Claude-Mem, now presented as Grok Mem, records an agent's work, compresses it with AI, and brings relevant notes into later sessions so the agent can remember decisions and next steps. It is intended for persistent context across agent conversations and supports multiple coding-agent environments. The catalogue add-ons provide the workflows and integrations used to operate this memory system.
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 skills add thedotmack/claude-mem --skill agent-cost-reportgit clone --depth 1 https://github.com/thedotmack/claude-memWrote 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/thedotmack/claude-mem/agent-cost-report)<a href="https://agentmods.dev/skills/thedotmack/claude-mem/agent-cost-report"><img src="https://agentmods.dev/badge/skills/thedotmack/claude-mem/agent-cost-report/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.
<a href="https://agentmods.dev/skills/thedotmack/claude-mem/agent-cost-report"><img src="https://agentmods.dev/badge/skills/thedotmack/claude-mem/agent-cost-report.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00075 | $0.05116 |
| Opus 5.5 | $0.00030 | $0.02046 |
| Sonnet 5.5 | $0.00015 | $0.01023 |
| Haiku 4.5 | $0.00007 | $0.00512 |
Grade A, and why
Agent Cost Report 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 15d 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 — 242 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Cost Report
Claude-Mem / Claude Code skill. Runtime is the scripts/ pipeline (transcripts → tokens → dollars → Timing-style report) plus a progressive Mem Search review pass that confirms the drafted labels. The Notion draft is SPEC history only — never the product, never the runtime, never the ship vehicle.
Resolve the absolute directory containing this SKILL.md; all helper paths are relative to that directory. ${CLAUDE_SKILL_DIR} is the shortcut: python3 "${CLAUDE_SKILL_DIR}/scripts/acr.py" …. Python 3.9+ standard library only, with IANA timezone data for America/Los_Angeles; no pip installs. tzdata is the only exception to the no-pip-installs rule, and only when acr.py exits saying that timezone data is unavailable (stock Windows Python ships none): show the user the lines it printed and ask (AskUserQuestion) before installing it. On a yes, run the line for your shell (the plain quoted line in Bash or cmd, the PowerShell: line in PowerShell), then rerun the failed command. Setting PYTHONTZPATH instead needs no install. The look lives in scripts/acr/render.py, never here.
Purpose
Turn Claude-Mem activity into a manager-readable cost and failure report.
Product idea: a reusable skill that searches Claude-Mem via Mem Search, reconstructs real units of work, assigns cost and failure categories, and renders a printable report.
Insight north star
The headline is dollars, to two decimals, labeled. The dollars come from Claude Code transcripts (exact per-reply token usage) priced at OpenRouter public list prices, so they are ESTIMATED. Measured provider spend appears only when a sanctioned source gives it. Directly under the dollars: what the mistakes cost, what shipped, and both on one time axis.
Questions the report must answer
- What work was completed?
- What did each outcome cost?
- What was wasted through looping, hedging, wrong turns, rework, or poor routing?
- Were any unauthorized actions attempted?
- What should the manager change next?
