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/dev-jahn/hippocampus/dispatchnpx skills add Dev-Jahn/hippocampus --skill dispatchgit clone --depth 1 https://github.com/Dev-Jahn/hippocampusWhat 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 | $0.00080 | $0.04012 |
| Opus 5 | $0.00040 | $0.02006 |
| Sonnet 5 | $0.00016 | $0.00802 |
| Haiku 4.5 | $0.00008 | $0.00401 |
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.
How it starts
The opening of the file, as written. The whole thing — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.
hippo: dispatch — parallel delegation waves
The successor to fleet-dispatch, revised. Every revision here comes from a dogfooding audit or a measurement against the Opus 5 guide.
0. Thirty seconds before launch
hippo prior show— check which (model, effort) measured better for this kind. A prior is advice: main still decides the final routing from the difficulty and volume of the work at hand.hippo task— what can start now: a lane whose task shows awaiting on:line still has an unfinished dep and belongs in a later wave.hippo directive list --active— check what the lanes will see. Directives whose audience includes executors reach every lane through its own capsule (status --inject, re-injected after compaction) — do not copy them into briefs; one source, no drift. Hand-fold a constraint only where hooks cannot run and the lane might skip the bootstrap. Grep COMMON against the individual brief for conflicting clauses (contradictory clauses once produced a fail-closed NO-GO).- Asset preflight: main verifies that the files, models and data the brief names actually exist.
1. Role routing
| Kind of work | Assigned to |
|---|---|
| Registry, merge, gate, push, acceptance verdict | main, directly |
| An experiment that is one command (soak/bench) | main's run_in_background Bash |
| Implementation or investigation that edits files | an external executor lane (own worktree) |
| Boundary verification of another executor's output | a verification lane — budget in §4 |
| Hard design work | an independent duo, then synthesis by main |
- Never spawn a subagent to re-verify your own work — current models verify themselves. A verification lane is for the boundary of a different executor's output.
- Do not delegate small chores: when writing the prompt costs more than doing the work, it costs more.
2. Launch contract
hippo dispatch --kind kernel-impl --scope "pass2 tensorize" --task feat/x \
-m gpt-5.6-sol -c model_reasoning_effort=high \
-C .claude/worktrees/pass2 --dangerously-bypass-approvals-and-sandbox --skip-git-repo-check \
"$(cat .hippo/briefs/COMMON.md .hippo/briefs/pass2.md)"
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 · 240 lines · 80 tokens per session scan A 2443ba5a3097
dispatch is a skill published in the GitHub repository Dev-Jahn/hippocampus (4 stars, last pushed 19d ago), licensed MIT. It adds 80 tokens to every session and 4,012 once invoked, about $0.0004 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
codexkit-repository-maintenance
Use when maintaining or improving the GameStudio-CodexKIT source repository, including CI, governance, catalog, generators, adapters, packaging, documentation, versioning, or release readiness.
unity-ui-art-and-motion-production
Use when new or revised Unity UI visuals, icons, panels, 9-slice sprites, component states, HUD or menu layouts, popup motion, screen transitions, or flattened UI screenshot decomposition must be produced through Figma and integrated into uGUI, NGUI, or UI Toolkit; not for UI debugging, localization-only work…
game-screenshot-showcase-and-store-packaging
Use when a Unity team needs approved PlayMode screenshots, immutable capture evidence, reviewed showcase slides, or report-only store screenshot packaging without auto-upload, signing, or submission.
studio-project-scaffold
Use when running gamestudio init, status, or uninit, or bootstrapping a new or adopted game repository with AGENTS.md, HANDOFF.md, .agents/CONTRACT.md, project governance, a subsystem registry, or a per-project adapter report, plan digest, named reviewer, backup root, generated agent overlay, apply, uninstall, and…
using-game-studio-skills
Use when starting any GameStudio-CodexKIT task or when a model runner is unavailable and someone requests a confidence-based PASS.
skill-authoring-and-audit
Use when creating or revising a GameStudio-CodexKIT skill, resolving ambiguous skill triggers, auditing provenance or lifecycle maturity, or deriving reusable capabilities from session history.