eval-memory

A procedure for checking both the health and actual usefulness of a personal-knowledge memory system. It compares reordered search results with unmodified retrieval using a fixed test set and an independent assessment.

In plain words
What is it for?
Use it to run read-only memory checks, assess whether automatic learning improves retrieval, and record results over time.
Why use it?
Growing activity numbers do not prove that memory search has improved, especially when past searches influence future results.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/pcamarajr/personal-knowledge/eval-memory
Any agent
npx skills add pcamarajr/personal-knowledge --skill eval-memory
Clone the repo
git clone --depth 1 https://github.com/pcamarajr/personal-knowledge

Made for: Claude Code, Codex.

Per session 104 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,373 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00104 $0.02373
Opus 5 $0.00052 $0.01187
Sonnet 5 $0.00021 $0.00475
Haiku 4.5 $0.00010 $0.00237

Measured yesterday against content hash 8bc362150fbd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

eval-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 yesterday.

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.

.claude/skills/eval-memory/SKILL.md · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.

eval-memory — memory system health & efficacy runner

You are the runner. This skill is a procedure you execute live, mostly quiet, pausing to converse only where the user's judgment matters (the verdict and the dashboard gap). Default runs are read-only and safe to run unattended.

The one idea that makes this non-trivial

Every autolearn signal is self-referential: co-access feeds re-rank, which shapes what co-surfaces, which feeds co-access. So "the numbers are growing" proves activity, not improvement — it can be a self-confirming loop. The only way to claim "it's working" is a ground-truth judge external to the signal loop. That judge is you, ruling blind on whether re-ranked retrieval beats raw retrieval. Protect that blindness or the whole eval is theater.

Config (read, don't hardcode elsewhere)

  • Server base URL: http://127.0.0.1:7345 (from MEMORY_HTTP_HOST/MEMORY_HTTP_PORT in .env).
  • Repo data dir: data/ (gitignored). Key files: search-history.json, auto-signals.json, .autolearn-state.json, autolearn.config.json.
  • Frozen probe set: eval/probe-set.json (local, gitignored — copy from eval/probe-set.example.json and author your own; the controlled ruler — see Q4 below).
  • Outputs: eval/ledger.jsonl (trend, append-only) and eval/reports/<YYYY-MM-DD>.md (narrative).

Procedure

Phase 0 — Setup (quiet)

  1. Read eval/probe-set.json. If missing, stop and tell the user to seed it (see "Seeding" below).
  2. GET /health/detail. Record autolearn_level, totals, last_flip_at, last_backup_*, and whether learning_stats is present.
  3. Read the last few rows of eval/ledger.jsonl (if any) for trend comparison.

Phase 1 — Health (quiet batch, Q9/B)

Collect, don't narrate each item. Three layers:

  • Plumbing: /health reachable; /health/detail.autolearn_level == expected (activation per current .env); totals sane vs ledger; learning_stats present iff level==activation.
  • Freshness (high-value — catches a silently-dead 60s flush timer): is auto-signals.json and search-history.json mtime / newest-entry ts recent relative to known activity? A stale file at activation level is a red flag — learning has quietly stopped while everything looks fine.
  • Corpus hygiene: run analyze_subject on the top live subjects (your most active projects and the memory system) and/or scan totals for: orphans, untagged, state past expected_until, decisions-without-outcomes, contradictions, and obvious noise (test/tombstone/probe records). Produce a compact health summary with PASS/WARN/FAIL per check.

Read the full file on GitHub · 146 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. yesterday First seen · 146 lines · 104 tokens per session scan A 8bc362150fbd

Subscribe to this mod's changes

eval-memory is a skill published in the GitHub repository pcamarajr/personal-knowledge (0 stars, last pushed 2mo ago), licensed MIT. It adds 104 tokens to every session and 2,373 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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.

obra/superpowers · 37 tokens

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.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens

agent-host-chat-contributions

Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.

microsoft/vscode · 56 tokens

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.

microsoft/vscode · 62 tokens