Only a proved rejected-before-send flow may later use
wakeflow_prepare_delivery operation=target-rearm.
Never poll for completion, delete a lease file, or release by semantic window name. Controller-return has its own preview/apply/pre-send path and takes no target lease.
$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 · 35 lines · 20 tokens per session scan A 390ce5d314c7
dispatch is a command published in the GitHub repository GxFn/Wakeflow (5 stars, last pushed 8d ago), licensed MIT. It adds 20 tokens to every session and 389 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.