memory-close-session

A session-closing guide for a memory system in testing. It records what happened, the next step, aging inbox items, project context, pending promotions, and summaries for the next session.

In plain words
What is it for?
Use it to write a session summary, review stale memory items, update active context, promote eligible records, and prepare memory for the next session.
Why use it?
It prevents useful decisions and unfinished work from being lost when a coding session ends.

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/pyros-projects/limitless/memory-close-session
Any agent
npx skills add pyros-projects/limitless --skill memory-close-session
Clone the repo
git clone --depth 1 https://github.com/pyros-projects/limitless

Made for: Claude Code, Codex.

Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,171 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 $0.00058 $0.01171
Opus 5 $0.00029 $0.00585
Sonnet 5 $0.00012 $0.00234
Haiku 4.5 $0.00006 $0.00117

Measured 2d ago against content hash 9aa17a17db3e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

memory-close-session 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 2d 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/codies-memory/skills/memory-close-session/SKILL.md · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Memory Close Session

BETA — This memory system is in active testing. If you encounter bugs, confusing behavior, or have suggestions, run: codies-memory feedback "describe what happened" — your feedback is saved and reviewed.

When To Use

At the end of every work session.

What It Does

  1. Write session summary with next_step
  2. Optionally write a dream (see "Dream at Sign-Off" below)
  3. Review inbox items older than 7 days
  4. Enforce 14-day inbox aging rule (promote, compact, or discard stale items)
  5. Update project active context
  6. Evaluate pending promotions
  7. Rebuild warm summaries so the next boot sees updated project summaries and recent episodes

How To Run

# 1. Write session summary
AGENT="your-agent-name"
TODAY="$(python - <<'PY'
from datetime import date
print(date.today().isoformat())
PY
)"

codies-memory create session \
  --agent "$AGENT" \
  --title "Session Summary - $TODAY" \
  --short "one-line summary of the session" \
  --body "## What Happened\n- [describe what was done]\n\n## Decisions Made\n- [list decisions]\n\n## Next Step\n- [what the next session should pick up]" \
  --field mode=implement \
  --field next_step="[what to do next]"

# This automatically appends to the global daily log. If no named project vault
# resolves, the session lands in the reserved _general project vault.

# 2. Check inbox aging and status
codies-memory status --agent "$AGENT"

# 3. Run promotion evaluation
uv run python -c "
from codies_memory.records import list_records
from codies_memory.promotion import evaluate_for_promotion
from codies_memory.vault import resolve_global_vault, resolve_project_vault
from pathlib import Path

agent = 'your-agent-name'
global_vault = resolve_global_vault(agent)
project_vault = resolve_project_vault(global_vault, Path.cwd())
if project_vault is None:
    print(f'No named project vault found for {Path.cwd()}; skipping project promotion evaluation.')
else:
    for rtype in ['inbox', 'thread']:
        items = list_records(project_vault, rtype, scope='project', status='active')
        for item in items:
            result = evaluate_for_promotion(item, context={'session_count': 1})
            if result['eligible']:
                print(f'  Promote {rtype}: {item[\"frontmatter\"][\"title\"][:60]}')

"

# 4. Refresh warm summaries
codies-memory refresh --agent "$AGENT"

Read the full file on GitHub · 128 lines

Files

What ships with it

2 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.

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. 2d ago First seen · 128 lines · 58 tokens per session scan A 9aa17a17db3e

Subscribe to this mod's changes

memory-close-session is a skill published in the GitHub repository pyros-projects/limitless (9 stars, last pushed 20d ago), licensed MIT. It adds 58 tokens to every session and 1,171 once invoked, about $0.0003 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.