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/youdie006/sessionwiki/session-recallnpx skills add youdie006/sessionwiki --skill session-recallgit clone --depth 1 https://github.com/youdie006/sessionwikiWrote 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/youdie006/sessionwiki/session-recall)<a href="https://agentmods.dev/skills/youdie006/sessionwiki/session-recall"><img src="https://agentmods.dev/badge/skills/youdie006/sessionwiki/session-recall.svg" alt="Measured on agentmods" 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 | $0.00103 | $0.00851 |
| Opus 5 | $0.00051 | $0.00426 |
| Sonnet 5 | $0.00021 | $0.00170 |
| Haiku 4.5 | $0.00010 | $0.00085 |
Grade A, and why
session-recall 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Session recall: use sessionwiki as long-term memory
The user's machine has a sessionwiki index of every past Claude Code, Codex,
and Gemini CLI session. Treat it as the agent's long-term memory. It is local
and offline - no network. Before solving something from scratch, check whether
it was already solved.
When to recall
- Starting a non-trivial task -> search for prior work on the same topic first.
- The user references earlier work ("the auth flow we built", "last week", "that CORS fix") -> recall it instead of asking them to re-explain.
- You need to know which session changed a file -> trace it.
How to recall (run these, do not guess)
-
First time only, confirm the tool exists:
command -v sessionwikiIf it prints nothing, the tool is not installed - see "If sessionwiki is missing" below and stop using this skill for the rest of the turn.
-
Search prior sessions on the task topic:
sessionwiki search --json "<topic keywords>"Returns an array of hits:
id,tool,project,started,role,snippet. Pick the 1-3 most relevantids. -
Pull context from a promising session before acting:
sessionwiki brief --json <id>Returns the session's title, project, date, and a budgeted markdown transcript. Read it; carry forward decisions, file names, and gotchas. Do not re-derive what the prior session already settled.
-
Trace a file to the sessions that touched it, newest first:
sessionwiki trace --json <path-as-it-appears-in-the-editor>e.g.
sessionwiki trace --json src/auth.rs. Returns sessions that touched the file (not line-level authorship) - use it to find the conversation behind a change, thenbriefit.
Rules
- Prefer recall over re-asking the user for context that already exists on disk.
- Keep queries specific: "jwt refresh retry", not "auth". Two-word topics beat one. The index matches substrings, so partial identifiers and non-English (e.g. Korean, including short words) text work.
- Cite what you recalled: "Found it - session
3f9cset the retry to 3 attempts." - Recall is read-only. It never modifies sessions or code.
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 First seen · 71 lines · 103 tokens per session scan A d3cc0048eba1
session-recall is a skill published in the GitHub repository youdie006/sessionwiki (6 stars, last pushed yesterday), licensed MIT. It adds 103 tokens to every session and 851 once invoked, about $0.0005 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
qmd
Search the vault using QMD semantic search. Use PROACTIVELY before reading files. Preference order: (1) MCP tools — mcpqmdquery, mcpqmdget, mcpqmdmultiget, mcpqmdstatus — if they appear in your tool menu, use them first; (2) CLI qmd --index ... as fallback; (3) Grep/Glob only when QMD is not installed. Trigger…
neo4j-agent-memory-skill
Authoritative reference for the neo4j-agent-memory Python package — a graph-native memory system for AI agents built on Neo4j — and for the hosted service (NAMS) at memory.neo4jlabs.com. Use this skill whenever the user mentions neo4j-agent-memory, agent memory with Neo4j, context graphs, the POLE+O model…
context-degradation
Recognize patterns of context failure: lost-in-middle, poisoning, distraction, and clash.
context-compression
Design and evaluate compression strategies for long-running sessions.
lov-search-chat
从本机 Ataru 记忆索引里召回过去的 AI 会话上下文，返回可定位的命中与原文片段。 Use when asked what was discussed, decided, or fixed in an earlier session.
context-optimization
Apply compaction, masking, and caching strategies.