anamnesis

anamnesis is a skill for Claude Code, Codex from chaosisnotrandomitisrhythmic/anamnesis-mcp. It costs 58 tokens per session (626 once invoked), scanned A, original, MIT.

A tool for searching and comparing past Claude Code session logs. It can find sessions, entries, sections, and open work items across the recorded history.

In plain words
What is it for?
Use it to find a previous session, summarize what was done, locate a specific section, or cross-reference plans and open items across sessions.
Why use it?
It helps recover decisions, context, and unfinished tasks without manually opening old session files one by one.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Claude Code.

Good fit Use it to find a previous session, summarize what was done, locate a specific section, or cross-reference plans and open items across sessions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/chaosisnotrandomitisrhythmic/anamnesis-mcp/skill
Install

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.

Any agent
npx skills add chaosisnotrandomitisrhythmic/anamnesis-mcp --skill skill
Clone the repo
git clone --depth 1 https://github.com/chaosisnotrandomitisrhythmic/anamnesis-mcp

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for anamnesis

README.md
[![agentmods](https://agentmods.dev/badge/skills/chaosisnotrandomitisrhythmic/anamnesis-mcp/skill.svg)](https://agentmods.dev/skills/chaosisnotrandomitisrhythmic/anamnesis-mcp/skill)
Your own site
<a href="https://agentmods.dev/skills/chaosisnotrandomitisrhythmic/anamnesis-mcp/skill"><img src="https://agentmods.dev/badge/skills/chaosisnotrandomitisrhythmic/anamnesis-mcp/skill.svg" alt="Measured on agentmods" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 626 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00058 $0.00626
Opus 5 $0.00029 $0.00313
Sonnet 5 $0.00012 $0.00125
Haiku 4.5 $0.00006 $0.00063

Measured 8d ago against content hash cf87061a8378, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

anamnesis 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 8d 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.

examples/skill/SKILL.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Anamnesis — Session Search & Cross-Reference

Search, summarize, and cross-reference past Claude Code session logs via the Anamnesis MCP server.

How to Execute

1. Search for sessions

Use the anamnesis MCP tools:

Core tools:

  • mcp__anamnesis__search_sessions — BM25 full-text search (primary tool)
  • mcp__anamnesis__get_session — retrieve full session by ID
  • mcp__anamnesis__list_sessions — browse/paginate with date/tag/host filters
  • mcp__anamnesis__search_entries — cross-session search for Plan/Done/Open items

Section tools:

  • mcp__anamnesis__get_section — extract a specific timestamped section from a session
  • mcp__anamnesis__list_sections — list all headings in a session
  • mcp__anamnesis__search_sections — find a heading across all sessions

Analysis tools:

  • mcp__anamnesis__analyze_corpus — corpus stats (sessions, words, tags, open items)
  • mcp__anamnesis__run_analysis — ad-hoc Python code execution against session data (local only)

2. Summarize results

When presenting session search results:

  • List matching sessions with date, title, and a one-line summary
  • Quote the rolling summary paragraph for relevant hits
  • Highlight Open items — these are unfinished work the user may want to resume

3. Cross-reference sessions

When asked to cross-reference or find related sessions:

  • Search for overlapping topics, tools, or projects across multiple sessions
  • Group related sessions chronologically to show how work evolved
  • Call out when an Open item from one session was resolved in a later session
  • Note recurring themes or tools across sessions

4. Resume suggestions

When a session has open items, remind the user they can resume with:

claude --resume <session-id>

The session ID is in the footer of each log file.

Rules

  1. Always search via the MCP tools — don't rely on memory alone
  2. Default to search_sessions for topic queries, search_entries for finding specific Plan/Done/Open items
  3. When multiple sessions match, present them in chronological order
  4. Keep summaries concise — the user can ask to read the full log
  5. Use get_session to retrieve full content when the user wants detail

Read the full file on GitHub · 61 lines

Changes

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.

  1. 8d ago First seen · 61 lines · 58 tokens per session scan A cf87061a8378

Subscribe to this mod's changes

anamnesis is a skill published in the GitHub repository chaosisnotrandomitisrhythmic/anamnesis-mcp (1 stars, last pushed 5mo ago), licensed MIT. It adds 58 tokens to every session and 626 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

media-ingest

Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.

garrytan/gbrain · 52 tokens

mem0-oss-to-platform

Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…

mem0ai/mem0 · 273 tokens

Cortex

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…

danielmiessler/LifeOS · 196 tokens

memory

Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.

opensquilla/opensquilla · 44 tokens

ha-data-stores

Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…

shiwenwen/hope-agent · 115 tokens

establishing-project-context

Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.

GanyuanRan/Aegis · 45 tokens