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 vbcherepanov/total-agent-memory --skill reportgit clone --depth 1 https://github.com/vbcherepanov/total-agent-memoryWrote 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/vbcherepanov/total-agent-memory/report)<a href="https://agentmods.dev/skills/vbcherepanov/total-agent-memory/report"><img src="https://agentmods.dev/badge/skills/vbcherepanov/total-agent-memory/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/vbcherepanov/total-agent-memory/report"><img src="https://agentmods.dev/badge/skills/vbcherepanov/total-agent-memory/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 | $0.00089 | $0.00935 |
| Opus 5.5 | $0.00036 | $0.00374 |
| Sonnet 5.5 | $0.00018 | $0.00187 |
| Haiku 4.5 | $0.00009 | $0.00093 |
Grade A, and why
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 17d 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/report — activity report from memory
The report is built by the memory_report tool (your client may prefix it, e.g.
mcp__memory__memory_report). It is deterministic: numbers, decisions, fixes,
errors, open next steps, files and a daily timeline come straight from stored
records, each with source IDs. If no memory_report tool is available, say the
memory server is not connected (or is older than this skill) and stop.
1. Read the request
Take the period and project from $ARGUMENTS or the user's words:
| The user says | Arguments |
|---|---|
| today, for the day, daily | period: "day" |
| yesterday | period: "day", offset: -1 |
| this week, weekly (default when nothing is said) | period: "week" |
| last week | period: "week", offset: -1 |
| this month, monthly | period: "month" |
| last month | period: "month", offset: -1 |
| all time, ever, since the start | period: "all" |
| from 2026-09-01 to 2026-09-15, since Monday, last 10 days | period: "custom", since: "YYYY-MM-DD", until: "YYYY-MM-DD" (until is inclusive; omit it for "until today") |
- Project: "for project X", "in X", or the current repository/folder name when the
user says "this project". Omit
projectfor "all projects". - Timezone: pass
tz(IANA name, e.g.Europe/Berlin) only when the user names a zone or city; otherwise the server uses the machine's zone. - Team server only: "department X report" →
scope: "team", team_id: "X"; "company report" →scope: "company"; otherwisescope: "personal". AForbiddenerror means the user lacks the department head / company viewer role: say so plainly.
2. Call the tool
Call memory_report with those arguments and format: "markdown". Add
include_llm_summary: true only when the user asks for a written summary or
narrative; it needs a configured LLM and the report is complete without it.
3. Present it concisely
Do not paste the whole report unless asked. Give:
- One line with the period (as the report labels it) and the headline numbers with their change against the previous period (records, decisions, errors, active days).
- The 3–5 most important decisions with their WHY, and the main fixes.
- Recurring error patterns (count this period vs all time) and lessons learned.
- Open next steps and pitfalls that were not picked up yet.
- Anything notable in files, technologies or the timeline (e.g. one very busy day).
What ships with it
1 file 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.
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.
- 17d ago First seen · 73 lines · 89 tokens per session scan A 5ad9336222da
report is a skill published in the GitHub repository vbcherepanov/total-agent-memory (73 stars, last pushed 2d ago), licensed MIT. It adds 89 tokens to every session and 935 once invoked, about $0.0004 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 2026-09-29.
Other skills, from other repositories
status
Render the feature × stage integrity matrix — every feature vs every Iron Law stage with pass/skip/fail markers. Use when the user wants a project-wide status board, a release-readiness view, or to spot which features are still behind which stage. Activate only when the connected project contains spec.yaml or the user…
crm-workflow
Use when the user is working with StudioMeyer CRM and you need to pick the right tool. Covers the Lead → Contact → Deal → Pipeline flow, daily CRM routine, and how to run import/export safely.
yoke-workflow
Use when the user asks Yoke to plan and build a feature, run stories autonomously, continue a Yoke loop, or only interrupt for major decisions.
project-consolidation
Safely consolidate drifted/duplicate project folders in the memex vault — cwd-fragment folders (e.g. Apps-arena, GitHub-loom), duplicate/split projects (one project's content scattered across two folders), and name-mismatch folders. Trigger on "consolidate project folders", "merge duplicate projects", "fix project…
status
Show every codex-claude-loop slug and where it stands (plan/review gates, impl marker, base).
qshipcheck
Validates that all orchestrator Phase 2 (review), Phase 3 (acceptance), and Phase 4 (deliver) steps were executed after qship pipeline completion. Run this after qship finishes to catch any skipped steps.