What ships with it
51 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- .gitignore 100 B
- CHECKSUMS.txt 4.7 KB
- scripts/acr.py 12 KB runs code
- scripts/acr/__init__.py 105 B runs code
- scripts/acr/behavior.py 16 KB runs code
- scripts/acr/classify.py 5.5 KB runs code
- scripts/acr/costs.py 6.3 KB runs code
- scripts/acr/devices.py 5.4 KB runs code
- scripts/acr/evidence.py 9.2 KB runs code
- scripts/acr/labels.py 7.0 KB runs code
- scripts/acr/measure.py 5.6 KB runs code
- scripts/acr/mistakes.py 23 KB runs code
- scripts/acr/patterns.py 25 KB runs code
- scripts/acr/period.py 3.8 KB runs code
- scripts/acr/prices.py 5.0 KB runs code
- scripts/acr/render.py 53 KB runs code
- scripts/acr/rollup.py 31 KB runs code
- scripts/acr/rules.json 3.5 KB
- scripts/acr/rules.py 4.4 KB runs code
- scripts/acr/sample.py 3.6 KB runs code
- scripts/acr/snapshot.py 2.0 KB runs code
- scripts/acr/sync.py 3.4 KB runs code
- scripts/acr/transcripts.py 7.4 KB runs code
- scripts/acr/wins.py 21 KB runs code
- scripts/tests/_db.py 3.6 KB runs code
- scripts/tests/_paths.py 337 B runs code
- scripts/tests/fixtures/codex/sessions/2026/09/18/rollout-codex-1.jsonl 664 B
- scripts/tests/fixtures/make_report_fixtures.py 2.0 KB runs code
- scripts/tests/fixtures/prices_sample.json 611 B
- scripts/tests/fixtures/projects/-workspace-proj-a/sess-aaaa.jsonl 2.9 KB
- scripts/tests/fixtures/projects/-workspace-proj-b/sess-bbbb.jsonl 537 B
- scripts/tests/fixtures/report-1day.json 20 KB
- scripts/tests/fixtures/report-30day.json 48 KB
- scripts/tests/fixtures/report-7day.json 29 KB
- scripts/tests/fixtures/report-empty.json 14 KB
- scripts/tests/fixtures/report-session.json 17 KB
- scripts/tests/test_behavior.py 19 KB runs code
- scripts/tests/test_devices.py 6.5 KB runs code
- scripts/tests/test_labels.py 6.1 KB runs code
- scripts/tests/test_measure.py 6.8 KB runs code
- scripts/tests/test_pdf_windows.py 2.6 KB runs code
- scripts/tests/test_period.py 7.0 KB runs code
- scripts/tests/test_prices.py 5.3 KB runs code
- scripts/tests/test_render_encoding.py 3.3 KB runs code
- scripts/tests/test_render.py 12 KB runs code
- scripts/tests/test_rollup.py 19 KB runs code
- scripts/tests/test_snapshot.py 2.5 KB runs code
- scripts/tests/test_sync.py 2.8 KB runs code
- scripts/tests/test_transcript_encoding.py 6.2 KB runs code
- scripts/tests/test_transcripts.py 8.4 KB runs code
- scripts/tests/test_wins.py 16 KB runs 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.
- 15d ago Changed 40b6e0045dbe
- 24d ago First seen · 242 lines · 75 tokens per session scan A a8388ef9d748
Agent Cost Report is a skill published in the GitHub repository thedotmack/claude-mem (101,962 stars, last pushed today), licensed Apache-2.0. It adds 75 tokens to every session and 5,116 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 2026-09-27.
Other skills, from other repositories
hivemind-goals
Create, track and update team goals via the Deeplake virtual filesystem at memory/goal/. Use whenever the user mentions a goal, objective, target, milestone, or asks to track progress on something measurable. ALSO use when the user says "task", "todo", "work item", "remind me to", "fix X", or any actionable work item…
hivemind-memory
Global team and org memory powered by Activeloop. ALWAYS check BOTH built-in memory AND Hivemind memory when recalling information.
hivemind-memory
Global team and org memory powered by Activeloop. ALWAYS check BOTH built-in memory AND Hivemind memory when recalling information.
hivemind-graph
Query the local code graph (functions, classes, calls, imports) through the Deeplake mount at memory/graph/. Use when the user asks structural questions about the codebase — "what calls X?", "what does Y import?", "where is Z defined?", "what's the architecture / which subsystems exist?", "what's the impact of…
hivemind
Global team and org memory powered by Activeloop. ALWAYS check BOTH built-in memory AND Hivemind memory when recalling information.
dejavu
Review and manage learned antipattern rules. Use when Claude should review its past mistakes, apply learned rules to CLAUDE.md, or check rule effectiveness. Triggers on "/dejavu", "review rules", "what did you learn".