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.
git clone --depth 1 https://github.com/conorbronsdon/agent-memory-kitWrote 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/commands/conorbronsdon/agent-memory-kit/start)<a href="https://agentmods.dev/commands/conorbronsdon/agent-memory-kit/start"><img src="https://agentmods.dev/badge/commands/conorbronsdon/agent-memory-kit/start/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/commands/conorbronsdon/agent-memory-kit/start"><img src="https://agentmods.dev/badge/commands/conorbronsdon/agent-memory-kit/start.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 | $0.00016 | $0.00423 |
| Opus 5.5 | $0.00006 | $0.00169 |
| Sonnet 5.5 | $0.00003 | $0.00085 |
| Haiku 4.5 | $0.00002 | $0.00042 |
Grade A, and why
start 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 1mo 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.
What it actually says
/start — Begin Session
Recall: load the context, state, and memory index so you know where things stand before doing anything.
1. Date
Run date +%Y-%m-%d (TODAY) and note the day of week.
2. What changed since last session
Find the most recent session log, then:
git log --oneline --since="<last session date>"
Flag any context or state files modified since the last session — these may hold updates from another agent run or a manual edit. Mention changed files in the briefing.
3. Load context (in order)
CONTEXT.md— who the user is + routing rules.state/current.md— active priorities, open threads, recent context.memory/MEMORY.md— the memory index (one line per durable fact). Pull a detail file only if a line looks relevant to today.sessions/{TODAY}.mdif it exists (resuming today), else the most recentsessions/*.mdfor continuity.
4. State freshness
Check the "Last updated" line on state files and flag staleness — this catches drift from skipped /end runs.
| File | Stale if | Flag |
|---|---|---|
state/current.md |
> 3 days | "⚠ current.md is N days stale" |
If fresh, one line: "State: fresh."
5. Brief
Keep it short:
- Date and day.
- State freshness (one line if fresh).
- Files changed since last session (one line each, or "no changes").
- Top 2–3 priorities from
state/current.md. - Time-sensitive open threads.
- Ask what to focus on.
If resuming today's session, acknowledge what's already covered and pick up from there.
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.
- 1mo ago First seen · 53 lines · 16 tokens per session scan A d04dc14325c3
start is a command published in the GitHub repository conorbronsdon/agent-memory-kit (2 stars, last pushed 23d ago), licensed MIT. It adds 16 tokens to every session and 423 once invoked, about $0.0001 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 2026-08-31.
Other commands, from other repositories
pull-learnings
Pulls shared organization patterns into local org-patterns.toon.
patterns
Scan recent sessions for recurring patterns and turn them into captures (rules, concept notes, writing seeds).
using-pensyve
Show available Pensyve memory tools, skills, and commands.
memory-status
Show Pensyve memory namespace statistics and health overview.
recall
Search Pensyve memory by semantic similarity and text matching.
forget
Delete all memories for an entity from Pensyve.