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/hythe-dev/hythe/memorynpx skills add hythe-dev/hythe --skill memorygit clone --depth 1 https://github.com/hythe-dev/hytheWhat 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 | $0.00045 | $0.00594 |
| Opus 5 | $0.00023 | $0.00297 |
| Sonnet 5 | $0.00009 | $0.00119 |
| Haiku 4.5 | $0.00005 | $0.00059 |
Grade A, and why
memory 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 2d 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory Protocol (HYTHE)
One authoritative server holds the knowledge graph (entities → observations →
relations), agent inboxes, and session checkpoints. You talk to it through
mcp__hythe__* tools.
What belongs in memory
Save (via add_observations) when any of these happen:
| Event | kind | Notes |
|---|---|---|
| Decision made | decision |
include the why, not just the what |
| Bug fixed | bug / fix |
root cause mandatory |
| Non-obvious discovery | finding |
|
| Prior memory was wrong | correction |
MUST supersede — see below |
| Proposal/design produced | proposal |
|
| Handoff to another agent | handoff |
also send_ai_message |
Provenance rule: factual claims carry their source in the content (URL, command output, message id). An unattested figure is future bad data.
Corrections — the one thing you must not get wrong
A correction that merely adds leaves the wrong fact as a sibling. Always:
kind: correction, withcanonicalFactstating the corrected truthsupersedes: [<old-observation-id>], ormode: replace-currentto supersede the entity's current observation server-side
Retrieval
- Known entity name →
search_entitieswithsearchType: exact(fast, precise) - Fuzzy/exploratory →
searchType: hybrid, keeplimitsmall,compact: true - Entity state →
get_current_observation(NOT the embedded observations array, which is a creation-time snapshot) - Full content of one item →
get_entity_detail/get_message_detail
Sessions
- Start of session:
resume(recovers prior state), thenget_ai_messages(inbox — other agents leave work and answers there) - Substantial work finished, or compaction happened:
checkpointwith goal / discoveries / accomplished / next steps / relevant entities - Replying to another agent:
send_ai_messagewithfrom= your agentId; usesupersedeswhen replacing an earlier message of yours
Identity
Your agentId comes from HYTHE_AGENT_ID (e.g. claude-desktop; legacy
ENGRAM_AGENT_ID is honored only when it agrees). Never invent one; never
write attributed memory under another agent's id except an explicitly
authorized proxy write (say so in the content).
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.
- 2d ago First seen · 58 lines · 45 tokens per session scan A 51271c59f49f
memory is a skill published in the GitHub repository hythe-dev/hythe (0 stars, last pushed 5d ago), licensed Apache-2.0. It adds 45 tokens to every session and 594 once invoked, about $0.0002 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…