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 skills add Dev-Jahn/hippocampus --skill hippogit clone --depth 1 https://github.com/Dev-Jahn/hippocampusWrote 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/dev-jahn/hippocampus/hippo)<a href="https://agentmods.dev/skills/dev-jahn/hippocampus/hippo"><img src="https://agentmods.dev/badge/skills/dev-jahn/hippocampus/hippo/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/dev-jahn/hippocampus/hippo"><img src="https://agentmods.dev/badge/skills/dev-jahn/hippocampus/hippo.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00013 | $0.01095 |
| Opus 5.5 | $0.00005 | $0.00438 |
| Sonnet 5.5 | $0.00003 | $0.00219 |
| Haiku 4.5 | $0.00001 | $0.00110 |
Grade A, and why
hippo 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 5d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
hippo — the project's hippocampus
hippo does not control you; it holds the memory — what you delegated, what was accepted or refuted, which of the user's instructions are still alive. The judgment is always yours.
Grammar
hippo init
hippo status [--inject]
hippo task add <type>/<slug> --title T [--notes N] [--deps a,b]
[--status pending|active|done|dropped]
hippo task set <id> title|status|notes|deps <value> # positional: no --flags
hippo task done <id> [--note N]
hippo task list [--status s1,s2] [--all] [--json]
hippo task show <id> [--json]
hippo task drop <id>
hippo log dispatch --id D --kind K --exec executor/model/effort --scope S
[--task T] [--depth N] [--parent D]
hippo log outcome --ref <dispatch-id>|task:<task-id> --result accepted|revised|refuted|no-go|lost
[--attr work|brief|harness] [--rework N] [--by executor/model] [--note N]
hippo log outcome --from-batch <journal> [--dry-run] < verdicts.jsonl
hippo log review --id R --base <sha> --source S --findings N
hippo log review-status --ref R --addressed full|partial|none [--at <sha>]
hippo log raw '<json>'
hippo log tail [-n N] [--ev TYPE]
hippo directive add --text T [--id kebab-id] [--audience main|executor|all]
[--state active|withdrawn|expired]
hippo directive list [--active] [--json]
hippo directive withdraw <id>
hippo prior show
hippo prior distill [--days N]
hippo dispatch --kind K --scope S [--task T] [--depth N] [--fast] [--] <codex exec args…>
hippo dispatch --batch <manifest.yaml> [--dry-run | --entry <id>] # --entry: the Workflow face's call, never typed
hippo dispatch --watch <dispatch-id|batch-id> [--for SECONDS]
# a bare noun reads: task → list, log → tail, directive → list, prior → show
When
- Work will outlive this turn →
task add;task donewhen it ships. - A delegation gets a verdict →
log outcome(--ref task:<id>finds its open dispatch). - The user rules →
directive add; re-add the same--idto change it,withdrawwhen done,--audience mainwhen a lane never needs it. A rule for the next answer only is not one. - An external review arrives →
log review; its findings dealt with →log review-status. - Before routing a delegation →
prior. - Codex lanes →
dispatch(--batchfor many,--watch <id>to wait); see/hippo:dispatch. - A subagent or Workflow run (Codex: a
spawn_agentchild): no call; the scribe records it and your verdict, in Claude Code asag-<agentId>or, once a Workflow ends,ag-wf_…(Run ID, not Task ID): name it in its verdict. One task id in its brief links it. - Lost your place →
status.
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.
- 5d ago Changed 43b746b49d43
- 21d ago Changed a4c15eff098c
- 22d ago Changed · +1 lines 5ca20f813141
- 23d ago Changed · +8 lines 52fce3606395
- 24d ago Changed · +5 lines ed5c2204ae67
- 1mo ago First seen · 61 lines · 13 tokens per session scan A ee57ac2b1c9e
hippo is a skill published in the GitHub repository Dev-Jahn/hippocampus (4 stars, last pushed 5d ago), licensed MIT. It adds 13 tokens to every session and 1,095 once invoked, about $0.0001 per session on Opus 5.5. 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
session-handoff
Synthesizes the current session into a structured HANDOFF block for context transfer between sessions. Captures what was built, decisions made, and unresolved items.
state-management
Cache management, configuration best practices, and progressive disclosure patterns for efficient context window usage. Use when working with large responses, optimizing token costs, or managing plugin state across operations.
session-recap
Document Claude Code sessions by extracting knowledge into cross-referenced documentation. Triggers on "recap the session", "summarize the work", or after significant code changes.
knowledge-bank-lookup
Delegates knowledge bank lookups to Explore subagents with reflections-first strategy that learns from past mistakes. Checks /reflections/ directory before documentation to extract documented failures to avoid and proven approaches to apply. Automatically triggers when user mentions services ([project-a], [project-b]…
kb-ingest
Ingest external sources into the knowledge bank through interactive study or quick filing. Two modes — Quick (summarize → file) and Study (theme-by-theme deep dive with online research and personal notes → multi-layer KB output → optional blog/slack synthesis). Triggers on "ingest this", "study this article", "add to…
session-manager
Set the current session's name, project, tags, or summary on its session note. Use when the user names, tags, or summarizes this session, sets its project, or mentions in passing what this session has been about.