agentmods.dev

memory-doctor

memory-doctor is a skill for Claude Code from atman-33/workhub. It costs 67 tokens per session (799 once invoked), scanned A, original, MIT.

A diagnostic tool that checks whether the agent's long-term memory system is set up and recording sessions correctly.

In plain words
What is it for?
Use it when memory seems out of date, after sessions stop being remembered, or before investigating a memory problem. It reports whether the system works and explains actions for common failures.
Why use it?
Memory systems can fail quietly, leaving sessions empty or stale without showing an error. This check identifies setup, storage, model-cache, database, and recording problems.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: mentions OpenCode.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the memory plugin — 5 skills shipped together

not rated 3repo 2d ago A scan 67 tokens original MIT

Good fit Use it when memory seems out of date, after sessions stop being remembered, or before investigating a memory problem. It reports whether the system works and explains actions for common failures.

Compare 6 skills from other repositories ↓
View source ↗ atman-33/workhub
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add atman-33/workhub
Claude Code
/plugin install memory

Made for: Claude Code.

Or install memory, the plugin that ships this one along with the rest of its 5 skills.

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 memory-doctor

README.md
[![agentmods](https://agentmods.dev/badge/skills/atman-33/workhub/memory-doctor/github.svg)](https://agentmods.dev/skills/atman-33/workhub/memory-doctor)
Your own site
<a href="https://agentmods.dev/skills/atman-33/workhub/memory-doctor"><img src="https://agentmods.dev/badge/skills/atman-33/workhub/memory-doctor/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.

agentmods 80×15 button for memory-doctor

Your own site · 80×15
<a href="https://agentmods.dev/skills/atman-33/workhub/memory-doctor"><img src="https://agentmods.dev/badge/skills/atman-33/workhub/memory-doctor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 799 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 $0.00067 $0.00799
Opus 5.5 $0.00027 $0.00320
Sonnet 5.5 $0.00013 $0.00160
Haiku 4.5 $0.00007 $0.00080

Measured 28d ago against content hash e4aecda71321, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

memory-doctor 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 28d 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.

plugins/memory/skills/memory-doctor/SKILL.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

memory-doctor — Is memory actually working?

memory-recall answers "what do I remember". This answers "am I still remembering at all".

It exists because the engine is deliberately silent: every hook swallows its own errors so a session is never broken by a memory problem. That is the right trade for a hook and the wrong one for the owner — capture failed on 180 of 193 sessions for six weeks before anyone looked (T-0366). Nothing surfaces unless something goes looking.

Steps

  1. Run the check.

    node "${CLAUDE_PLUGIN_ROOT}/engine/cli.mjs" doctor

    Every line is ok / WARN / FAIL, and each problem carries the action that fixes it. The command exits 1 only on FAIL, so a warning does not fail a script that runs it.

  2. Report what it found, in the user's language. Lead with the verdict — working, working with a caveat, or not working — then the lines that are not ok. Do not paste the whole report when everything passes; say it passed and give the memory and session counts.

  3. Act on the common ones, rather than only relaying them:

    Line What it means What to do
    FAIL setup No marker, or it predates this engine version Run the memory-setup skill. Until it succeeds every hook is a no-op
    FAIL engine copy ~/.workhub/memory-engine/engine/ is missing or stale Run memory-setup. OpenCode calls that copy, not the plugin
    FAIL database The file cannot be opened Check it is not held open elsewhere; report the message verbatim
    FAIL capture failures Writes are failing in a row Read lastError. Once the cause is gone, cli.mjs capture-retry
    WARN capture queue Sessions written to the retry queue cli.mjs capture-retry, or just start another session — capture drains it
    WARN capture (never / N days) Nothing has been recorded recently If the user has been working in this vault since, capture is failing — not idle
    WARN embeddings A backlog of un-embedded rows cli.mjs embed-pending --all and watch for an error; search is keyword-only until it clears
    WARN opencode log The OpenCode side logged a problem Read <vault>/.opencode/plugins/logs/memory.log — it is only written when something went wrong

Read the full file on GitHub · 59 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. 28d ago First seen · 59 lines · 67 tokens per session scan A e4aecda71321

Subscribe to this mod's changes

memory-doctor is a skill published in the GitHub repository atman-33/workhub (3 stars, last pushed 2d ago), licensed MIT. It adds 67 tokens to every session and 799 once invoked, about $0.0003 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 2026-09-19.

Claude CodeDebuggingMemory and contextclaude-code-plugincross-platformdesktop-appdeveloper-toolsobsidian
Related

Other skills, from other repositories

distill

When there's a failure, bug, unexpected behavior, or important finding, distills it into a verified general rule saved under .loop/memory/. Invoke right after resolving a gate (test/typecheck) failure, right after fixing a verifier-graded fail, or right after pinning down a cause through debugging. Exclude failures…

hiphapis/loopcraft · 80 tokens

code-understand

Map the load-bearing files, symbols, callers, and dependencies of an unfamiliar codebase before making changes. Use for architecture orientation, impact analysis, what-would-break questions, or finding callers. Uses CodeGraph when available and a dependency-free builtin fallback.

Ar9av/obsidian-wiki · 55 tokens

compound-docs

Searchable Elixir/Phoenix/Ecto solution documentation system with YAML frontmatter. Builds institutional knowledge from solved problems. Use when consulting past solutions before investigating new issues.

oliver-kriska/claude-elixir-phoenix · 38 tokens

garden-tending

Tend the knowledge garden — diagnose vault health, condense project memos into project.md overviews, create/merge cross-project topics, fix broken links, archive superseded notes, extend trails. Trigger on "tend the garden", "condense", "update project overview", "check vault health", "where are we with X?", "what…

linxule/memex-plugin · 131 tokens

diagnose

Use when an AI Brain vault needs a health check or something feels off: Claude ignores CLAUDE.md, journal entries missing from /weekly, hooks not firing, something broke after a git pull, a friend's install misbehaves, Obsidian crashes or pegs the CPU, a .claude/worktrees folder appeared, Granola/WhatsApp/Slack/Gmail…

mycelium-hq/ai-brain-starter · 110 tokens

curator-practice

Operating philosophy for autonomous memex curator tending — orientation protocol, signal triage, bounded work units, initiative thresholds, logging conventions. Trigger on cron-launched runs with no user prompt, "use your judgment", "tend without instructions", "do a pass on the vault", "I'll be away — do what needs…

linxule/memex-plugin · 153 tokens