Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/tomzx/agentsnpx agentmods add skills/tomzx/agents/improve-sessionsWrote 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/tomzx/agents/improve-sessions)<a href="https://agentmods.dev/skills/tomzx/agents/improve-sessions"><img src="https://agentmods.dev/badge/skills/tomzx/agents/improve-sessions/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/tomzx/agents/improve-sessions"><img src="https://agentmods.dev/badge/skills/tomzx/agents/improve-sessions.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 | $0.00098 | $0.01969 |
| Opus 5.5 | $0.00039 | $0.00788 |
| Sonnet 5.5 | $0.00020 | $0.00394 |
| Haiku 4.5 | $0.00010 | $0.00197 |
Grade A, and why
improve-sessions scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 22d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BASE_DIR=!~/.agents/scripts/get-env NOTES_DIR
TODAY=!date +%Y-%m-%d
Improve Sessions
Reads a window of past sessions from the agentsview archive (which syncs OpenCode, Codex, Gemini, Claude, and other harnesses), identifies recurring friction patterns across them, and proposes concrete changes that make future sessions better: AGENTS.md rules, memory entries, new or improved skills, hooks, and scheduled agents.
The analysis is read-only over the archive.
It never advances the sessions-memory watermark, so it can run at any cadence without interfering with memory processing.
Prerequisites
- agentsview archive: a
sessions.dbproduced by the agentsview daemon, resolved by the shared script in this order: explicit--dbflag,$AGENTSVIEW_DATA_DIR, then~/.agentsview/sessions.db. If none exists, tell the user to install and run agentsview first. - Data access comes from the
sessions-memoryscript; do not write a second parser:
uv run skills/sessions-memory/scripts/fetch_sessions.py status
- Read-only discipline: use
fetchandshowonly. Never runcommit, that belongs tosessions-memory; skipping it is safe and only means the same sessions reappear there later.
Scope boundaries
/automate-sessionand/improve-autonomyreflect on the current session. This skill works over historical sessions and only produces recommendations./sessions-memoryturns sessions into memory artifacts. This skill turns them into improvement recommendations, and may hand some findings to it (memory entries) or to/identify-skill-gaps(skill backlog entries).
Steps
1. Scope the window and fetch sessions
uv run skills/sessions-memory/scripts/fetch_sessions.py status
uv run skills/sessions-memory/scripts/fetch_sessions.py fetch --since 2026-09-11 --min-user-messages 2 --limit 30
Defaults when the user gives no window: the last 14 days, limit 30.
Raise --max-content (or set 0) when transcripts need to be read in full, and use show <id> for deep dives on specific sessions.
Sessions with fewer than two user messages offer little to improve, so --min-user-messages 2 is the default lens here.
The script also excludes deleted sessions, automated runs, subagents, and scheduler-triggered runs (title carries the run timestamp); pass --include-scheduled when a scheduled run itself is under review.
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.
- 22d ago Changed · -20 lines f32dadfafb5b
- 25d ago Changed 23bdb0a625c7
- 28d ago First seen · 205 lines · 98 tokens per session scan A 2234cb0f21be
improve-sessions is a skill published in the GitHub repository tomzx/agents (13 stars, last pushed yesterday), licensed MIT. It adds 98 tokens to every session and 1,969 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 2026-10-01.
Other skills, from other repositories
knowledge-ingest
Ingest documents, articles, conversations, or supplied text into Knowledge with retained originals, sourced claims, entity updates, source notes, and cross-links; also learn durable lessons from a set of conversations, transcripts, or past sessions (/learn), including the Learn from conversations and Learn from Memory…
mem0-oss-to-platform
Plan, then execute, a migration of a project from the mem0 open-source / self-hosted SDK (local Memory class) to the mem0 Platform / hosted SDK (MemoryClient). TRIGGER when: the developer wants to move, switch, or migrate mem0 off OSS/self-hosted to the hosted API, e.g. "migrate my mem0 setup to the platform", "switch…
forget
Remove a personal fact, preference, relationship detail, topic, or prior event from Muse's active memory and stop existing copies or automations from bringing it back. Use for explicit requests such as 'forget that', 'don't remember this about me', or 'remove that from your memory'. Do not use when 'forget it' merely…
Cortex
LifeOS memory, prior-session recall, and learning capture. USE WHEN capture this learning, document this learning, what did we learn recently, recent learnings, cortex, knowledge, knowledge base, search knowledge, what do we know about, archive, harvest, knowledge status, develop note, add to knowledge, add a people…
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.
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…